KENDRIYA VIDYALAYA SANGATHAN HYDERABAD REGION

MODEL QUESTION PAPER - 11

2024-25
CLASS:X TIME:02 HOURS
SUBJECT: ARTIFICIAL INTELLEGENCE MAX.MARKS:50

SECTION A: OBJECTIVE TYPE QUESTIONS

Q. 1 Marks
Answer any 4 out of the given 6 questions on Employability Skills (1 x 4 = 4 marks)
1 Direction: In the questions given below, there are two statements marked as Assertion 1M
(A) and Reason (R). Choose the correct option out of the choices given below in each
question:
Assertion (A): To communicate well in the classroom is a natural ability.
Reason (R): Effective teaching in the classroom demands knowledge of the
communication process.
a) Both (A) and (R) are correct and (R) is the correct explanation of (A).
b) Both (A) and (R) are correct and (R) is not the correct explanation of (A).
c) (A) is True but (R) is False.
d) (A) is False but (R) is True.
2 ________________ refers to focusing human efforts for maintaining a healthy body and 1M
mind capable of better withstanding stressful situations.
a) Mental Healthb) Emotional Healthc) Self-Managementd) Stress Management
3 Kiran gets up at 5:30 am and goes for his hobby classes. Then he comes back home and 1M
finishes his homework before going to school. He does all work by himself. No one tells
him to do so. This is called ___________.
a) Self-Awareness b) Self-Motivation c) Self-Regulation d) Discipline
4 __________ act as an interface between the user and the computer. 1M
a) Operating Systemb) MS Excelc) Impressd)Robot
5 The aim of Sustainable development goals is 1M
a) to inculcate the value of self-resistance amongst the people
b) to save natural resources for everyone
c) to utilize judiciously and ensure its availability for future generations
d) All of these
6 Nitya decides to sell her company tyres in Sri Lanka. It does not sell and she has a loss. 1M
She apologises to the people who work for her. She says she will plan better next time.
She _________.
a) thinks before deciding b) does not give up
c) takes responsibility for her mistakesd)is creative

Q. 2 Answer any 5 out of the given 6 questions (1 x 5 = 5 marks)

1 Which of the following is Not AI? 1M
i) Air Conditioner
ii) Automatic Washing Machine
iii) Self-Driving Car
iv) Smart TV
a)i, ii & iiib)i& iic)i, ii & ivd) iii & iv
 2 ___________ means collecting data from web using some technologies. 1M
a) Robotics
b) Kinematics
c) Lifting
d) Web Scraping
3 Statement1: A neural network is a group of algorithms that simulates the way the 1M
human brain works
Statement2: It attempts to identify brain cells in a set of data.
a) Both Statement1 and Statement2 are correct
b) Both Statement1 and Statement2 are incorrect
c) Statement1 is correct but Statement2 is incorrect
d) Statement2 is correct but Statement1 is incorrect
4 In neural network terminology, additional layers between the input layer and the 1M
output layer are called ___________.
a) hidden layersb) input layersc) removal layersd) output layers
5 The _________ module implements classes to read and write tabular data in CSV 1M
format.
a) math b) statistics c) db d) csv
6 Assertion (A): Natural Language Processing (NLP) deals with interaction between 1M
human and computer systems using common and frequently spoken languages like
Hindi, English, etc.
Reasoning (R): Spell-check feature is an implementation of NLP.
a) Both A and R are true and R is the correct explanation of A.
b) Both A and R are true but R is not the correct explanation of A.
c) A is true but R is false.
d) A is false but R is true.

Q. 3 Answer any 5 out of the given 6 questions (1 x 5 = 5 marks)

1 _____________ refer to the type of data you want to collect. 1M

a) test datab) data featuresc) board datad) training data
2 In ______________ model, the dataset which is fed to the machine is labelled. 1M
a)unsupervised learning b) reinforcement learning
c) supervised learning d) record learning
3 Data science is useful in 1M
a) Better decision-making b)Improved efficiency
c) Predictive analytics d)All of the above
4 What does segmentation in Computer Vision refer to? 1M
a) Enhancing image details b) Dividing an image into parts or regions
c) Reducing image size d) Increasing image resolution
5 ___________, refers to the process of reducing a word to its word stem that affixes to 1M
suffixes and prefixes or the roots.
a) Bag of words (BOW)
b) Dictionary
c) Clause
d) Stemming
6 When the prediction is False and reality is True, that condition is called……….. 1M
a) TNb) TFc) FPd) FN
Q. 4 Answer any 5 out of the given 6 questions (1 x 5 = 5 marks)
 1 Karunya wants to know who works with the data science team to define the problem 1M
and develop a strategy for analysis. Can you identify them in the list below?
a)Business managers b)IT managers c)Data science managers d)AI Engineers
2 Statement1: The primary purpose of evaluation in the AI project cycle is to check the 1M
reliability of the AI model.
Statement2: It helps determine if the model is performing as expected and if it can
make accurate predictions or classifications based on the test dataset.
a) Both A and R are true and R is the correct explanation of A.
b) Both A and R are true but R is not the correct explanation of A.
c) A is true but R is false.
d) A is false but R is true.
3 Reena advised Karan to learn _________ language as it is the most popular data science 1M
languages in the last several years. Which of the following is it?
a) Java b)Python c)Scala d)PHP
4 In computer vision and image processing, a _________ is a piece of information which 1M
is relevant for solving the computational task related to a certain application.
a)language b)number c)mobile d)feature
5 What is NLTK tool in Python? 1M
a) Natural Linguistics Toolb) Natural Language Toolkit
c) Neutral Linguistics Kitd) Neutral Language Toolkit
6 Surjit wants to know the formula for precision. Can you identify it from the list below? 1M
a) FP/TP+FP*100% b) TN/TP+FP*100%
c)TP/TP+FP*100% d) FN/TP+FP*100%
Q. 5 Answer any 5 out of the given 6 questions (1 x 5 = 5 marks)

1 Anthony was surprised when he observed that most of the virtual assistants had a 1M
female voice. This is an example of_________.
a)AI Access b) AI Bias c) Remote Sensor d) Virus
2 _________ can be defined as the fraction of positive cases that are correctly identified. 1M
a) F1 Score b) Accuracy c) Recall d) Precision
3 Find the odd one out. 1M
a)Blue b)Yellow c)Green d)Red
4 Automatic Summarization, Sentiment Analysis, Text classification, Virtual Assistants are 1M
some of the applications of _________.
a)Bit coinb)Data Sciencec)Natural Language Processing d)Computer Vision
5 If the model’s output does not match with the true function at all. Then the model is 1M
said to be ________
a)underfitting b) overfitting c) perfect d) unbiased
6 Everything that is sent to the machine has to be converted to _________. 1M
a)coins b)numbers c)images d)papers

SECTION B: SUBJECTIVE TYPE QUESTIONS

Answer any 3 out of the given 5 questions on Employability Skills (2 x 3 = 6 marks)
Answer each question in 20 – 30 words.
Q 6 List the different types of verbal communication? 2M
Q .7 What is stress? Enlist few simple stress management techniques. 2M
Q 8 Define hardware and software in Computer systems. 2M
Q .9 Write any two qualities of an Entrepreneur. 2M
Q 10 How can we become responsible about our own environment? 2M
Answer any 4 out of the given 6 questions in 20 – 30 words each (2 x 4 = 8 marks)

Q 11 What is a problem statement template and what is its significance? 2M

Q .12Define AI Project Cycle, Name all the stages of an AI Project cycle. 2M
Q 13 Jubedha wants to know the applications of Data Science. Can you help her? 2M
Q .14Define the following terms with respect to Computer Vision 2M
a)Classification
b)Instance Segmentation
Q 15 Briefly discuss any two of the following: 2M
a)lemmatisation
b)Bag–of-words
c)TF-IDF
d)case normalisation
Q 16 Ram wants to know why evaluation is important in AI Project cycle. Help him 2M
understand?
Answer any 3 out of the given 5 questions in 50– 80 words each (4 x 3 = 12 marks)

Q.17 What do you understand by AI, ML & DL? How are they different from each other? 4M
Q.18 Discuss about Problem Statement Template in detail. 4M
Q.19 Shahid has a doubt on the learning based approach to modelling. Can you explain him 4M
what it is all about?
Q.20 Niharika wants to the use of Chatbots. Explain her with suitable examples. 4M
Q.21 What do you know about Confusion Matrix? 4M

KENDRIYA VIDYALAYA SANGATHAN HYDERABAD REGION

ARTIFICIAL INTELLIGENCE (SUBJECT CODE - 417)
Class X
Model Question Paper – 11 (Solutions)

SECTION A: OBJECTIVE TYPE QUESTIONS

Q. 1 Marks
Answer any 4 out of the given 6 questions on Employability Skills (1 x 4 = 4 marks)
1 d) (A) is False but (R) is True 1M
2 d) Stress Management 1M
3 b) Self-Motivation 1M
4 a) Operating System 1M
5 d) All of these 1M
6 c) takes responsibility for her mistakes 1M
Q. 2 Answer any 5 out of the given 6 questions (1 x 5 = 5 marks)
1 c)i, ii & iv 1M
2 d) Web Scraping 1M
3 c) Statement1 is correct but Statement2 is incorrect 1M
4 a) hidden layers 1M
 5 d) csv 1M
6 b) Both A and R are true but R is not the correct explanation of A. 1M
Q. 3 Answer any 5 out of the given 6 questions (1 x 5 = 5 marks)
1 b) data features 1M
2 c) supervised learning 1M
3 d)All of the above 1M
4 b) Dividing an image into parts or regions 1M
5 d) Stemming 1M
6 d) FN 1M
Q. 4 Answer any 5 out of the given 6 questions (1 x 5 = 5 marks)

1 a)Business managers 1M
2 a) Both A and R are true and R is the correct explanation of A. 1M
3 b)Python 1M
4 d)feature 1M
5 b) Natural Language Toolkit 1M
6 c)TP/TP+FP*100% 1M
Q. 5 Answer any 5 out of the given 6 questions (1 x 5 = 5 marks)

1 b) AI Bias 1M
2 c) Recall 1M
3 b)Yellow 1M
4 c)Natural Language Processing 1M
5 a)underfitting 1M
6 b)numbers 1M

SECTION B: SUBJECTIVE TYPE QUESTIONS

Answer any 3 out of the given 5 questions on Employability Skills (2 x 3 = 6 marks)
Answer each question in 20 – 30 words.
Q 6 a) Interpersonal Communication 2M
b) Written Communication
c)Group Communication
d)Public Communication
Q .7 Stress can be defined as our emotional, mental, physical and social reaction to any 2M
perceived demands or threats
Here are a few simple stress management techniques. (Any two)
a) Time management
b) Positivity
c)Physical Exercise and Fresh Air
d)Healthy Diet
e) Holidays with Family and Friends
f) Good Sleep
g) Organising your work and not delaying
 Q 8 Hardware refers to the physical and visible components of the system such as a 2M
monitor, CPU, keyboard and mouse.
Software refers to a set of instructions which enable the hardware to perform a specific
set of tasks. Software is a generic term used to refer to applications, scripts and
programs that run on a device.
Q .9  They are confident: Entrepreneurs are confident beings. They decide to take up 2M
a venture and it is their confidence that ensures survival and success of their
idea.
 They try new and innovative ideas: Entrepreneurs introduce new and innovative
ideas in the market. Sometimes, such ideas may even displace the inefficient
players from the market.
 They are creative: Entrepreneurs are creative people. They always try to find
opportunities for a better product/service through their creativity.
 They show patience: Entrepreneurs are resilient people. They wait till the
venture succeeds. This quality also helps them deal effectively with their
employees.
 Perseverance: Entrepreneurs show perseverance as any small hurdle doesn’t
stop them from achieving their ambitions. They keep on working towards
fulfilment of their ambition.
 Takes responsibility: Entrepreneurs take responsibility to successfully execute
the business idea into a full-fledged profit-making enterprise.
 Have leadership Skills: Entrepreneurs are leaders as well. They have the
responsibility to lead the venture towards its Organisational Vision. Further,
they also lead the team of employees and guide them to work effectively
towards Organisational Goals.
 Hard working: Entrepreneurs work hard, especially in the initial phase of
venture. This quality ensures that they keep on working with passion and
dedication.
 Take calculated risk: Entrepreneurs take calculated risk, which pays them off
well as they always keep in mind the Risk-Reward ratio.
 Never Give Up spirit: Entrepreneurs don’t give up easily. This persist with their
efforts and always try to turn things around.
(Any two valid points)
Q 10 We can become responsible about our own environment by 2M
1. Reusing paper, glass, plastic, water, etc.
2. Taking cloth bags to market carrying fruits and vegetables.
3. Donate things we do not use such as clothes, books, furniture, food, etc.
4. Buy and eat seasonal fruits and vegetables from local growers.
5. Repair leaking taps and pipes to avoid wasting water.
6. Sort and treat garbage before disposing
(Any two valid points)
Answer any 4 out of the given 6 questions in 20 – 30 words each (2 x 4 = 8 marks)

Q 11 The problem statement template gives a clear idea about the basic framework required to 2M
achieve the goal. It is the 4Ws canvas which segregates; what is the problem, where does it
arise, who is affected, why is it a problem? It takes us straight to the goal.
Q Project Cycle is a step-by-step process to solve problems using proven scientific methods 2M
.12 and drawing inferences about them. The AI Project Cycle provides us with an appropriate
framework which can lead us towards the goal.
The AI Project Cycle mainly has 5 stages: They are
 a) Problem Scoping b) Data Acquisition c) Data Exploration d) Modelling e) Evaluation.

Q 13 a) Predictive maintenance: Predicting equipment failures and scheduling maintenance. 2M

b) Fraud detection: Identifying unusual patterns and anomalies to detect fraud.
c) Recommendation systems: Personalized product recommendations based on user
behavior.
d) Healthcare: Analyzing medical data to improve patient outcomes and reduce costs.
e) Customer segmentation: Grouping customers based on behavior and preferences.
f) Supply chain optimization: Optimizing logistics and inventory management.
g) Image and speech recognition: Developing AI-powered recognition systems.
h) Climate change analysis: Analyzing data to understand and mitigate climate change.
i) Business intelligence: Informing business decisions with data-driven insights.
j) Social media analysis: Analyzing social media data to understand public opinions and
trends.
(Any two valid points)
Q a)Classification 2M
.14 Image Classification problem is the task of assigning an input image one label from a fixed
set of categories. This is one of the core problems in CV that, despite its simplicity, has a
large variety of practical applications.
b)Instance Segmentation
Instance Segmentation is the process of detecting instances of the objects, giving them a
category and then giving each pixel a label on the basis of that. A segmentation algorithm
takes an image as input and outputs a collection of regions (or segments).
Q 15 a)lemmatisation 2M
It is the process of converting a word to its actual root form linguistically.
b)Bag–of-words
Bag – of-words is a model used for extracting features from text for use in modelling, with
many AI algorithms.
c)TF-IDF
TF-IDF refers Term Frequency-Inverse Document Frequency.TF-IDF is a statistical measure
that evaluates how relevant a word is to a document in a collection of documents.
d)case normalisation
Case normalisation refers to conversion of all the words in the samecase. (often lower
case)
Q 16 In the Evaluation stage, we will explore different methods of evaluating an AI model. 2M
Model Evaluation is an integral part of the model development process. It is important as it
helps to find the best model that represents our data and how well the chosen model will
work in the future.

Answer any 3 out of the given 5 questions in 50– 80 words each (4 x 3 = 12 marks)

Q.17 a) Artificial Intelligence (AI) 4M

Refers to any technique that enables computers to mimic human intelligence. It gives the
ability to machines to recognize a human’s face; to move and manipulate objects; to
understand the voice commands by humans, and also do other tasks. The AI-enabled
machines think algorithmically and execute what they have been asked for intelligently.
b) Machine Learning (ML)
It is a subset of Artificial Intelligence which enables machines to improve at tasks with
experience (data). The intention of Machine Learning is to enable machines to learn by
themselves using the provided data and make accurate Predictions/ Decisions.
 c) Deep Learning (DL)
It enables software to train itself to perform tasks with vast amounts of data. In Deep
Learning, the machine is trained with huge amounts of data which helps it in training itself
around the data. Such machines are intelligent enough to develop algorithms for
themselves. Deep Learning is the most advanced form of Artificial Intelligence out of these
three. Then comes Machine Learning which is intermediately intelligent and Artificial
Intelligence covers all the concepts and algorithms which, in some way or the other mimic
human intelligence.
Q.18 The 4W’s of Problem Scoping are Who, What, Where, and Why. 4M
This 4W’s helps in identifying and understanding the problem in a better and efficient
manner.
 Who - “Who” part helps us in comprehending and categorizing who all are affected
directly and indirectly with the problem and who are called the Stake Holders.
 What - “What” part helps us in understanding and identifying the nature of the
problem and under this block, you also gather evidence to prove that the problem
you have selected exists.
 Where - "Where” does the problem arise, situation, context, and location?
 Why - “Why” is the given problem worth solving?
After filling the 4Ws Problem canvas, we need to summarise all the cards into one
template.

The Problem Statement Template helps us to summarise all the key points into one single
Template so that in future, whenever there is need to look back at the basis of the
 problem, we can take a look at the Problem Statement Template and understand the key
elements of it.
Q.19 Learning based approach refers to the AI modelling where the machine learns by itself. 4M
Under the Learning Based approach, the AI model gets trained on the data fed to it and
then is able to design a model which is adaptive to the change in data. That is, if the model
is trained with X type of data and the machine designs the algorithm around it, the model
would modify itself according to the changes which occur in the data so that all the
exceptions are handled in this case.

The learning-based approach can further be divided into three types:

a)Supervised Learning
In a supervised learning model, the dataset which is fed to the machine is labelled. In other
words, we can say that the dataset is known to the person who is training the machine
only then he/she is able to label the data.
There are two types of Supervised Learning models:
i. Classification: Where the data is classified according to the labels.
ii. Regression: Such models work on continuous data.
b)Unsupervised Learning
An unsupervised learning model works on unlabelled dataset. This means that the data
which is fed to the machine is random and there is a possibility that the person who is
training the model does not have any information regarding it.
c)Reinforcement learning (RL)
Reinforcement learning is a machine learning technique that trains software to make
decisions to achieve the most optimal results. It mimics the trial-and-error learning process
that humans use to achieve their goals. Software actions that work towards your goal are
reinforced, while actions that detract from the goal are ignored. RL algorithms use a
reward-and-punishment paradigm as they process data. They learn from the feedback of
each action and self-discover the best processing paths to achieve final outcomes.
Q.20 A chatbot is a software application or web interface that is designed to mimic human 4M
conversation through text or voice interactions. The following are some of the advantages
we have with chatbot:
i)Provide fast answers to customer inquiries
Chatbots answer customer questions quickly, around the clock.
ii)Give personalized services and suggestions
Chatbots deliver useful messages and recommend new products. Higher customer
satisfaction can increase the customer value.
iii)Interact when and where customers are
Chatbots can engage customers through web pages, digital ads, mobile or messaging apps,
telephone, in-store kiosks, social media or SMS.
iv)Speak customers’ language
Enterprise-grade chatbots can support multiple languages and can even make an educated
 guess based on the initial input, whether it’s in chat, text or voice.
v)Offer self-service options
Chatbot can provide self-service options and resource directions, saving the customers
time and reducing the staffing needs.
vi)Operate 24×7
Chatbots operate around the clock, helping to ensure that customers can access
information and support outside regular business hours. Chatbots provide instant
responses to inquiries, leading to faster query resolution and an improved customer
journey.
(Any four relevant points)
Q.21 The confusion matrix helps assess classification model performance in machine learning by 4M
comparing predicted values against actual values for a dataset.
In a confusion matrix, columns represent the predicted values of a given class while rows
represent the actual values (i.e. ground truth) of a given class, or vice-versa.This grid
structure is a convenient tool for visualizing model classification accuracy by displaying the
number of correct predictions and incorrect predictions for all classes alongside one
another.
A standard confusion matrix template for a binary classifier may look like this:

Where,
 True positives (TP), being the number of correct predictions for the positive class.
 False positives (FP), those negative-class instances incorrectly identified as positive
cases. These are also called type I errors in statistics.
 False negatives (FN), the actual positive instances erroneously predicted negative.
 True negatives (TN), which are the actual negative class instances accurately
predicted negative.
Totaling up each of these values would provide the model’s total number of predictions.
 KENDRIYA VIDYALAYA SANGATHAN HYDERABAD REGION
MODEL QUESTION PAPER -12
2024-25
CLASS:X TIME:02HOURS
SUBJECT:ARTIFICIAL INTELLEGENCE MAX.MARKS:50
SECTION A: OBJECTIVE TYPE QUESTIONS

Q. 1 Marks
Answer any 4 out of the given 6 questions on Employability Skills (1 x 4 = 4 marks)

1 Sunil, when leaving from his friend’s house is bidding goodbye by waving his hands. 1M
Which type of non-verbal communication is used by Sunil?
a) Expressionb) Body languagec)Gestured)All the above
2 SMART method can be used to set goals to make you successful in your career and 1M
personal life. What does 'M' in SMART stand for?
a)Money b)Millet c)Measureabled)Meter
3 Arushi gets up at 5 am and goes to her badminton classes. Then she comes home and 1M
finishes her homework before going to school. She does this all by herself. No one tells
her to do it. This is an example of
a) Self-motivationb) External motivation
c) Both self and external motivationd) Not any specific type of motivation
4 Assertion (A): E-Governance is regarded as the ICT-enabled system in achieving Good 1M
Governance.
Reason (R): Empathy is one of the desirable characteristics of e-Governance. In the light
of the above statements, choose the correct answer from the options given below:
a)Both (A) and (R) are true and (R) is the correct explanation of (A)
b)Both (A) and (R) are true but (R) is NOT the correct explanation of (A)
c)(A) is true but (R) is false
d)(A) is false but (R) is true
5 Choose the option which is not a sustainable development goal according to United 1M
Nations.
a) Clean Water and Sanitation b) Gender Equality
c) Population d) Reduced Inequalities
6 Which of the following are misconception about Entrepreneur? 1M
a) Entrepreneurs are born, not made.
b) A person having a big business is an entrepreneur.
c) A person needs a lot of money to start a business.
d) All of the above
Q. 2 Answer any 5 out of the given 6 questions (1 x 5 = 5 marks)

1 Choose the five stages of AI project cycle in correct order. 1M

a) Evaluation -> Problem Scoping -> Data Exploration -> Data Acquisition ->Modelling
b) Problem Scoping -> Data Exploration -> Data Acquisition -> Evaluation ->Modelling
c) Data Acquisition -> Problem Scoping -> Data Exploration -> Modelling ->Evaluation
d) Problem Scoping -> Data Acquisition -> Data Exploration -> Modelling ->Evaluation
 2 __________ is an unsupervised machine learning technique designed to group 1M
unlabeled examples based on their similarity to each other.
a) Clustering b)Classification c)Regression d)Dimensionality Reduction
3 Deep learning is in fact a new name for an approach to artificial intelligence called 1M
__________.
a) small network b) big network c) machine network d) neural networks
4 Statement 1: Neural networks are made up of layers of neurons. 1M
Statement 2: Human brain consists of millions of neurons.
a)Only Statement A is correct b) Only Statement B is correct
c) Both the statements are correct d) None of the statements is correct
5 CSV files can't save _________. 1M
a) simple data
b) images or other complex data
c) standard data
d) text data
6 Assertion (A): Natural Language Processing (NLP) is a challenging field. 1M
Reason (R): because of the complexities of human language.
a) Both Assertion (A) and Reason (R) are correct and Reason (R) is the correct
explanation of Assertion (A).
b) Both Assertion (A) and Reason (R) are correct, but Reason (R) is not the correct
explanation of Assertion (A).
c) Assertion (A) is correct, but Reason (R) is not correct.
d) Assertion (A) is not correct, but Reason (R) is correct.

Q. 3 Answer any 5 out of the given 6 questions (1 x 5 = 5 marks)

1 What do you understand by Interpersonal Intelligence? 1M

2 The method of collecting correct and dependable data to work with is known as 1M
___________.
a) Problem Scopingb) Data Acquisitionc) Data Explorationd) Modeling
3 Which machine learning model is used for predicting continuous outcomes? 1M

4 ________images are images which have a range of shades of gray without apparent 1M
colour.
a) Historicalb) RGBc) Grayscale d) Switch
5 _____are the words which occur very frequently in the corpus but do not addany value 1M
to it.
a) Special Charactersb)Stopwords
c) Roman Numbers d) Useless Words
6 Out of the following, which evaluation methods are used to calculate F1 score? 1M
a) Accuracy & recallb) Precision & F1 score
c) Accuracy and Precisiond) Precision & Recall
Q. 4 Answer any 5 out of the given 6 questions (1 x 5 = 5 marks)

1 Nitya wants to learn machine learning. Suggest a free and open-source library from the 1M
list below:
a)scikit-learnb)Matplotlibc)NumPyd)Pandas
2 Statement 1: F1 score is evaluated based on precision or recall. 1M
Statement 2: When the F1 score is 0, the model accuracy is 100%
a) Both statement1 and statement 2 are correct.
 b) Both statement1 and statement 2 are incorrect.
c) Statement 1 is correct but statement 2 is incorrect.
d) Statement 1 is incorrect but statement 2 is correct.
3 Srinivas would like to know what dimensionality reduction is. Help him with a 1M
definition.
4 Expand CNN____ 1M
a)conventional natural networkb)concrete neural network
c)contradictory natural networkd)convolutional neural network
5 Write any two applications of NLP. 1M

6 Neeraja wants to know the need of evaluation. Can you explain her? 1M

Q. 5 Answer any 5 out of the given 6 questions (1 x 5 = 5 marks)

1 George is an employee in MNC, whenever he feels stressed, he would like to spend 1M

some time with friends, listens to music and relieves his stress, He possess
________________ Intelligence.
a) Kinestheticb) Spatialc) Inter Personal d) Intra Personal
2 Which of the following parameters will be consider by recall, while evaluating a model`s 1M
performance?
i) False negative
ii) True negative
iii) False positive
iv) True Positive
Choose the correct option:
a) only (i) b) (ii) and (iii)c) (iii) and (iv) d) (i) and (iv)
3 ____________ is the core technology behind the development of autonomous vehicles. 1M

4 What is a chatbot called which uses simple FAQs without any intelligence? 1M
a) Smart Chatbot
b) Script Chatbot
c) AI Chatbot
d) ML Chatbot
5 The higher the value, the more important the word in the document – this istrue 1M
ofwhich model?
a) Bag of Words
b)TF-IDF
c) YOLO
d) LUDO
6 F1 score=? 1M

SECTION B: SUBJECTIVE TYPE QUESTIONS

Answer any 3 out of the given 5 questions on Employability Skills (2 x 3 = 6 marks)
Answer each question in 20 – 30 words.
Q 6 What are 7C's of Effective Communication? Briefly discuss any two of them. 2M
Q .7 What is Self-Management? Explain its importance. 2M
Q 8 What is Operating System (OS)? Write any two popular operating systems. 2M
Q .9 List out any two myths about entrepreneurship. 2M
Q 10 What is Sustainable Development? Explain any two problems related to sustainable 2M
development.
Answer any 4 out of the given 6 questions in 20 – 30 words each (2 x 4 = 8 marks)

Q 11 What is an AI Project Cycle? Explain its Components. 2M

Q .12 Explain Data Acquisition stage in AI Project Cycle. 2M
Q 13 What is Data Science? Write about any two disadvantages of it. 2M
Q .14 What do you know about Computer Vision? List any two applications of CV. 2M
Q 15 Explain the interaction between machines and humans using Natural Language 2M
Q 16 Processing.
Hari wants to know about recall of an AI model. Explain him with the help of formula. 2M

Answer any 3 out of the given 5 questions in 50– 80 words each (4 x 3 = 12 marks)

Q.17 What are the different domains of AI? 4M

Q.18 What do you know about the Problem Scoping stage of AI Project Cycle? 4M

Q.19 Dilip is confused about rule-based and learning-based approaches to AI 4M

modelling.Explain the differences between both with suitable examples.
Q.20 Define Text normalization and explain the different steps in involved. 4M

Q.21 Pradeep wants to know different evaluationmethods of AI models. Can you explain him 4M
with the help of formulas?

KENDRIYA VIDYALAYA SANGATHAN HYDERABAD REGION

ARTIFICIAL INTELLIGENCE (SUBJECT CODE - 417)
Class X
Model Question Paper – 12 (Solutions)

SECTION A: OBJECTIVE TYPE QUESTIONS

Q. 1 Marks
Answer any 4 out of the given 6 questions on Employability Skills (1 x 4 = 4 marks)

1 c)Gesture 1M
2 c)Measureable 1M
3 a) Self-motivation 1M
4 c)(A) is true but (R) is false 1M
5 c) Population 1M
6 d) All of the above 1M
Q. 2 Answer any 5 out of the given 6 questions (1 x 5 = 5 marks)

1 d) Problem Scoping -> Data Acquisition -> Data Exploration -> Modelling ->Evaluation 1M
2 a) Clustering 1M
3 d) neural networks 1M
4 c) Both the statements are correct 1M
5 b) images or other complex data 1M
 6 a) Both Assertion (A) and Reason (R) are correct and Reason (R) is the correct 1M
explanation of Assertion (A).
Q. 3 Answer any 5 out of the given 6 questions (1 x 5 = 5 marks)

1 Understanding human emotions, feelings and influenced by them is known as 1M

interpersonal intelligence.
OR
Interpersonal intelligence is the ability to communicate with others by understanding
other people's feelings, being influenced by the person.
OR
Interpersonal intelligence refers to the ability of a person to relate well with people and
manage relationships. It enables people to understand the needs and motivations of
those around them, which helps strengthen their overall influence.
OR
Interpersonal intelligence refers to the ability to understand social situations and the
behavior of other people.
2 b) Data Acquisition 1M
3 Regression 1M
4 c) Grayscale 1M
5 b)Stopwords 1M
6 d) Precision & Recall 1M
Q. 4 Answer any 5 out of the given 6 questions (1 x 5 = 5 marks)
1 a)scikit-learn 1M
2 c) Statement 1 is correct but statement 2 is incorrect. 1M
3 The Dimensionality reduction refers to the process of converting a data set with vast 1M
dimensions into data with fewer dimensions (fields) to convey similar information
concisely.
(Any relevant definition)
4 d)convolutional neural network 1M

5 1) Automatic summarization is relevant not only for summarizing the meaning of 1M

documents and information, but also to understand the emotional meanings within the
information, such as in collecting data from social media.
2) Sentiment Analysis: The goal of sentiment analysis is to identify sentiment among
several posts or even in the same post where emotion is not always explicitly
expressed.
3) Text classification makes it possible to assign predefined categories to a document
and organize it to help you find the information you need or simplify some activities.
4) Virtual Assistants like Google Assistant, Cortana, Siri, Alexa, etc have become an
integral part of our lives.
(Any two relevant applications)
6 While in modelling, we make different types of models. Then a decision to be taken 1M
which model is better than another. So, for that proper testing and evaluation is
needed to calculate the efficiency and performance of a model.
An efficient evaluation model proves helpful in selecting the most suitable modelling
method that would represent our data.
(Any one relevant point)
Q. 5 Answer any 5 out of the given 6 questions (1 x 5 = 5 marks)
 1 d) Intra Personal 1M

2 d) (i) and (iv) 1M

3 Computer vision 1M

4 b) Script Chatbot 1M

5 a) Bag of Words 1M

6 2*(precision*recall)/(precision+recall) 1M
OR
TP/TP+1/2(FP+FN)

SECTION B: SUBJECTIVE TYPE QUESTIONS

Answer any 3 out of the given 5 questions on Employability Skills (2 x 3 = 6 marks)
Answer each question in 20 – 30 words.
Q 6  Clear: While communicating one should be clear about what he / she say. 2M
 Concise: Use simple words and say only what is needed.
 Concrete: Your arguments should be based on solid facts and opinions from
credible sources and you should share reliable data to support your stand.
 Correct: It’s essential that along with the factual information, the language and
grammar you use are correct.
 Coherent: Your words should make sense. Along with that it should related with
the main topic
 Complete: Your message should be complete. It should have all the needed
information
 Courteous: Be respectful, honest and friendly throughout your communication
(Any two of the above)
Q .7 Self-Management: 2M
 Self-management is the ability to control one’s emotions, thoughts and
behaviour effectively in different situations.
Importance of Self-Management:
 Self-sufficient and independent
 Ownership and accountability lead to self-confident
 Goal-oriented and strategy maker
 Self-monitoring and discipline reinforce good habits and behaviours
 Organise life and remove stress
Q 8 An Operating System (OS) is an interface between a computer user and computer 2M
hardware. An operating system is a software which performs all the basic tasks like file
management, memory management, process management, handling input and output,
and controlling peripheral devices such as disk drives and printers.
Some popular operating systems are:
• DOS (Disk Operating System)
• Windows It is an operating system developed by Microsoft.
• Linux It is an operating system designed for personal computers. It is a free and Open
Source Software
 • Mobile operating Systems
 Android
 Symbian
 Windows Phone
 iOS
Q .9 A myth, or a misconception, is a false belief or opinion about something. 2M
Misconception 1: Every business idea needs to be unique or special
 A person can take an idea that is already there in the market and do something
different with it.
 For example: Cab Service named ‘inDrive’ simply introduced an option wherein
a user can quote his/her fare and negotiate with cab driver. This is unlike stand
Cab Service providers like ‘Ola’ and ‘Uber’
Misconception 2: A person needs a lot of money to start a business
 Capital is important for starting. However, every business does not need a lot of
capital to start. Moreover, today there is no dearth of credit and even venture
capitalists are willing to provide funding.
 Depending on how much money you have or can borrow, you can start a
business with that much money. Once you make more money, you can reinvest
profits back into your business to make it bigger.
 For example: ‘BTW’ or “BittooTikkiWala” initially started as a street seller and
later on expanded based on reploughing of profits back into business.
Misconception 3: Only a person having a big business is an entrepreneur
 No business is big or small. If a person is running a business to fulfil a customer
need, they are an entrepreneur from Day 1. Most businesses start small. It
becomes big with hard work and creativity, over time.
Misconception 4: Entrepreneurs are born, not made.
 It is only a myth that some people have the talent for doing business. An
entrepreneur is a person who does whatever it takes to make the business
successful. Being an entrepreneur starts with a way of thinking. Moreover,
entrepreneurial skills cam be developed too through training.
(Any two relevant points)
Q 10 Sustainable development is the development that satisfies the needs of the present 2M
without compromising the capacity of future generations, guaranteeing the balance
between economic growth, care for the environment and social well-being.
Three major problems related to sustainable development are:
 Food: The amount of rich, fertile land needed to grow crops, such as wheat, rice,
etc., is becoming less as we are using up more and more land for other
purposes. Soil nutrients are also getting depleted and lots of chemicals are
spoiling the soil due to use of chemical fertilizers.
 Water: We use fresh water from rivers and ponds for drinking and cleaning but
dump garbage into them. The rivers and ponds are getting polluted. This way
after several years, we will have no clean water for our use.
 Fuel: We are using a lot of wood from trees as fuels and for construction of
homes and furniture. As more and more trees are being cut, it is affecting the
climate of the place. Extreme weather conditions, such as floods, extreme cold
or heat, are seen in many places, which affect the people living there.
(Any Two relevant)
Answer any 4 out of the given 6 questions in 20 – 30 words each (2 x 4 = 8 marks)
Q 11 AI Project Cycle is a step-by-step process to solve problems using proven scientific 2M
methods and drawing inferences about them.
Components of the project cycle are the steps that contribute to completing the
Project. The Components of AI Project Cycle are: -
 Problem Scoping - Understanding the problem
 Data Acquisition - Collecting accurate and reliable data
 Data Exploration - Arranging the data uniformly
 Modelling - Creating Models from the data
 Evaluation - Evaluating the project
Q .12 Data Acquisition is the second stage of AI Project Cycle. This stage is about 2M
acquiringdata for the project.
There can be various ways in which we can collect data. Some of them are:
 Surveys
 Web Scraping
 Sensors
 Cameras
 Observations
 API(Application Program Interface)

Q 13 Data science is a field that combines statistics, computer science, and domain expertise 2M
to extract insights and knowledge from data.
Disadvantages:
 Data privacy concerns: There is a risk of data privacy concerns when data is
collected and analyzed.
 Bias in data: Data can be biased due to many factors, such as the selection of the
data or the way it is collected.
 Misinterpretation of data: Data science involves complex statistical analysis,
which can sometimes lead to misinterpretation of the data.
 Data quality issues: Data science depends on the quality of the data used. If the
data is not accurate, complete or consistent, it can lead to incorrect results.
 Cost and time: Data science can be time-consuming and expensive.
(Any two relevant points)
Q .14 Computer vision is a branch in the Domain of AI that enables computers to analyze 2M
meaningful information from images, videos, and other visual inputs.
Applications of Computer Vision
Facial recognition
The most frequently used technology is smartphones. It is a technology to remember
and verify a person, object, etc from the visuals from the given pre-defined data. Such
kinds of mechanics are often used for security and safety purposes.
Facial filters
Modern days social media apps like Snapchat and Instagram use such kinds of
technology that extract facial landmarks and process them using AI to get the best
result.
Google lens
To search data, Google uses Computer vision for capturing and analysing different
features of the input image to the database of images and then gives us the search.
Automotive
The machinery in industries is now using Computer vision. Automated cars are
equipped with sensors and software which can detect the 360 degrees of movements
determine the location, detect objects and establish the depth or dimensions of the
 virtual world.
Medical Imaging
It creates and analyses images and helps doctors with their interpretation.The
application is used to read and convert 2D scan images into interactive 3D models.
(Any two relevant points)
Q 15 A usual interaction between machines and humans using Natural Language Processing 2M
could go as follows:
• Humans talk to the computer
• The computer captures the audio
• There is an audio to text conversion
• Text data is processed Data is converted to audio
• The computer plays the audio file and responds to humans
Q 16 The true positive rate (TPR), or the proportion of all actual positives that were classified 2M
correctly as positives, is also known as recall.
Recall is mathematically defined as:

Answer any 3 out of the given 5 questions in 50– 80 words each (4 x 3 = 12 marks)
Q.17 The Three Domain of AI: 4M
a) Data Science: -
Data science is a domain of AI related to data systems and processes, in which the system
collects numerous data, maintains data sets and derives meaning/sense out of them.
The information extracted through data science can be used to decide about it.
Applications:
Price Comparison Websites, Targeted Advertising, Stock Market Analysis and etc
b) Computer Vision: -
Computer Vision is a domain of AI that depicts the capability of a machine to get and
analyse visual information and afterwards predict some decisions about it.
The entire process involves image acquiring, screening, analysing, identifying and
extracting information.
This makes devices visually enabled and gives the capability to understand the visual
information.
Applications:
Self-Driving Cars, Face lock in smart phones, Filters in images and etc.
c) Natural Language Processing: -
Natural Language Processing is a domain of AI that deals with the interaction of
computers and humans using the natural language.
Natural language refers to language that is spoken and written by people.
Natural Language Processing (NLP) attempts to extract information from the spoken and
written words to understand its meaning.
Applications: -
Virtual Assistants, E-Mail Filters, Speech to Text conversion and etc.
Q.18 Many times, we become so used to a problem that it becomes a part of our life. 4M
Identifying such a problem and having a vision to solve it, is what Problem Scoping is
about.
Scoping a problem is not that easy as we need to have a deeper understanding around it
so that the picture becomes clearer while we are working to solve it. The 4Ws Problem
canvas helps in identifying the key elements related to the problem.
Who?
 The “Who” block helps in analysing the people getting affected directly or indirectly due
to it. Under this, we find out who the ‘Stakeholders’ to this problem are and what we
know about them. Stakeholders are the people who face this problem and would be
benefitted with the solution.
What?
Under this block, you also gather evidence to prove that the problem you have selected
actually exists. Newspaper articles, Media, announcements, etc are some examples.
Where?
This block will help us look into the situation in which the problem arises, the context of
it, and the locations where it is prominent.
Why?
The “Why” canvas, think about the benefits which the stakeholders would get from the
solution and how it will benefit them as well as the society.
Q.19 Rule Based Approach: It refers to the AI modelling where the relationship or patterns in 4M
data are defined by the developer. The machine follows the rules or instructions
mentioned by the developer, and performs its task accordingly.
For example, suppose you have a dataset comprising of 100 images of apples and 100
images of bananas. To train your machine, you feed this data into the machine and label
each image as either apple or banana. Now if you test the machine with the image of an
apple, it will compare the image with the trained data and according to the labels of
trained images, it will identify the test image as an apple. This is known as Rule based
approach. The rules given to the machine in this example are the labels given to the
machine for each image in the training dataset.
Learning Based Approach: In this approach, the machine learns by itself. It refers to the
AI modelling where the relationship or patterns in data are not defined by the developer.
In this approach, random data is fed to the machine and it is left on the machine to figure
out patterns and trends out of it. Generally, this approach is followed when the data is un
labelled and too random for a human to make sense out of it.
For example, suppose you have a dataset of 1000 images of random stray dogs of your
area. You would put this into a learning approach-based AI machine and the machine
would come up with various patterns it has observed in the features of these 1000
images which you might not have even thought of!
Q.20 Text Normalization is a process to reduce the variations in text’s word forms to a 4M
common form when the variation means the same thing. The different in text
normalization is
1. Sentence Segmentation
2. Tokenisation
3. Removing Stop words, Special characters and Numbers
4. Converting text to a common case
5. Stemming
6. Lemmatization
1. Sentence Segmentation: Under sentence segmentation, the whole text is divided into
individual sentences.
2. Tokenisation: After segmenting the sentences, each sentence is then further divided
into tokens. Tokens is a term used for any word or number or special character occurring
in a sentence. Under tokenisation, every word, number and special character is
considered separately and each of them is now a separate token.
3. Removing Stop words, Special characters and Numbers: Stop words are the words in
any language which do not add much meaning to a sentence. They can safely be ignored
without sacrificing the meaning of the sentence These words occur the most in any given
sentence but talk very little or nothing about the context or the meaning of it. Hence, to
 make it easier for the computer to focus on meaningful terms, these words are removed.
4. Converting text to a common case: After the stop words removal, we convert the
whole text into a similar case, preferably lower case. This ensures that the case-sensitivity
of the machine does not consider same words as different just because of different cases.
5. Stemming: -stemming is the process in which the affixes of words are removed, and
the words are converted to their base form. In stemming, the stemmed words (words
which are we get after removing the affixes) might not be meaningful.
6. Lemmatization: In lemmatization, the word we get after affix removal (also known as
lemma) is a meaningful one. Lemmatization makes sure that lemma is a word with
meaning and hence it takes a longer time to execute than stemming.
Q.21 Accuracy is the proportion of all classifications that were correct, whether positive or 4M
negative. It is mathematically defined as:

Recall, or true positive rate

The true positive rate (TPR), or the proportion of all actual positives that were classified
correctly as positives, is also known as recall.
Recall is mathematically defined as:

Precision is the proportion of all the model's positive classifications that are actually
positive. It is mathematically defined as:

The F1 score is the harmonic mean (a kind of average) of precision and

recall.Mathematically, it is given by:
 KENDRIYA VIDYALAYA SANGATHAN HYDERABAD REGION
MODEL QUESTION PAPER - 13
2024-25
CLASS:X TIME:02HOURS
SUBJECT:ARTIFICIAL INTELLEGENCE MAX.MARKS:50
SECTION A: OBJECTIVE TYPE QUESTIONS
Q. 1 Marks
Answer any 4 out of the given 6 questions on Employability Skills (1 x 4 = 4 marks)
1 Kiran travelled to Spain from India to pursue her higher education. But he doesn't know 1M
how to speak Spanish (language of Sweden). Because of this, he was unable to find a part
time job. This is an example of _____________
a) Interpersonal barrierb) Physical barrier
c) Organisational barrierd) Linguistic barrier
2 Which of the following is not a key element of self-management skills? 1M
a)Prioritising your work
b)Not taking feedback
c)Goal setting
d)Staying updated about new practices
3 What are the ABC of Stress Management? 1M
a) Avertible, Belief, Consequences.
b) Adversarial, Being, Control,
c) Adversity, Belief, Consequences
d) Adversity, Belief, Control
4 Direction: In the questions given below, there are two statements marked as Assertion 1M
(A) and Reason (R). Choose the correct option out of the choices given below in each
question:
Assertion (A): An operating system is the most important software that runs on your
computer.
Reason (R): It enables you to communicate with the computer without knowing how to
speak the computer's language.
a) Both (A) and (R) are correct and (R) is the correct explanation of (A).
b) Both (A) and (R) are correct and (R) is not the correct explanation of (A).
c) (A) is True but (R) is False.
d) (A) is False but (R) is True.
5 _______are the knowledge, abilities, values and attitudes needed to live in, develop and 1M
support a sustainable and resource-efficient society.
a) ICT skills
b) Entrepreneur skills
c) Reading skills
d) Green skills
6 While writing the functions of an entrepreneur, Amulya wrongly listed one function. Can 1M
you identify it?
a) Making decisions
b) Worrying about losses
c) Managing the business
d) Taking risk
Q. 2 Answer any 5 out of the given 6 questions (1 x 5 = 5 marks)

1 Which of the following is invalid with regard to Data Privacy? 1M

a) Allow all permission while installing apps in smart phones can leak data.
b) Denying all permission will allow to install app in smart phone.
c) Use apps which don’t make permissions compulsory.
d) Use apps Reliable and Authentic.
2 Statement1: Who block helps in finding out the stakeholders of the problem 1M
Statement2: Where block, focuses on the context/situation/location of the problem.
a) Both Statement1 and Statement2 are correct
b) Both Statement1 and Statement2 are incorrect
c) Statement1 is correct but Statement2 is incorrect
d) Statement2 is correct but Statement1 is incorrect
3 Assertion (A): Deep learning and neural networks are used interchangeably. 1M
Reason (R): because all deep learning systems are not made of neural networks.
a) Both (A) and (R) are correct and (R) is the correct explanation of (A).
b) Both (A) and (R) are correct and (R) is not the correct explanation of (A).
c) (A) is True but (R) is False.
d) (A) is False but (R) is True.
4 Odd man out: 1M
a) Convolutional neural networks
b) Radial basis functions networks
c) Pen belief networks
d) Generative adversarial networks
5 JSON is better than CSV while working with______. 1M
a) smaller files
b) unknown data
c) redundant data
d) big data
6 ________is a particular representation model used to simplify the contents of a selection 1M
of text.
a)Stop Wordsb)Bag of wordsc)Lemmatizationd)Normalization
Q. 3 Answer any 5 out of the given 6 questions (1 x 5 = 5 marks)

1 _________uses machine learning algorithms to analyze and cluster unlabeled datasets 1M

(subsets called clusters).
a) Undo learning b) Redo learning c) Supervised learning d) Unsupervised learning
2 _________is related with understanding the problem. 1M
a) Modelling
b) Data Acquisition
c) Data Exploration
d) Problem Scoping
3 The _______is an incredibly powerful tool for interactively developing and presenting AI 1M
related projects.
a) Mars Notebookb) Saturn Notebookc) Jupyter Notebookd) Earth Notebook
4 A _________ is nothing but a space where we can find codes or functions or modules of 1M
similar type.
a) packageb) baggagec) luggaged) suitcase
5 Major tasks in _________ are speech recognition, text classification, 1M
languageunderstanding etc.
a)Data Science
 b)Computer Vision
c)Natural Language Processing
d)Data Vision Processing
6 _______can be seen as a measure of quality, and ______ as a measure of quantity. 1M
a) recall, precision
b) precision, recall
c) precision, F1 Score
d) recall, accuracy
Q. 4 Answer any 5 out of the given 6 questions (1 x 5 = 5 marks)

1 Srikanth forgotten the AI domain that works around numeric and alpha numeric data. 1M
Can you identify it from the below:
a)Computer Vision
b)Data Sciences
c)Computer Science
d)Natural Language Processing
2 Statement1: Recall is defined as the fraction of positive cases that are wrongly Identified. 1M
Statement2: Accuracy is defined as the percentage of correct predictions out of all the
observations.
a) Both Statement1 and Statement2 are correct
b) Both Statement1 and Statement2 are incorrect
c) Statement1 is correct but Statement2 is incorrect
d) Statement2 is correct but Statement1 is incorrect
3 Sunitha is working on a data science project and would like to learn a tool for data 1M
visualization. Can you suggest one?
4 Find the odd man out. 1M
a) SimpleCV
b) OpenCV
c) Simos
d) Keras
5 Which of the following is not related to Natural Language Processing (NLP) 1M
a)NLTKb)Zoomc)SpaCy d)Gensim
6 Dinesh is learning the conditions that make up the confusion matrix. He came across a 1M
scenario in which the machine that was supposed to predict a banana was always
predicting a banana. What is this condition called?
a) False Positiveb) True Positivec) False Negatived) True Negative
Q. 5 Answer any 5 out of the given 6 questions (1 x 5 = 5 marks)

1 Riyaz is an employee in MNC, whenever he feels stressed, he would like to spend some 1M
time with friends, listens to music and relieves his stress. He possess ________________
Intelligence.
a) Kinesthetic
b) Spatial
c) Inter Personal
d) Intra Personal
2 ________is used to identify patterns and relationships within a dataset, which can then 1M
be applied to new and unseen data.
a) Classification b)Regression c)Dimension Reduction d)Dictionary
3 Google Translate App is one of the applications of _________. 1M
a)Data Science
b)Networks
 c)DBMS
d)Computer Vision
4 Stemming uses the _______ of the word, while lemmatization uses the context in which 1M
the word is being used.
a)nerve
b)root
c)stem
d)pronoun
5 ______ measures how important a term is within a document relative to a collection of 1M
documents.
a)TF-IDF
b)Bag of Words
c)Corpus
d)RAM
6 The training data is used to train the machine learning algorithm. The testing data is used 1M
to ______ the accuracy of the trained algorithm.
a)break
b)remember
c)predict
d)evaluate

SECTION B: SUBJECTIVE TYPE QUESTIONS

Answer any 3 out of the given 5 questions on Employability Skills (2 x 3 = 6 marks)
Answer each question in 20 – 30 words.
Q 6 Write a short note on barriers to effective communication. 2M
Q .7 What is the importance of setting goals in life? 2M
Q 8 List the various threats to a computer and its data. 2M
Q .9 What do entrepreneurs do when they run their business? 2M
Q 10 What led to Environment Pollution? 2M
Answer any 4 out of the given 6 questions in 20 – 30 words each (2 x 4 = 8 marks)
Q 11 Explain Data Exploration Stage. 2M
Q .12 What are the features of an Artificial Neural Network? 2M
Q 13 What is feature engineering, and how is it important in data science? 2M
Q .14 How is pixel value represented in a grayscale image? 2M
Q 15 Tinku wants to understand the difference between Stemming and Lemmatization. Can 2M
you help him with the differences?
Q 16 Shahid wants to understand the condition TP. Can you help him understand? 2M
Answer any 3 out of the given 5 questions in 50– 80 words each (4 x 3 = 12 marks)
Q.17 Explain the AI Categories/branches? 4M
Q.18 Dinesh wants to know about Supervised Learning and Unsupervised Learning in detail. 4M
Will you help him with definitions?
Q.19 Aaadyais multi-talented and has excelled in academics, music, dancing, sports and 4M
painting.Describe different types of intelligences by naming and explaining any four
types of intelligences?
Q.20 Normalise the text on the segmented sentences given below: 4M
Document 1: Diya and Riya are best friends.
Document 2: Diya likes to play guitar but Riya prefers to play violin
Q.21 An IT company situated in Bombay developed an AI model which predicts the 4M
purchasing of electronic gadgets. During testing, the AI model came up with the
following predictions.Based on the given predictions, calculate the following

Reality
Confusion matrix
YES NO
YES 60 25
Prediction
NO 5 10
i) How many total tests have been performed in the above scenario?
ii) Calculate precision, recall and F1 score.

KENDRIYA VIDYALAYA SANGATHAN HYDERABAD REGION

ARTIFICIAL INTELLIGENCE (SUBJECT CODE - 417)
Class X
Model Question Paper – 13 (Solutions)

SECTION A: OBJECTIVE TYPE QUESTIONS

Q. 1 Marks
Answer any 4 out of the given 6 questions on Employability Skills (1 x 4 = 4 marks)
1 d) Linguistic barrier 1M
2 b)Not taking feedback 1M
3 c) Adversity, Belief, Consequences 1M
4 a) Both (A) and (R) are correct and (R) is the correct explanation of (A). 1M
5 d) Green skills 1M
6 b) Worrying about losses 1M
Q. 2 Answer any 5 out of the given 6 questions (1 x 5 = 5 marks)
1 b) Denying all permission will allow to install app in smart phone. 1M
2 a) Both Statement1 and Statement2 are correct 1M
3 c) (A) is True but (R) is False. 1M
4 c) Pen belief networks 1M
5 d) big data 1M
6 b)Bag of words 1M
Q. 3 Answer any 5 out of the given 6 questions (1 x 5 = 5 marks)
1 d) Unsupervised learning 1M
2 d) Problem Scoping 1M
3 c) Jupyter Notebook 1M
4 a) package 1M
5 c)Natural Language Processing 1M
6 b) precision, recall 1M
Q. 4 Answer any 5 out of the given 6 questions (1 x 5 = 5 marks)
1 b)Data Sciences 1M
2 d) Statement2 is correct but Statement1 is incorrect 1M
3 Tableau or Power BI orMatplotlib orSeaborn or any other relevant tool 1M
4 c) Simos 1M
5 b)Zoom 1M
6 c) False Negative 1M
 Q. 5 Answer any 5 out of the given 6 questions (1 x 5 = 5 marks)
1 d) Intra Personal 1M
2 b) Regression 1M
3 d)Computer Vision 1M
4 c)stem 1M
5 a)TF-IDF 1M
6 d)evaluate 1M

SECTION B: SUBJECTIVE TYPE QUESTIONS

Answer any 3 out of the given 5 questions on Employability Skills (2 x 3 = 6 marks)
Answer each question in 20 – 30 words.
Q 6 Physical Barriers 2M
Physical barrier is the environmental and naturalcondition that act as a barrier in
communication insending message from sender to receiver. Not beingable to see gestures,
posture and general body languagecan make communication less effective.
Linguistic Barriers
The inability to communicate using a language is knownas language barrier to communication.
Languagebarriers are the most common communicationbarriers, which cause
misunderstandings andmisinterpretations between people.
Interpersonal Barriers
Barriers to interpersonal communication occur whenthe sender’s message is received
differently from howit was intended. It is also very difficult to communicatewith someone
who is not willing to talk or express theirfeelings and views. Stage fear, lack of will to
communicate,personal differences can create interpersonal barriersto communication.
Organisational Barriers
Organisations are designed on the basis of formalhierarchical structures that follow
performancestandards, rules and regulations, procedures, policies,behavioural norms, etc. All
these affect the free flowof communication in organisations and therefore,need to be suitably
managed.
Cultural Barriers
Cultural barriers is when people of different cultures areunable to understand each other’s
customs, resulting ininconveniences and difficulties.People sometimes makestereotypical
assumptions about others based on theircultural background, this leads to difference in
opinionsand can be a major barrier to effective communication.
(Any two relevant points)
Q .7 Following are the importance of Goal setting 2M
1. Goals allow you to separate out what’s important.
2. It helps you to focus on the end result instead of less Important work.
3. This will make you successful in your Career and personal life.
(Any two relevant points)
Q 8 The various threats to a computer and its data: 2M
● Virus
● Phishing
● Online theft
● Cyber crime
● Hacking
Q .9 1. Fulfil Customer Needs 2M
 2. Use Local Materials
3. Help Society
4. Create Jobs
5. Sharing of Wealth
6. Lower Price of Products
(Any four points)
Q 10 With economic development, there has been an increase in environmental pollution. For 2M
example, with the introduction of high input agriculture, we can grow more food by using
fertilisers, pesticides and hybrid crops. But it has led to soil and environmental degradation.

Answer any 4 out of the given 6 questions in 20 – 30 words each (2 x 4 = 8 marks)

Q 11 In this stage of project cycle, we try to interpret some useful information out of the data we 2M
haveacquired. For this purpose, we need to explore the data and try to put it uniformly for a
betterunderstanding. This stage deals with validating or verification of the collected data and
to analysethat:
 The data is according to the specifications decided.
 The data is free from errors.
 The data is meeting our needs
Q Any Artificial Neural Network, irrespective of the style and logic of implementation, has a few 2M
.12 basic features as given below.
 The Artificial Neural Network systems are modelled on the human brain and nervous
system.
 They are able to automatically extract features without feeding the input by
programmer.
 Every node of layer in a Neural Network is compulsorily a machine learning algorithm.
 It is very useful to implement when solving problems for very huge datasets.
Q 13 Feature engineering is the process of selecting and transforming variables to create new 2M
features that improve model performance. It's important because:
 It helps reduce dimensionality
 Improves model interpretability
 Enhances model performance
 Reduces noise and correlations
 Facilitates feature selection
Q In a grayscale image, the pixel value is represented by an intensity level ranging from 0 to 255, 2M
.14 where 0 represents black, 255 represents white, and values in between represent different
shades of gray.
Q 15 Stemming: 2M
Stemming is a rudimentary rule-based process of stripping the suffixes (“ing”, “ly”, “es”, “s”
etc) from a word.Stemming is a process of reducing words to their word stem, base or root
form (for example, books — book, looked — look).
Lemmatization:
Lemmatization, on the other hand, is an organized &stepby step procedure of obtaining the
root form of the word, it makes use of vocabulary (dictionary importance of words) and
morphological analysis (word structure and grammar relations).
Q 16 TP stands for True Positive. When the Prediction matches with the Reality, that condition is 2M
called TP. That is, prediction is True and the Reality is True.
Answer any 3 out of the given 5 questions in 50– 80 words each (4 x 3 = 12 marks)

Q.1 AI Categories: 4M
7 Artificial Intelligence:
 Refers to any technique that enables computers to mimic human intelligence. It gives the
ability to machines to recognize a human’s face; to move and manipulate objects; to
understand the voice commands by humans, and also do other tasks. The AI-enabled machines
think algorithmically and execute what they have been asked for intelligently.
Machine Learning (ML)
It is a subset of Artificial Intelligence which enables machines to improve at tasks with
experience (data). The intention of Machine Learning is to enable machines to learn by
themselves using the provided data and make accurate Predictions/ Decisions.
Deep Learning (DL)
It enables software to train itself to perform tasks with vast amounts of data. In Deep Learning,
the machine is trained with huge amounts of data which helps it in training itself around the
data. Such machines are intelligent enough to develop algorithms for themselves.
Q.1 Supervised learning 4M
8 Supervised learning is an approach to creating artificial intelligence (AI), where the program is
given labelled input data and the expected output results. OR Supervised learning is a learning
in which we teach or train the machine using data which is well labelled that means some data
is already tagged with the correct answer. After that, the machine is provided with a new set of
examples (data) so that supervised learning algorithm analyses the training data (set of training
examples) and produces a correct outcome from labelled data. In a supervised learning model,
the dataset which is fed to the machine is labelled. It means some data is already tagged with
the correct answer. In other words, we can say that the dataset is known to the person who is
training the machine only then he/she is able to label the data.
Unsupervised Learning: An unsupervised learning model works on unlabelled dataset. This
means that the data which is fed to the machine is random and there is a possibility that the
person who is training the model does not have any information regarding it. The unsupervised
learning models are used to identify relationships, patterns and trends out of the data which is
fed into it. It helps the user in understanding what the data is about and what are the major
features identified by the machine in it.
Q.1 Types of Intelligences: 4M
9 Linguistic Intelligence: Aaadya's ability to excel in academics and possibly writing or public
speaking showcases linguistic intelligence, which involves proficiency in language and
communication.
Musical Intelligence: Aaadya's talent in music indicates musical intelligence, which involves
sensitivity to rhythm, melody, and sound.
Bodily-Kinesthetic Intelligence: Aaadya's prowess in dancing and sports suggests bodily-
kinesthetic intelligence, which relates to physical coordination, agility, and control.
Visual-Spatial Intelligence: Aaadya's skill in painting reflects visual-spatial intelligence, which
involves the ability to perceive the world accurately and manipulate objects mentally.
Q.2 Stopwords in the given sentence which should not be removed are: @, . (fullstop) 4M
0 ,_(underscore) , 123(numbers) These tokens are generally considered as stopwords, but in the
above sentence, these tokens are part of email id. Removing these tokens may lead to invalid
website address and email ID. So these words should not be removed from the above sentence.
(1 mark for identifying any twostop words from the above, and 1 mark for the valid
justification.)
Q.2 i) Total tests performed = Sum of all entries in the confusion matrix = 60 + 25 + 5 + 10 = 100 4M
1 ii)
Precision = True Positives / (True Positives + False Positives) = 60 / (60 + 5) = 0.923 Recall = True
Positives / (True Positives + False Negatives) = 60 / (60 + 25) = 0.706
F1 Score = 2 * (Precision * Recall) / (Precision + Recall) = 2 * (0.923 * 0.706) / (0.923 + 0.706) ≈
0.801
 KENDRIYA VIDYALAYA SANGATHAN HYDERABAD REGION
MODEL QUESTION PAPER-14
2024-25
CLASS:X TIME:02 HOURS
SUBJECT:ARTIFICIAL INTELLEGENCE MAX.MARKS:50

SECTION A: OBJECTIVE TYPE QUESTIONS

Q. 1 Marks
Answer any 4 out of the given 6 questions on Employability Skills (1 x 4 = 4 marks)

1 Assertion(A): It is important to know about the culture and cultural preferences of an 1M

audience before communication.
Reason(R): Knowing about a culture is useful in overcoming cultural barriers.
(a) Both A and R are correct and R is the correct explanation of A
(b) Both A and R are correct but R is NOT the correct explanation of A
(c) A is correct but R is not correct
(d) A is not correct but R is correct
2 High expectations from self can leave one with chronic anxiety and stress, thus leading 1M
to _____________stress.
a. Physical b. Emotional c. Mental d. Financial
3 Which of the following is not a key element of self-management skills? 1M
(a)Prioritising your work
(b)Not taking feedback
(c)Goal setting
(d)Staying updated about new practices
4 Sometimes you may receive very attractive offers saying you have won a huge 1M
amount of money in a lottery and that you can claim the prize by depositing a
certain amount of money known as ___________.
a. Trojan House
b. Online Predator
c. Theft
d. Internet Scams
5 ____ is the development that satisfies the needs of the present without compromising 1M
the capacity of future generations.
a. Overall development
b. Economic development
c. Sustainable development
d. None of the above
6 Ravi’s customer comes to his store and starts shouting at him. He does not get angry. 1M
He listens to what his customer is saying. He is ____________.
a. Hardworking
b. Confident
c. Patient
d. Trying new ideas
Q. 2 Answer any 5 out of the given 6 questions (1 x 5 = 5 marks)
 1 “People with this type of intelligence have the ability to communicate with others by 1M
understanding other people’s feelings, characteristics, emotions and intentions. They
are essentially a people person.”
Identify the type of intelligence described in the above statement.
2 The AI Project Cycle is a ____________ that a company must follow in order to derive 1M
value from an AI project and to solve the problem.
a. Step-by-step process b. Random process c. Reverse process d. None of the above
3 Fill in the blank: Neural Network is a mesh of multiple ____________. 1M

4 DeepLearning,particularlyConvolutionalNeuralNetworks(CNNs),iscommonlyusedinCom 1M
puterVision (True / False)
5 CSV file extension stands for_________ 1M
a) Cell-separated verb
b) Civil-services van
c) Customer-service value
d) Comma-separated value
6 Which of these is not an NLP library? 1M
(a) NLTK
(b) NLP Kit
(c) Open NLP
(d) NLP Suite
Q. 3 Answer any 5 out of the given 6 questions (1 x 5 = 5 marks)

1 An organization is using a AI enabled Security surveillance system. Surya works as a 1M

Security guard in the Organization. Due to usage of AI enabled security system he has a
feeling that he may not be needed in the near future. What is this situation?
a. Data Privacy b. AI Bias c. AI Access d. AI is creating Unemployment
2 Identify the algorithm based on the given graph. 1M

(a) Dimensionality reduction (b) Classification(c) Clustering (d) Regression

3 What is the primary goal of data science? 1M

4 What is feature extraction in Computer Vision? 1M

A) Reducing image noise
B) Identifying and describing relevant characteristics from an image
C) Increasing image contrast
D) Storing image data
5 Which of the following is the type of data used by NLP applications? 1M
(a) Images (b) Numerical data (c) Graphical data (d) Text and Speech

6 When the model always predicts correctly on the training data set and incorrectly on 1M
the test data set, this situation leads to (Underfitting/Overfitting)
Q. 4 Answer any 5 out of the given 6 questions (1 x 5 = 5 marks)
 1 When a user installs an app in the smartphone, it asks for access to gallery, contacts, 1M
etc. After accepting this, it gives the user agreement which most users accept without
realizing the implications. What is the concern here?
(a) Data Privacy (b) Unemployment (c) AI bias (d) No concern
2 A bank has implemented an AI system to detect fraudulent transactions. After 1M
deployment, they want to evaluate how effectively the model is identifying fraudulent
activities without blocking legitimate transactions.Which evaluation metric would best
measure the bank's concern about minimizing false positives in the fraud detection AI?
(a) Recall
(b) Precision
(c) Accuracy
(d) F1-Score
3 What is Matplotlib library mainly used for? 1M

4 A grayscale image represents intensity values ranging from 0 to ________. 1M

5 _____are the words which occur very frequently in the corpus but do not addany value 1M
to it.
a. Special Characters
b. Stopwords
c. Roman Numbers
d. Useless Words
6 Seema is learning the conditions that make up the confusion matrix. She cameacross a 1M
scenario in which the machine that was supposed to predict a bird wasalways
predicting a bird. What is this condition called?
a. False Positive
b. True Positive
c. False Negative
d. True Negative
Q. 5 Answer any 5 out of the given 6 questions (1 x 5 = 5 marks)

1 Which of the following is invalid with regard to Data Privacy? 1M

a. Allow all permission while installing apps in smart phones can leak data.
b. Denying all permission will allow to install app in smart phone.
c. Use apps which don’t make permissions compulsory.
d. Use apps Reliable and Authentic.
2 Priya was confused with the terms used in the evaluation stage. Suggest her the term 1M
used for the percentage of correct predictions out of all the observations.
(a) Accuracy (b) Precision (c) Recall (d) F1-Score
3 What is a common application of Computer Vision in security systems? 1M
A) Document editing
B) Video streaming
C) Facial recognition
D) Web browsing
4 After Lemmatization, the words which we are get after removing the affixes is called 1M
a. Lemmat
b. Lemma
c. Lemmatiz
d. Lemmatiza
5 What is a chatbot called which uses simple FAQs without any intelligence? 1M
(a) Smart Chatbot
 (b) Script Chatbot
(c) AI Chatbot
(d) ML Chatbot
6 Raunak was learning the conditions that make up the confusion matrix. He came across 1M
a scenario in which the machine that was supposed to predict an animal was always
predicting not an animal. What is this condition called?
(a) False Positive (b) True Positive (c) False Negative (d) True Negative

SECTION B: SUBJECTIVE TYPE QUESTIONS

Answer any 3 out of the given 5 questions on Employability Skills (2 x 3 = 6 marks)
Answer each question in 20 – 30 words.
Q 6 List two best practices for effective communication. 2M

Q .7 What is the importance of setting goals in life? 2M

Q 8 “The Trojan Horse was a wooden horse said to have been used by the Greeks during 2M
the Trojan War to enter the city of Troy and win the war”.
What does Trojan horse mean in computer terminology?
Q .9 How is society helping entrepreneurs in their business? 2M

Q 10 Mention any two human activities that lead to environmental degradation. 2M

Answer any 4 out of the given 6 questions in 20 – 30 words each (2 x 4 = 8 marks)

Q 11 Differentiate between AI and Non-AI technology. 2M

Q .12 What do you understand by the Evaluation and Deployment stage in AI project cycle? 2M

Q 13 Explain the concept of bias and variance in machine learning and how they affect model 2M
performance.
Q .14 What is an RGB image? Why is it called so? 2M

Q 15 What is Tokenization? Count the number of tokens in the following sentence: If you fail, 2M
never give up because FAIL means "First Attempt in Learning.”
Q 16 People of a village are totally dependent on the farmers for their daily food items. 2M
Farmers grow new seeds by checking the weather conditions every year. An AI model is
being deployed in the village which predicts the chances of heavy rain to alert farmers
which helps them in doing the farming at the right time. Which evaluation parameter
out of precision, recall and F1 Score is best to evaluate the performance of this AI
model? Explain
Answer any 3 out of the given 5 questions in 50– 80 words each (4 x 3 = 12 marks)

Q.17 Explain any four Applications of Artificial Intelligence? 4M

Q.18 Explain the4WsofProblemScoping. 4M

Q.19 Explain learning-based AI modeling approaches.? 4M

Q.20 Define Text normalization and explain the different steps in involved. 4M
Q.21 An IT company situated in Bombay developed an AI model which predicts the 4M
purchasing of electronic gadgets. During testing, the AI model came up with the
following predictions.
Based on the given predictions, calculate the following
Reality
Confusion matrix
YES NO
YES 60 25
prediction
NO 5 10
How many total tests have been performed in the above scenario.
Calculate precision, recall and F1 score.

KENDRIYA VIDYALAYA SANGATHAN HYDERABAD REGION

ARTIFICIAL INTELLIGENCE (SUBJECT CODE - 417)
Class X
Model Question Paper – 14 (Solutions)

SECTION A: OBJECTIVE TYPE QUESTIONS

Q. 1 Marks
Answer any 4 out of the given 6 questions on Employability Skills (1 x 4 = 4 marks)
1 (a) Both A and R are correct and R is the correct explanation of A 1M
2 c. Mental 1M
3 (b)Not taking feedback 1M
4 d. Internet Scams 1M
5 c. Sustainable development 1M
6 c. Patient 1M
Q. 2 Answer any 5 out of the given 6 questions (1 x 5 = 5 marks)
1 Interpersonal Intelligence 1M
2 a. Step-by-step process 1M
3 Hidden Layers 1M
4 True 1M
5 d) Comma-separated value 1M
6 (b) NLP Kit 1M
Q. 3 Answer any 5 out of the given 6 questions (1 x 5 = 5 marks)
1 (d) AI is creating Unemployment 1M
2 (c) Clustering 1M
3 To extract insights and knowledge from data. 1M
4 B) Identifying and describing relevant characteristics from an image 1M
5 (d) Text and Speech 1M
6 Overfitting 1M
Q. 4 Answer any 5 out of the given 6 questions (1 x 5 = 5 marks)
1 When a user installs an app in the smartphone, it asks for access to gallery, contacts, 1M
etc. After accepting this, it gives the user agreement which most users accept without
realizing the implications. What is the concern here?
(a) Data Privacy (b) Unemployment (c) AI bias (d) No concern
 2 b) Precision. 1M
3 Matplotlib is a Python library used for Data Visualization 1M
4 A grayscale image represents intensity values ranging from 0 to ________. 1M
5 b. Stopwords 1M
6 False Negative 1M
Q. 5 Answer any 5 out of the given 6 questions (1 x 5 = 5 marks)
1 b. Denying all permission will allow to install app in smart phone. 1M
2 (a) Accuracy 1M
3 C) Facial recognition 1M
4 b. Lemma 1M
5 (b) Script Chatbot 1M
6 c)False Negative 1M

SECTION B: SUBJECTIVE TYPE QUESTIONS

Answer any 3 out of the given 5 questions on Employability Skills (2 x 3 = 6 marks)
Answer each question in 20 – 30 words.
Q 6 1. Use simple language 2M
2. Be respectful of others’ opinions
3. Do not form assumptions on culture, religion or geography
4. Try to communicate in person as much as possible
5. Use visuals
6. Take help of a translator to overcome differences in language
Q .7 1. The process of goal setting in your life helps you decide on how to live your life, 2M
where you want to be, and how you want to be in the future.
2. It helps you to focus on the end result instead of less important work.
3. This will make you successful in your career and personal life.
Q 8 A Trojan Horse is a type of malwarewhichdisguises itself i.e., it appears to be a useful 2M
software program but once it reaches a computer it starts behaving like a virus and
destroys data.
Q .9 Society is helping entrepreneurs by 2M
1. Creating needs
2. Providing raw material
3. buying/selling of items
4. making money
Q 10 1. Use of fertilisers, pesticides,etc for increasing the production of crops. 2M
2. Cutting down of forests for personal use such as construction of buildings, factories
etc
Answer any 4 out of the given 6 questions in 20 – 30 words each (2 x 4 = 8 marks)

Q 11 2M
AITECHNOLOGY NON-AITECHNOLOGY
Asoftwareormachinethatcanoperate A software or machine that performs
autonomously and adapt to user a fixed set of functions and does not
behavior adapt to user behaviour.
Example:Siri Example: MS Word
Q .12 Evaluation and Deployment is the final stage in AI project cycle. In evaluation, the 2M
trained model’s performance is evaluated using evaluation metrics. Once Evaluation is
done, the model is deployed to make real-life applications available and this process is
called Deployment.
Q 13 Bias refers to systematic error, while variance refers to model sensitivity to data. High 2M
bias leads to under fitting, while high variance leads to overfitting. The goal is to
balance bias and variance to achieve optimal model performance.
Q .14 RGB stands for RED GREEN BLUE.It represents digital images. 2M
RGB images are called so because they work on RGB color models which use the
primary colors (Red Green Blue) and produces a wide range of colors by combining
varying intensities of colors in each channel
Q 15 Tokenization is a fundamental process that involves breaking down sentences and 2M
transforming sentence segmentation into individual units called tokens. These tokens
can be words, numbers or special characters occurring in a sentence.
Tokenizers split the given sentence (raw data) as
*‘If’,‘you’,‘fail’,‘,’,‘never’,‘give’,‘up’,‘because’,‘FAIL’,‘means’,‘”’,‘First’,‘Attempt’,‘in’,‘Lear
ning’,‘”’,‘.’+.
Numberoftokens=17
Q 16 Let us take each of the factor into consideration at once, If precision is considered, FN 2M
cases will not betaken into account, so it will be of great loss as if the machine will
predict there will be no heavy rain, but if the rain occurred, it will be a big monetary
loss due to damage to crops.
If only recall is considered, then FP cases will not be taken into account. This situation
will also cause a big amount of loss, as all people of the village are dependent on
farmers for food, and if the model predicts there will be heavy rain and the farmers
may not grow crops, it will affect the basic needs of the people.
Hence F1 Score is the best suited parameter to test this AI model, which is the balance
between Precision and Recall.
Answer any 3 out of the given 5 questions in 50– 80 words each (4 x 3 = 12 marks)

Q.17 1. Healthcare: AI is used for diagnosing diseases, recommending treatments, and 4M

developing personalized care plans through predictive analytics.
2. Finance: AI systems help detect fraudulent transactions, automate trading, and
provide customer support via chatbots.
3. Autonomous Vehicles: AI enables self-driving cars to recognize obstacles, follow
traffic rules, and make real-time decisions.
4. Natural Language Processing (NLP): AI powers voice assistants like Siri and Alexa,
helping them understand and respond to human language.
Q.18 The 4 W's of Problem Scoping are Who, What, Where, and Why. These Ws help in 4M
identifying and understanding the problem in a better and efficient manner.
1. Who: The "Who" part helps us in comprehending and categorizing who all are
affected directly and indirectly by the problem and who are called the Stakeholders.
2. What: The "What" part helps us in understanding and identifying the nature of
the problem and how we get to know what helps to get us the evidence.
3. Where: "Where" does the problem arise, including the situation and the
location?
4. Why: "Why" is the given problem worth solving?
Q.19 Learning Based Approach: In this approach, the machine learns by itself. It refers to the 4M
AI modelling where the relationship or patterns in data are not defined by the
developer. In this approach, random data is fed to the machine to figure out patterns
and trends out of it. Generally, this approach is followed when the data is un labelled
 and too random for a human to make sense out of it. For example, suppose you have a
dataset of 1000 images of random stray dogs of your area. You would put this into a
learning approach-based AI machine and the machine would come up with various
patterns it has observed in the features of these 1000 images which you might not have
even thought of.
Q.20 Text Normalization is a process to reduce the variations in text’s word forms to a 4M
common form when the variation means the same thing. The different in text
normalization is
1. Sentence Segmentation
2. Tokenisation
3. Removing Stop words, Special characters and Numbers
4. Converting text to a common case
5. Stemming
6. Lemmatization
1. Sentence Segmentation: Under sentence segmentation, the whole text is divided into
individual sentences.
2. Tokenisation: After segmenting the sentences, each sentence is then further divided
into tokens. Tokens is a term used for any word or number or special character
occurring in a sentence. Under tokenisation, every word, number and special character
is considered separately and each of them is now a separate token.
3. Removing Stop words, Special characters and Numbers: Stop words are the words in
any language which do not add much meaning to a sentence. They can safely be
ignored without sacrificing the meaning of the sentence These words occur the most in
any given sentence but talk very little or nothing about the context or the meaning of it.
Hence, to make it easier for the computer to focus on meaningful terms, these words
are removed.
4. Converting text to a common case: After the stop words removal, we convert the
whole text into a similar case, preferably lower case. This ensures that the case-
sensitivity of the machine does not consider same words as different just because of
different cases.
5. Stemming: -stemming is the process in which the affixes of words are removed, and
the words are converted to their base form. In stemming, the stemmed words (words
which are we get after removing the affixes) might not be meaningful.
6. Lemmatization : In lemmatization, the word we get after affix removal (also known as
lemma) is a meaningful one. Lemmatization makes sure that lemma is a word with
meaning and hence it takes a longer time to execute than stemming.
Q.21 Accuracy is defined as the percentage of correct predictions out of all the observations. 4M
A prediction can be said to be correct if it matches the reality.
(TP +TN )
Accuracy = TP +TN +FP +FN ∗ 100%
Recall is defined as the fraction of positive cases that are correctly identified.
TP
Recall = ∗ 100
TP + FN
Precision is defined as the percentage of true positive cases versus all the cases where
the prediction is true.
TP
Precision = ∗ 100
TP + FP

F1 score is defined as the measure of balance between precision and recall.

Precision ∗ Recall
F1 score = 2 ∗
Precision + Recall
Precision = True Positives / (True Positives + False Positives) = 60 / (60 + 5) = 0.923
 Recall = True Positives / (True Positives + False Negatives) = 60 / (60 + 25) = 0.706
F1 Score = 2 * (Precision * Recall) / (Precision + Recall) = 2 * (0.923 * 0.706) / (0.923 +
0.706) ≈ 0.801
(ii) Total tests performed = Sum of all entries in the confusion matrix = 60 + 25 + 5 + 10
= 100

KENDRIYA VIDYALAYA SANGATHAN HYDERABAD REGION

MODEL QUESTION PAPER - 15
2024-25
CLASS: X TIME:02 HOURS
SUBJECT: ARTIFICIAL INTELLEGENCE MAX.MARKS:50

SECTION A: OBJECTIVE TYPE QUESTIONS

Q. 1 Marks
Answer any 4 out of the given 6 questions on Employability Skills (1 x 4 = 4 marks)

1 Assertion(A): Giving general overview is a type of non-specific feedback. 1M

Reason(R): Non-specific feedback has to be descriptive.
(a) Both A and R are correct and R is the correct explanation of A
(b) Both A and R are correct but R is NOT the correct explanation of A
(c) A is correct but R is not correct
(d) A is not correct but R is correct
2 Pranjali gets up at 5 am and goes to her badminton classes. Then she comes home and 1M
finishes her homework before going to school. She does this all by herself. No one tells
her to do it. This is an example of
(a) Self-motivation
(b) External motivation
(c) Both self and external motivation
(d) Not any specific type of motivation
3 What are the ABC of Stress Management? 1M
a) Avertible, Belief, Consequences.
b) Adversarial, Being, Control,
c) Adversity, Belief, Consequences
d) Adversity, Belief, Control
4 Internet Explorer is a ……... 1M
a. Internet
b. Web browser
c. Search Engine
d. Service Provide
5 Which of the following are common Sustainable Practices? 1M
a. Reusing of Waste Water
b. Conserving Rain Water
c. Segregating waste at source
d. All of the above
6 Ritu leaves the company she worked for and starts catering food for marriage 1M
 programmes. She is an _________________.
a. Entrepreneur
b. Employee
c. Cook
d. None of the above
Q. 2 Answer any 5 out of the given 6 questions (1 x 5 = 5 marks)

1 People with strong………….intelligence are able to use words well in both writing and 1M
speaking.These people are typically excellent writers, poets, lawyers and public
speakers.
2 The stages of the AI project cycle are _____________. 1M
a. Problem Scoping & Data Acquisition
b. Data Exploration & Modeling
c. Evaluation
d. All of the above
3 Statement A: Neural networks are made up of layers of neurons. 1M
Statement B: Human brain consists of millions of neurons.
i)Only Statement A is correct
(ii) Only Statement B is correct
(iii) Both the statements are correct
(iv) None of the statements is correct
4 Divya was learning neural networks. She understood that there were three layers in a 1M
neural network. Help her identify the layer that does processing in the neural network.
(a) Output layer
(b) Hidden layer
(c) Input layer
(d) Data layer
5 CSV file extension stands for_________ 1M
a) Cell-separated verb
b) Civil-services van
c) Customer-service value
d) Comma-separated value
6 Identify the type of chatbot with the information given below: 1M
All the assistants like Google Assistant, Alexa, Cortana, Siri, etc., can not only handle
conversations but also manage to do other tasks.
Q. 3 Answer any 5 out of the given 6 questions (1 x 5 = 5 marks)

1 What is important to make a Good AI Machine? 1M

a. Algorithm
b. Data
c. Test cases
d. All the above.
2 Identify the algorithm based on the given graph 1M

(a) Dimensionality reduction

(b) Classification
(c) Clustering
 (d) Regression

3 Deep Learning is a subset of 1M

(a) Artificial Intelligence (b)Machine Learning
(b) Computer Vision (d)Natural Language Processing
4 Aspect ratio in computer vision refers to proportional relationship between the 1M
____________ and ____________ of an object or image.
(a) Width, Height (b) Width, Pixels
(c) Height, Intensity (d) Length, Breadth
5 Aaron is facing issue in his internet connectivity at home. He called customer care 1M
service, A virtual assistant took his complaint and replied with an acknowledgement
number. What is the AI technology used by Internet service provider?
a. Data Science
b. Machine Learning
c. Computer Vision
d. Natural Language Processing

6 Evaluation is the process of understanding the reliability of any AI model based on 1M

predictions and comparing it with reality. Which of the following data sets are used to
build and evaluate the model?
(a)Training and test data sets (b) Test data sets and training data sets
(c) Test data sets and noise (d) Raw data sets and training data sets

Q. 4 Answer any 5 out of the given 6 questions (1 x 5 = 5 marks)

1 Which of these is not a phase for a data science project? 1M

(a) Problem scoping
(b) Data acquisition
(c) Data exploration
(d) Data summarisation
2 Which evaluation metrics should be used when classes are balanced and both positive 1M
and negative instances are equally important?
(a) Precision (b) Accuracy (c) Recall (d) F1 Score
3 We can’t make “good” decisions without information. (True/False) 1M

4 What does the pixel value represent in a grayscale image? 1M

A) The color
B) The intensity
C) The contrast
D) The brightness
5 ____________ words are commonly used words which occur very frequently and do 1M
not contribute much in a text
6 ......................... is the process of understanding the reliability of any AI model, based on 1M
outputs by feeding test data sets into the model and comparing them with actual
answers. (Modelling/Evaluation)
Q. 5 Answer any 5 out of the given 6 questions (1 x 5 = 5 marks)

1 AI Bias simply means 1M

(a) Accessibility of AI to all
(b) Unfair predictions due to discrimination in training data
(c) Risk of data security
 (d) Increasing risk of cyber attacks

2 The output given by the AI machine is known as ________. (Prediction/Reality) 1M

3 Which of the following tasks involves identifying and locating objects within an image? 1M
A) Image compression
B) Feature extraction
C) Object detection
D) Image enhancement
4 Which of these is not an NLP library? 1M
(a) NLTK
(b) NLP Kit
(c) Open NLP
(d) NLP Suite
5 What is the process of extracting emotions within a text data using NLP called? 1M
a. Sentiment Analysis
b. Emotional Data Science
c. Emotional Processing
d. Emotional Classification
6 _____________ is used to record the result of comparison between the prediction and 1M
reality. It is not an evaluation metric but a record which can help in evaluation.
(Accuracy Table/Confusion Matrix)

SECTION B: SUBJECTIVE TYPE QUESTIONS

Answer any 3 out of the given 5 questions on Employability Skills (2 x 3 = 6 marks)
Answer each question in 20 – 30 words.
Q 6 List two best practices for effective communication. ( 2M

Q .7 Write two stress causal agents. 2M

Q 8 Explain two popular mobile operating systems. 2M

Q .9 Hiten is working as a software engineer in an IT company where he gets a regular 2M

monthly salary and other benefits. What kind of entrepreneurship activity is Hiten
involved in?
Q 10 What do you understand by the terms Green Economy and Green Consumer? 2M

Answer any 4 out of the given 6 questions in 20 – 30 words each (2 x 4 = 8 marks)

Q 11 Differentiate between ML and DL. 2M

Q .12 Nitya has learnt different types of modelling in AI project life cycle. But she is confused 2M
about the Supervised and Unsupervised learning algorithms. Help her to understand
them.
Q 13 List some sources of acquiring data. 2M

Q .14 What is resolution, and how does it affect image quality? 2M

Q 15 Write the step-by-step approach to implement bag of words algorithm. 2M

Q 16 Give the possible reasons for an AI model not being efficient? 2M

Answer any 3 out of the given 5 questions in 50– 80 words each (4 x 3 = 12 marks)

Q.17 How Deep Learning Machines work? 4M

Q.18 Make a 4W Project Canvas. 4M

Risks will become more concentrated in a single network as more and more innovative
technologies are used. In such cases, cybersecurity becomes incredibly complex and is
no longerunder the authority of firewalls. It won’t be able to recognize odd behavior
patterns, includingdata migration.
Consider how AI systems can sift through voluminous data to find user behavior that is
vulnerable. To explicitly define the scope, the method of data collection, the model,
and the evaluation criteria, use an AI project cycle.
Q.19 Explain the Supervised Learning. 4M

Q.20 A 52-year-old man named Satya, a partially blind writer, writes short stories and poems 4M
in rural newspapers and magazines. He is dependent on villagers for his work. Suggest
some NLP-based techniques so that he can continue his work independently.
Q.21 A binary classification model has been developed to classify the information spread 4M
through social media is as either “Fake ” or “Real ”. The model was tested on a dataset
of 300 information, and the resulting confusion matrix is as follows:

Reality
Confusion matrix
YES NO
YES 150 40
prediction
NO 50 60
calculate Accuracy, precision, recall and F1 score.

KENDRIYA VIDYALAYA SANGATHAN HYDERABAD REGION

ARTIFICIAL INTELLIGENCE (SUBJECT CODE - 417)
Class X
Model Question Paper – 15 (Solutions)

SECTION A: OBJECTIVE TYPE QUESTIONS

Q. 1 Marks
Answer any 4 out of the given 6 questions on Employability Skills (1 x 4 = 4 marks)
1 (c) A is correct but R is not correct 1M
2 (a) Self-motivation 1M
3 c) Adversity, Belief, Consequences 1M
4 b. Web browser 1M
5 d. All of the above 1M
6 a. Entrepreneur 1M
Q. 2 Answer any 5 out of the given 6 questions (1 x 5 = 5 marks)
1 Linguistic 1M
2 d. All of the above 1M
3 (iii) Both the statements are correct 1M
4 (b) Hidden layer 1M
 5 d) Comma-separated value 1M
6 Smartbot 1M
Q. 3 Answer any 5 out of the given 6 questions (1 x 5 = 5 marks)
1 d. All the above. 1M
2 (c) Clustering 1M
3 Data Science 1M
4 (a)Width,Height 1M
5 d. Natural Language Processing 1M
6 (a)Training and test data sets 1M
Q. 4 Answer any 5 out of the given 6 questions (1 x 5 = 5 marks)

1 (d)Data summarisation 1M
2 (c)Accuracy 1M
3 True 1M
4 B) The intensity 1M
5 Stop 1M
6 Evaluation 1M
Q. 5 Answer any 5 out of the given 6 questions (1 x 5 = 5 marks)
1 (b) Unfair predictions due to discrimination in training data 1M
2 Prediction 1M
3 C) Object detection 1M
4 (b) NLP Kit 1M
5 d. Emotional Classification 1M
6 Confusion Matrix 1M

SECTION B: SUBJECTIVE TYPE QUESTIONS

Answer any 3 out of the given 5 questions on Employability Skills (2 x 3 = 6 marks)
Answer each question in 20 – 30 words.
Q 6 There are different methods of communication: non-verbal, verbal andvisual. However, all 2M
these methods can only be effective if we follow thebasic principles of professional
communication skills. These can beabbreviated as 7 Cs i.e.,
Clear, Concise, Concrete, Correct, Coherent, Complete and Courteous.
(Any two of 7 C’s)
Q .7 i.Mental: It is easy to get stressed due to examinations and assignments. There are 2M
expectations from parents and teachers besides peer pressure. This can lead to feelings of
anxiety and stress.
ii.Social: Managing relationships and friendships can be difficult in today’s time of social media
and societal expectations. One feels the need to be best at everything which can create a false
sense of pressure for overachievement.
Q 8 Mobile operating system is specially designed for mobile phones, tablets, smartwatches, 2M
etc.Twomobileoperatingsystemsare:
(i) Android OS: It is an open-source and free operating system. It is one of the most
popular OS.AndroidOSis developed byGoogle.
(ii) Apple iOS: It is designed to run on apple devices such as iPhones, iPad tablets, etc.
Apple iOShasvery strongsecurity features.
Q .9 Hiten is working as a salaried employee in an IT company and draws a regular salary (wages) 2M
and other benefits from his office. Salary is a form of monetary compensation for employees
and is paid according to the amount of time worked by the employee. It does not come under
entrepreneurship activity.
Q 10 Green economy is an economic system that seeks to promote sustainable development by 2M
incorporating principles and practices that reduce environmental risks by preserving
ecological scarcities.
Green consumer is an individual who makes purchasing decisions, keeping in mind the
environmental and sustainability aspects.
Answer any 4 out of the given 6 questions in 20 – 30 words each (2 x 4 = 8 marks)

Q 11 2M
ML DL
ML stands for Machine Learning. It DL stands for Deep Learning. It is a subset
is a subset of Artificial Intelligence of Machine Learning which enables
which enables machines to software to train itself to perform tasks with
improve at tasks with vast amounts of data.
experience(data).
The intention of Machine In Deep Learning, the machine is trained
Learning is to enable machines with huge amounts of data which helps it in
to learn by themselves using the training itself around the data. Such
provided data and make accurate machines are intelligent enough to develop
Predictions/Decisions. algorithms for themselves.
Machine Learning uses two types of Deep Learning uses Neural Networks
algorithms which makes it the most advanced form of
–Supervised and Unsupervised. Artificial Intelligence.

Q Supervised Learning: In a supervised learning model, the data set which is fed to the machine 2M
.12 is labelled. It means that the data used to train the machine is already tagged with the correct
answer. In other words, when the machine is provided with the new data set, the supervised
learning algorithm analyzes the training data and produces a correct outcome from labelled
data.

Unsupervised Learning: An unsupervised learning model works on an unlabelled dataset.

This means that the data which is fed to the machine is random, and there is a possibility that
the person who is training the model does not have any information regarding it. The
unsupervised learning models are used to identify relationships, patterns and trends out of the
data which is fed into it. It helps the user in understanding what the data is about and what are
the major features identified by the machine in it.
Q 13 Survey, Questionnaire, Open-sourced Govt. portal and statistical sites, records and 2M
documents.
Q Resolution refers to the number of pixels in an image, usually measured in pixels per inch 2M
.14 (PPI). Higher resolution means more pixels and greater detail, resulting in better image
quality.
Q 15 1.Text Normalization: Collect data and pre-process it by removing the known stop words. 2M
2. Design the vocabulary. Prepare the corpus (a collection of words) from the words in the
 document. The whole collection of textual data from all the documents is called corpus.
3. Create Document vectors. Score the word’s frequency in the document.
4. Calculate TF-IDF. Calculate Term Frequency and Inverse Document Frequency.
Q 16 • Lack of Training Data 2M
• Unauthenticated Data / Wrong Data
• Inefficient coding / Wrong Algorithms
Answer any 3 out of the given 5 questions in 50– 80 words each (4 x 3 = 12 marks)

Q.17 Deep Learning is a subset of Machine Learning. Deep Learning enables machines to train with 4M
huge amount of data which helps it in training itself around the data. These machines are
capable to develop algorithms for themselves.
Q.18 Who: The users are organizations that rely on AI for cybersecurity. 4M
What: The project focuses on using AI to enhance cybersecurity by detecting unusual
behaviors, especially data migration threats.
Where: Applied in environments with complex interconnected systems vulnerable to attacks.
Why: Traditional firewalls are no longer sufficient to manage risks; AI provides more advanced
solutions by analyzing large amounts of data to identify potential threats, improving security
measures beyond manual monitoring.
Q.19 Supervised learning is an approach to creating artificial intelligence (AI), where the program is 4M
given labelled input data and the expected output results. OR Supervised learning is a
learning in which we teach or train the machine using data which is well labelled that means
some data is already tagged with the correct answer. After that, the machine is provided with
a new set of examples (data) so that supervised learning algorithm analyses the training data
(set of training examples) and produces a correct outcome from labelled data. In a supervised
learning model, the dataset which is fed to the machine is labelled. It means some data is
already tagged with the correct answer. In other words, we can say that the dataset is known
to the person who is training the machine only then he/she is able to label the data.
Q.20 There are many applications based on NLP which Satya may use to continue his passion 4M
independently. Any application that converts speech to text will work for Satya. Such
applications may include:
(a) Siri or Alexa: Available on smart devices, Siri is a feature of IOS and is available on
iPhone. Alexa, onthe other hand, is an Amazon product.
(b) Microsoft word: The feature which recognizes speech and converts it into text is now
available on the latest version of Microsoft word.
(c) Applications like DictationandGboard may also work well for Satya.
Q.21 Accuracy = (TP +TN ) ∗ 100% 4M
TP +TN +FP +FN
Recall is defined as the fraction of positive cases that are correctly identified.
TP
Recall = ∗ 100
TP + FN
Precision is defined as the percentage of true positive cases versus all the cases where the
prediction is true.
TP
Precision = ∗ 100
TP + FP

F1 score is defined as the measure of balance between precision and recall.

Precision ∗ Recall
F1 score = 2 ∗
Precision + Recall
Accuracy=(150+60)/300=0.7
Recall=150/200=0.75
Precision=150/190=0.789
F1 score=2*0.75*0.789/(0.75+0.789)=0.76
 KENDRIYA VIDYALAYA SANGATHAN HYDERABAD REGION
MODEL QUESTION PAPER-16
2024-25
CLASS:X TIME:02HOURS
SUBJECT:ARTIFICIAL INTELLEGENCE MAX.MARKS:50

SECTION A: OBJECTIVE TYPE QUESTIONS

Q. Ma
Answer any 4 out of the given 6 questions on Employability Skills (1 x 4 = 4 marks)
1 rks
1 “Hey Dear! How are you!” is a type of ___________ feedback. 1M
(a) formal
(b) informal
(c) specific
(d) descriptive
2 Our emotional, mental, physical, and social responses to perceived demands or threats are 1M
referred to as__________.
a. Stress
b. Blood pressure
c. Constipation
d. Heart attack
3 Identifying weaknesses : 1M
a. Think of anything that you are always successful at.
b. Think about what others like in you.
c. Take out time and think about what you do well.
d. Be open to feedback and accept your weaknesses
4 Assertion (A): Regular maintenance of a computer can improve its performance and longevity. 1M
Reason (R): Maintenance activities like disk cleanup, defragmentation, and software updates
help in preventing system slowdowns and data corruption.
Assertion
(a) Both A and R are true, and R is the correct explanation of A.
(b) Both A and R are true, but R is not the correct explanation of A.
(c) A is true, but R is false.
(d) A is false, but R is true.
5 Which organisation has made the Sustainable Development Goals. 1M
(a) United Nations
(b) League of Nations
(c) UNICEF
(d) World Health Organisation
6 An entrepreneur is receiving negative feedback about his product from customers. What 1M
should be his approach to handle the situation?
A) Ignore the feedback and continue selling the same product
B) Analyze the feedback, identify areas of improvement, and make changes to the product
C) Blame customers for not understanding the product
D) Stop selling the product altogether
Q. 2 Answer any 5 out of the given 6 questions (1 x 5 = 5 marks)
 1 Assertion (A): Machine learning is a subset of Artificial Intelligence. 1M
Reason (R): Machine learning enables AI systems to learn from data and improve their
performance over time without explicit programming.
(a) Both A and R are true, and R is the correct explanation of A.
(b) Both A and R are true, but R is not the correct explanation of A.
(c) A is true, but R is false.
(d) A is false, but R is true.
2 A software tool helps users calculate their taxes by following predefined rules. It doesn’t 1M
adapt or learn over time. Is this an example of AI?
A) Yes, it makes decisions
B) No, it doesn’t learn from new data
C) Yes, because it automates a process
D) Yes, because it performs calculations
3 What is the main advantage of using neural networks over traditional algorithms? 1M
A) Simplicity in design
B) Ability to model complex patterns
C) Less data requirement
D) Faster computation
4 ___________ are loosely modeled after how neurons in the human brain behave. 1M
a. Neural networks
b. Neural science
c. Neural Analysis
d. None of the above
5 What does CSV stand for in computing? 1M
A) Comma-Spaced Values
B) Common-Shared Values
C) Comma-Separated Values
D) Code-Specific Variables
6 Statement 1: Tokenization is the process of converting numerical data into text. 1M
Statement 2: Tokenization helps in breaking text into smaller parts for analysis.
(a) Both Statement 1 and Statement 2 are true.
(b) Statement 1 is true, and Statement 2 is false.
(c) Statement 1 is false, and Statement 2 is true.
(d) Both Statement 1 and Statement 2 are false.
Q. 3 Answer any 5 out of the given 6 questions (1 x 5 = 5 marks)

1 An AI system is asked to recommend the best movie based on user preferences. What is the 1M
most important step for the AI system to make an accurate decision?
A) Randomly select a movie
B) Analyze the user’s past viewing habits and preferences
C) Choose the most popular movie available
D) Select a movie that is on sale
2 Which of the following is an example of supervised learning? 1M
A) Clustering customers based on purchasing behavior
B) Predicting house prices based on historical data
C) Finding hidden patterns in customer reviews
D) Reducing the number of features in a dataset
3 Which of the following is a common programming language used in data science? 1M
(a) HTML
(b) Java
(c) Python
 (d) CSS

4 What is the primary function of image classification in Computer Vision? 1M

A) Sorting text documents
B) Identifying which class or category an image belongs to
C) Translating languages based on image content
D) Storing large image files
5 ________________is considered to be one of the best methods to address stress as it is easy 1M
to implement on people and also gives good results.
a. CAD
b. CBT
c. CBD
d. CAM
6 _________ is defined as the percentage of correct predictions out of all the observations. 1M
a. Overfitting
b. Accuracy
c. Confusion Matrix
d. Data acquisition
Q. 4 Answer any 5 out of the given 6 questions (1 x 5 = 5 marks)
1 What is the role of a data scientist? 1M
(a) To collect and store data only
(b) To analyze data and derive actionable insights
(c) To maintain databases
(d) To manage IT infrastructure
2 Statement 1: The F1-score is the harmonic mean of precision and recall. 1M
Statement 2: A low F1-score indicates that both precision and recall are high for the AI model.
a) Both Statement 1 and Statement 2 are true.
b) Both Statement 1 and Statement 2 are false.
c) Statement 1 is true, but Statement 2 is false.
d) Statement 1 is false, but Statement 2 is true.
3 An e-commerce company uses data science to analyze customer buying patterns and 1M
recommend products based on previous purchases. The company’s recommendation system
helped increase sales by 25% within six months. The system uses customer data such as
browsing history, purchase history, and product ratings to make personalized
recommendations. What is the primary application of data science in this case?
(a) Analyzing sales patterns to reduce costs
(b) Predicting the financial health of the company
(c) Providing personalized product recommendations to increase sales
(d) Improving website design and layout
4 Computer Vision is most commonly used in which of the following applications? 1M
A) Online banking
B) Image search engines
C) Word processing
D) Audio recording
5 Which of the following is a virtual assistant developed by Microsoft? 1M
a. Siri
b. Cortana
c. Google Assistant
d. Alexa
 6 A healthcare company developed an AI model to detect early signs of diabetes from patient 1M
medical records. After training, the model was evaluated using a dataset of patient records.
The evaluation revealed that the model had an accuracy rate of 90% but also showed a higher
rate of false negatives, meaning some patients with diabetes were not detected by the model.
What aspect of the model is a key concern during the Evaluation stage in this case?
(a) High accuracy rate
(b) High rate of false negatives
(c) The size of the dataset
(d) The user interface of the AI model
Q. 5 Answer any 5 out of the given 6 questions (1 x 5 = 5 marks)
1 Sara is working on speech recognition software. She notices that the system needs to handle 1M
highly complex patterns in the audio data, which requires multiple layers of processing. Which
AI technique should she use?
A) Machine Learning with simple models
B) Deep Learning to handle complex patterns
C) Rule-based algorithms
D) Human-based manual processing
2 _______ is defined as the percentage of true positive cases versus all the cases where the 1M
prediction is true.
a. Overfitting
b. Accuracy
c. Precision
d. Data acquisition
3 Which of the following is NOT an example of a Computer Vision task? 1M
A) Object detection
B) Image classification
C) Text summarization
D) Image segmentation
4 ________ identify each document in the corpus, find out how many times the word from 1M
theunique list of words has occurred.
a. Text Normalization
b. Create Dictionary
c. Document Vectors
d. All of the above
5 TFIDF stands for ___________. 1M
a. Team Frequency and Inverse Document Frequency
b. Term Frequency and Inverse Document Frequency
c. Top Frequency and Inverse Document Frequency
d. Table Frequency and Inverse Document Frequency
6 ___________ can be defined as the measure of balance between precision and recall. 1M
a. Recall
b. Accuracy
c. Precision
d. F1 Score
SECTION B: SUBJECTIVE TYPE QUESTIONS
Answer any 3 out of the given 5 questions on Employability Skills (2 x 3 = 6 marks)
Answer each question in 20 – 30 words.
Q 6 List four characteristics of effective feedback. 2M
Q .7 What do you mean by SMART goals? 2M

Q 8 Name four commonly used operating systems. 2M

Q .9 How has entrepreneurship positively impacted the economy? Provide details. 2M

Q 10 List four Sustainable Development Goals (SDGs) included in the 2030 Agenda for Sustainable 2M
Development.
Answer any 4 out of the given 6 questions in 20 – 30 words each (2 x 4 = 8 marks)

Q 11 A healthcare provider is planning to collect patient data for an AI-driven health analytics 2M
project. They must ensure ethical standards are met. What ethical considerations
should the provider address when acquiring patient data for their AI project?
Q .12 A city government wants to implement a smart traffic management system using AI. 2M
They are at the problem scoping stage and need to identify the relevant stakeholders
for the project. What steps should the city government take to identify stakeholders
effectively, and how can engaging these stakeholders benefit the project?
Q 13 How can we use data science in the field health care. 2M

Q .14 What do you understand by image classification. 2M

Q 15 What are stop words? Explain with the help of examples. 2M

Q 16 Which two parameters are considered for Evaluation of a model? 2M

Answer any 3 out of the given 5 questions in 50– 80 words each (4 x 3 = 12 marks)

Q.17 What do you understand by AI, ML & DL? How are they different from each other? 4M

Q.18 Make 4W canvas:- 4M

A non-profit organization aims to develop an AI model to predict food shortages in
various regions to optimize their supply chain. They have collected some initial data on
past shortages but are unsure how to define the problem accurately. How should the
organization approach defining the problem scope using 4W canvas for their AI project?
Q.19 What is unsupervised learning? Explain the concept of clustering and dimensionality 4M
reduction.
Q.20 Through a step-by-step process, calculate TFIDF for the given corpus : 4M
Document1 : Johny Johny, Yes, Papa,
Document2 : Eating sugar? No Papa
Document3 : Telling lies? No Papa
Document4 : Open your mouth, Ha! Ha! Ha!
(Note:- log 4 =0.602, log(4/3)=0.124, log(2)=0.301)
Q.21 What is a confusion matrix? Explain in detail with the help of an example. 4M

KENDRIYA VIDYALAYA SANGATHAN HYDERABAD REGION

ARTIFICIAL INTELLIGENCE (SUBJECTCODE -417)
Class X
Model Question Paper–16(Solutions)
Q.No Answer
 Q. 1 Answerany4outofthegiven6questionsonEmployabilitySkills(1 x4=4marks)
i. Answer: (b) Informal
ii. Answer: (a) Stress
iii. Answer: (d) Be open to feedback and accept your weaknesses
iv. Answer: (a) Both A and R are true, and R is the correct explanation of A
v. Answer: (a) United Nations
vi. Answer: (b) Analyze the feedback, identify areas of improvement, and make changes to the
product
Q. 2 Answer any5out ofthegiven6questions(1x5=5marks)
i. Answer: (a) Both A and R are true, and R is the correct explanation of A
ii. Answer: (b) No, it doesn’t learn from new data
iii. Answer: (b) Ability to model complex patterns
iv. Answer: (a) Neural networks
v. Answer: (c) Comma-Separated Values
vi. Answer: (c) Statement 1 is false, and Statement 2 is true
Q. 3 Answer any5out ofthegiven6questions(1x5=5marks)
i. Answer: (b) Analyze the user’s past viewing habits and preferences
ii. Answer: (b) Predicting house prices based on historical data
iii. Answer: (c) Python
iv. Answer: (b) Identifying which class or category an image belongs to
v. Answer: (b) CBT
vi. Answer: (b) Accuracy
Q. 4 Answer any5out ofthegiven6questions(1x5=5marks)
i. Answer: (b) To analyze data and derive actionable insights
ii. Answer: (c) Statement 1 is true, but Statement 2 is false
iii. Answer: (c) Providing personalized product recommendations to increase sales
iv. Answer: (b) Image search engines
v. Answer: (b) Cortana
vi. Answer: (b) High rate of false negatives
Q. 5 Answer any5out ofthegiven6questions(1x5=5marks)
i. Answer: (b) Deep Learning to handle complex patterns
ii. Answer: (c) Precision
iii. Answer: (c) Text summarization
iv. Answer: (c) Document Vectors
v. Answer: (b) Term Frequency and Inverse Document Frequency
vi. Answer: (d) F1 Score
SECTIONB:SUBJECTIVE TYPE QUESTIONS
6  Specific (0.5 marks)
An  Timely (0.5 marks)
s
 Balanced (0.5 marks)
 Actionable (0.5 marks)
7. SMART goals are specific, measurable, achievable, relevant, and time-bound objectives that help in
setting clear and realistic targets.

8.  Windows
 macOS
 Linux
 Android
9. Entrepneurship promotes job creation, innovation, contributes to GDP growth, and encourages
investment. It also fosters competition, leading to better products and services.
10.  No poverty
 Zero hunger
 Quality education
 Climate action
11. Ethical considerations include:
 Ensuring informed consent
 Maintaining data privacy
 Securing sensitive information
 Preventing bias in data usage
12. Steps to identify stakeholders:
 Conduct a stakeholder analysis
 Engage with citizens, government agencies, and traffic authorities

Benefits:
 Increased support and collaboration
 Better design and functionality
13. Data science can help in:
 Predictive analytics for disease prevention
 Personalized medicine and treatments
 Monitoring health trends
 Fraud detection in insurance claims
14. Image classification is the process of categorizing and labeling images into predefined classes based on
their visual content. It is commonly used in applications like facial recognition and medical diagnosis.
15. Stop words are common words (e.g., "the," "is," "in") that are typically removed from text during
natural language processing to focus on important terms.
16. Precision and recall are two important parameters for evaluating the performance of a machine learning
model.
17. AI (Artificial Intelligence): Broad field focused on creating systems that mimic human
intelligence.
ML (Machine Learning): Subset of AI, enabling systems to learn from data without explicit
programming.
DL (Deep Learning): Subset of ML that uses neural networks with multiple layers to model
complex patterns.
Differences:
AI includes ML, which in turn includes DL. DL works with large datasets and complex patterns, while ML
uses simpler algorithms.
18.

19.  Unsupervised Learning: A type of machine learning where the model learns patterns from
unlabelled data.
 Clustering: Grouping similar data points together based on shared characteristics.
 Dimensionality Reduction: Reducing the number of features in a dataset while retaining essential
information to make data analysis easier.
20. TF-IDF Calculation for the Given Corpus
Step 1: List the Unique Terms in the Corpus
Johny, Yes, Papa, Eating, sugar, No, Telling, lies, Open, your, mouth, Ha,
Step 2: Term Frequency (TF)
Document 1: "Johny Johny, Yes, Papa" Document 2: "Eating sugar? No Papa"
Total terms: 4 Total terms: 4
TF: TF:
Johny: 2/4 = 0.5 Eating: 1/4 = 0.25
Yes: 1/4 = 0.25 sugar: 1/4 = 0.25
Papa: 1/4 = 0.25 No: 1/4 = 0.25
Papa: 1/4 = 0.25
Document 3: "Telling lies? No Papa" Document 4: "Open your mouth, Ha! Ha! Ha!"
Total terms: 4 Total terms: 6
TF: TF:
Telling: 1/4 = 0.25 Open: 1/6 = 0.167
lies: 1/4 = 0.25 your: 1/6 = 0.167
No: 1/4 = 0.25 mouth: 1/6 = 0.167
Papa: 1/4 = 0.25 Ha: 3/6 = 0.5

Step 3: Document Frequency (DF)

DF for each term:
Johny: 1 (only in Document 1) Yes: 1 (only in Document 1) Papa: 3 (Documents 1, 2, 3)
Eating: 1 (only in Document 2) sugar: 1 (only in Document 2) No: 2 (Documents 2, 3)
Telling: 1 (only in Document 3) lies: 1 (only in Document 3) Open: 1 (only in Document 4)
your: 1 (only in Document 4) mouth: 1 (only in Document 4) Ha: 1 (only in Document 4)
Step 4: Inverse Document Frequency (IDF)
IDF is calculated using the formula:
IDF Calculations:
 IDF Calculations:

Step 5: Calculate TF-ID

For Document 1: For Document 2:

 Johny: 0.5×0.602=0.3010  Eating: 0.25×0.602=0.1505

 Yes: 0.25×0.602=0.1505  sugar: 0.25×0.602=0.1505
 Papa: 0.25×0.124=0.031  No: 0.25×0.301=0.07525
 Papa: 0.25×0.124=0.031

For Document 3: For Document 4:

 Telling: 0.25×0.602=0.1505  Open: 0.167×0.602=0.1005

 lies: 0.25×0.602=0.1505  your: 0.167×0.602=0.1005
 No: 0.25×0.301=0.07525  mouth: 0.167×0.602=0.1005
 Papa: 0.25×0.124=0.031  Ha: 0.5×0.602=0.301

21. A Confusion Matrix is a table used to evaluate the performance of a classification model. It provides
insights into how well the model is performing by showing the actual and predicted classifications side
by side. It helps in understanding the accuracy, precision, recall, and other important metrics of the
model.
The matrix consists of four important values:
 True Positive (TP): The model correctly predicts the positive class.
 True Negative (TN): The model correctly predicts the negative class.
 False Positive (FP): The model incorrectly predicts the positive class).
 False Negative (FN): The model incorrectly predicts the negative class

Structure of a Confusion Matrix:

Predicted Positive Predicted Negative
Actual Positive True Positive (TP) False Negative (FN)
Actual Negative False Positive (FP) True Negative (TN)
Example:
Let’s assume we have a binary classification model to detect whether an email is spam or not spam. We
have a dataset with 100 emails, where:
 60 emails are actually spam .40 emails are not spam

Our model made predictions, and we generated the following confusion matrix:
Predicted Spam Predicted Not Spam
Actual Spam 50 (TP) 10 (FN)
Actual Not Spam 5 (FP) 35 (TN)
 KENDRIYA VIDYALAYA SANGATHAN HYDERABAD REGION
MODEL QUESTION PAPER-17
2024-25
CLASS:X TIME:02HOURS
SUBJECT: ARTIFICIAL INTELLEGENCE MAX.MARKS:50
SECTION A: OBJECTIVE TYPE QUESTIONS
Q. 1 Marks
Answer any 4 out of the given 6 questions on Employability Skills (1 x 4 = 4 marks)
1 Which of these are examples of positive feedback? 1M
(a) Excellent, your work has improved.
(b) You should come office on time.
(c) You are always doing it the wrong way.
(d) All of the above
2 Ravi works hard to get the best student award at the end of year. What type of 1M
motivation is this?
a. Internal
b. External
c. Both internal and external
d. Not any specific type of motivation
3 _________ is the ability to control one’s emotions, thoughts, and behavior effectively in 1M
different situations.
a. Self-Guided
b. Self-Awareness
c. Self-Motivation
d. Self-Management
4 DOS stands for ________ 1M
(a) Disk Operating System
(b) Dot Operating System
(c) Disk Open System
(d) Disk Operating Secure
5 Assertion (A): Green skills help in promoting sustainable development. 1M
Reason (R): Green skills focus on reducing the environmental impact of economic
activities by conserving resources and minimizing waste.
(a) Both A and R are true, and R is the correct explanation of A.
(b) Both A and R are true, but R is not the correct explanation of A.
(c) A is true, but R is false.
(d) A is false, but R is true.
6 Rahul believes that only people born with special business skills can become successful 1M
entrepreneurs. Which of the following would be the best advice for him?
A) He is correct; only people with natural talents can succeed in business.
B) Entrepreneurs can learn skills through education, experience, and continuous
improvement.
C) Entrepreneurs succeed only by taking extreme risks.
D) Entrepreneurs have guaranteed success if they work hard from day one
Q. 2 Answer any 5 out of the given 6 questions (1 x 5 = 5 marks)
1 ______ is defined as the ability to perceive the visual world and the relationship of one 1M
object with other.
 a. Mathematical Logical Reasoning
b. Musical Intelligence
c. Spatial Visual Intelligence
d. Linguistic Intelligence
2 What is the main purpose of training data in machine learning? 1M
A) To evaluate the model’s accuracy
B) To teach the model patterns
C) To visualize the data
D) To reduce dimensionality
3 The first layer of a Neural Network is known as the __________. 1M
a. Output Layer
b. Input Layer
c. Hidden Layer
d. Data Layer
4 In a Neural Network, Each node of these hidden layers has its own _______ which it 1M
executes on the data received from the input layer.
a. Formula
b. Logic
c. Machine Learning Algorithm
d. Code
5 Why is CSV used in Data Science? 1M
A) Stores data in tabular format
B) Stores images
C) Stores videos
D) Stores binary information
6 ___________ Information overload is a real problem when we need to access a specific, 1M
important piece of information from a huge knowledge base.
a. Automatic Summarization
b. Sentiment Analysis
c. Text Classification
d. All of the above
Q. 3 Answer any 5 out of the given 6 questions (1 x 5 = 5 marks)

1 An automated system in a car helps the driver avoid collisions by detecting obstacles 1M
and applying the brakes when necessary. Which category does this system belong to?
A) A simple sensor-based system
B) Artificial Intelligence, as it helps make decisions based on the environment
C) A manual system requiring human input
D) A standard GPS navigation system
2 What is a primary benefit of using unsupervised learning? 1M
A) Requires labeled data
B) Helps in finding hidden patterns in data
C) Always provides accurate predictions
D) Requires continuous data
3 What is the primary goal of data science? 1M
(a) To create visualizations of data
(b) To extract insights and knowledge from data
(c) To store large amounts of data
(d) To write code for data processing
4 Which of the following is a common task in Computer Vision? 1M
a) Audio processing
 b) Object detection
c) Data cleaning
d) Natural language translation
5 The goal of sentiment analysis is to identify sentiment among several posts or even in 1M
the same post where emotion is not always explicitly expressed.
a. Automatic Summarization
b. Sentiment Analysis
c. Text Classification
d. All of the above
6 ___________ is the process of understanding the reliability of any AI model, based on 1M
outputs by feeding test dataset into the model and comparing with actual answers.
a. Evaluation
b. Problem Scoping
c. Data acquisition
d. Data Exploration
Q. 4 Answer any 5 out of the given 6 questions (1 x 5 = 5 marks)
1 Statement 1: Data visualization helps in interpreting data insights effectively. 1M
Statement 2: Data visualization is only useful for large datasets.

(a) Both Statement 1 and Statement 2 are true.

(b) Statement 1 is true, and Statement 2 is false.
(c) Statement 1 is false, and Statement 2 is true.
(d) Both Statement 1 and Statement 2 are false.
2 Statement 1: Recall measures how many actual positive instances were correctly 1M
predicted by the AI model.
Statement 2: In cases where missing positive instances is costly, high recall is more
important than high precision.
a) Both Statement 1 and Statement 2 are true, and Statement 2 is the correct
explanation of Statement 1.
b) Both Statement 1 and Statement 2 are true, but Statement 2 is not the correct
explanation of Statement 1.
c) Statement 1 is true, but Statement 2 is false.
d) Statement 1 is false, but Statement 2 is true.
3 An e-commerce website uses Data Science to recommend products to its users based 1M
on their browsing and purchasing history. The system suggests new products users
might be interested in, which increases sales. Which Data Science technique is being
used in the recommender system?
a) Sentiment analysis
b) Recommender system algorithms
c) Image recognition
d) Text summarization
4 . What is the main goal of Computer Vision? 1M
a) To interpret textual data
b) To interpret and understand visual data from the world
c) To enhance network security
d) To generate synthetic images
5 Which of the following is an application of NLP? 1M
(a) Text classification
(b) Image segmentation
(c) Data Cleaning
 (d) Network security

6 A hospital implemented an AI system to assist doctors in diagnosing diseases. After 1M

development, the system went through an Evaluation phase, where its diagnostic
accuracy was compared to human doctors. The evaluation results showed that the
system was 85% accurate, but there were instances of false positives in certain
diagnoses. What aspect of the AI system is being tested in the Evaluation stage?
(a) The system's ability to replace doctors
(b) The system's accuracy in diagnosing diseases compared to human doctors
(c) The system’s ability to generate random diagnoses
(d) The system’s cost-effectiveness
Q. 5 Answer any 5 out of the given 6 questions (1 x 5 = 5 marks)
1 What is a primary benefit of using unsupervised learning? 1M
A) Requires labeled data
B) Helps in finding hidden patterns in data
C) Always provides accurate predictions
D) Simplifies the data
2 The result of comparison between the prediction and reality can be recorded in what 1M
we call the __________.
a. Overfitting
b. Problem Scoping
c. Confusion Matrix
d. Data acquisition
3 What is Computer Vision? 1M
A) A system that allows computers to talk
B) A field of AI that enables computers to interpret and understand visual information
C) A method to fix computer screens
D) A way to make computers hear sounds
4 ________ makes sure that lemma is a word with meaning and hence it takes a longer 1M
time to execute than stemming.
a. Stopwords
b. Stemming
c. Lemmatization
d. Token normalization
5 _______ bots work around a script which is programmed in them. 1M
a. Script-bot
b. Smart-bot
c. Learning based bot
d. Data bot
6 Which of the following is the correct formula to calculate accuracy in an AI model? 1M
(a) (TP + TN) / (TP + TN + FP + FN)
(b) TP / (TP + FP)
(c) TP / (TP + FN)
(d) (FP + FN) / (TP + TN + FP + FN)

SECTION B: SUBJECTIVE TYPE QUESTIONS

Answer any 3 out of the given 5 questions on Employability Skills (2 x 3 = 6 marks)
Answer each question in 20 – 30 words.
Q 6 Write is 7 C’s effective communication. 2M

Q .7 Write the four steps for effective Time management 2M

Q 8 Identify me 2M
a. I am a physical part of computer.
b. I am a collection of instruction doing specific task.
c. I am the software that starts working as soon as we switch on a computer.
d. I am an input device used to type text, numbers etc
Q .9 Write the positive impact of Entrepreneurship on society. 2M
Q 10 Write any four challenges to sustainable development. 2M
Answer any 4 out of the given 6 questions in 20 – 30 words each (2 x 4 = 8 marks)
Q 11 Mention the precautions to be taken while acquiring data for developing an AI Project. 2M

Q .12 What do you mean by Data Features? 2M

Q 13 How can E-commerce website are using data science as a salient feature. 2M

Q .14 What do you understand by RGB images. Explain it with example 2M

Q 15 What do you mean by corpus? 2M

Q 16 What is meant by Overfitting of Data? 2M

Answer any 3 out of the given 5 questions in 50– 80 words each (4 x 3 = 12 marks)

Q.17 How can AI be integrated with non-AI technologies? Explain with the help of two 4M
examples.
Q.18 What is the need of an AI Project Cycle? Explain. 4M

Q.19 What is an Artificial Neural Network? Explain the layers in an artificial neural network. 4M

Q.20 Create a document vector table for the given corpus: 4M

Document 1: We are going to Mumbai
Document 2: Mumbai is a famous place.
Document 3: We are going to a famous place.
Document 4: I am famous in Mumbai.
Q.21 Calculate Accuracy, Precision, Recall and F1 Score for the following Confusion Matrix on 4M
Heart Attack Risk. Also suggest which metric would not be a good evaluation parameter
hereand why?
 KENDRIYA VIDYALAYA SANGATHAN HYDERABAD REGION
ARTIFICIA LINTELLIGENCE(SUBJECTCODE -417)
Class X
Model Question Paper–17(Solutions)

Q.No Answer

Q. 1 Answerany4outofthegiven6questionsonEmployabilitySkills(1 x4=4marks)
i. Answer: (a) Excellent, your work has improved.
ii. Answer: (b) External
iii. Answer: (d) Self-management
iv. Answer: (a) Disk Operating System
v. Answer: (a) Both A and R are true, and R is the correct explanation of A
vi. Answer: (B) Entrepreneurs can learn skills through education, experience, and continuous improvement

Q. 2 Answer any5out ofthegiven6questions(1x5=5marks)

i. Answer: (c) Spatial Visual Intelligence

ii. Answer: (B) To teach the model patterns
iii. Answer: (b) Input Layer
iv. Answer: (c) Machine Learning Algorithm
v. Answer: (A) Stores data in tabular format
vi. Answer: (a) Automatic Summarization

Q. 3 Answer any5out ofthegiven6questions(1x5=5marks)

i. Answer: (B) Artificial Intelligence, as it helps make decisions based on the environment
ii. Answer: (B) Helps in finding hidden patterns in data
iii. Answer: (b) To extract insights and knowledge from data
iv. Answer: (b) Object detection
v. Answer: (b) Sentiment Analysis
vi. Answer: (a) Evaluation

Q. 4 Answer any5out ofthegiven6questions(1x5=5marks)

i. Answer: (b) Statement 1 is true, and Statement 2 is false
ii. Answer: (a) Both Statement 1 and Statement 2 are true, and Statement 2 is the correct explanation of
Statement 1
iii. Answer: (b) Recommender system algorithms
iv. Answer: (b) To interpret and understand visual data from the world
v. Answer: (a) Text classification
vi. Answer: (b) The system's accuracy in diagnosing diseases compared to human doctors

Q. 5 Answer any5out ofthegiven6questions(1x5=5marks)

i. Answer: (B) Helps in finding hidden patterns in data
ii. Answer: (c) Confusion Matrix
iii. Answer: (B) A field of AI that enables computers to interpret and understand visual information
iv. Answer: (c) Lemmatization
v. Answer: (a) Script-bot
vi. Answer: (a) (TP + TN) / (TP + TN + FP + FN)

SECTIONB:SUBJECTIVETYPEQUESTIONS
6. The 7 Cs of effective communication are: clear, concise, concrete, correct, coherent, complete,
courteous.
7. Four steps for effective time management are: Prioritize tasks, Set clear goals, Avoid distractions, and
Review progress.
8.  I am hardware.
 I am software.
 I am the operating system.
 I am a keyboard.

9. Positive impacts of entrepreneurship on society include job creation, economic growth, innovation, and
fostering competition.
10. four challenges to sustainable development:-
o Resource depletion due to overconsumption.
o Climate change from increasing greenhouse gas emissions.
o Social inequality hindering equitable development.
o Rapid urbanization straining infrastructure and services.

11. Precautions include data privacy, informed consent, data security, and avoiding bias during data
acquisition.

12. Data features are attributes or properties that describe data. These features are used to build machine
learning models.

13. E-commerce websites use data science for personalized recommendations, customer behavior analysis,
and improving customer satisfaction.
14. RGB images use the additive color model, where colors are created by combining red, green, and blue
light in varying intensities. Each color channel can have values ranging from 0 to 255. Here's a brief
explanation of the values:
For example:
Black: (0, 0, 0) – No light, resulting in black.
White: (255, 255, 255) – Full intensity of all colors, resulting in white.
15. A corpus is a collection of text or documents used for analysis in natural language processing tasks.

16. Overfitting occurs when a machine learning model is too complex and performs well on training data
but poorly on unseen data.
17. Today’s world is changing with the adoption of IOT (Internet of Things). IOT is helping in prominently
capturing a tremendous amount of data from multiple sources. The convergence of AI (Artificial
Intelligence) and IOT can redefine the way industries, business, and economies function. AI enabled IoT
creates intelligent machines that simulate smart behavior and supports decision making with little or no
human interference. While IOT provides data, artificial intelligence acquires the power to unlock
responses, offering both creativity and context to drive smart actions. Here are some examples:
Example : Self-driving Cars: Tesla’s self-driving cars are the best example of IoT and AI working
together. With the power of AI, self-driving cars predict the behavior of pedestrians and cards in
various circumstances. For example, they can determine road conditions, optimal speed, weather and
getting smarter with each trip.
18. Project cycle is the process of planning, organizing, coordinating, and finally developing a project
effectively throughout its phases, from planning through execution then completion and review to
achieve pre-defined objectives.
Our mind makes up plans for every task which we have to accomplish which is why things become
clearer in our mind. Similarly, if we have to develop an AI project, the AI Project Cycle provides us
with an appropriate framework which can lead us towards the goal.
The major role of AI Project Cycle is to distribute the development of AI project in various stages so
that the development becomes easier, clearly understandable and the steps / stages should become
more specific to efficiently get the best possible output. It mainly has 5 ordered stages which
 distribute the entire development in specific and clear steps: These are Problem Scoping, Data
Acquisition, Data Exploration, Modeling and Evaluation.

19. An Artificial Neural Network (ANN) is a computational model inspired by the biological neural networks
in the human brain. It consists of interconnected nodes (neurons) that process information through
weighted connections. ANNs typically have three types of layers:
 Input Layer: Receives the initial data inputs and passes them to the next layer.
 Hidden Layer(s): Intermediate layers that perform computations and feature extraction. The
number of hidden layers can vary, influencing the network's complexity.
 Output Layer: Produces the final result or prediction based on the processed information from
the hidden layers, determining the ANN's output.

20.

21.
 Accuracy: Accuracy = (TP + TN) / (TP + TN + FP + FN)
Accuracy = (50+20) / (50+20+20+10) = (70/100) = 0.7
 Precision: Precision = TP / (TP + FP)
= (50 / (50 + 20)) = (50/70) = 0.714
 Recall (Sensitivity): Recall = TP / (TP + FN)
= 50 / (50 + 60) = 50 / 110 = 0.5
 F1 Score: F1 Score = 2 * (Precision * Recall) / (Precision + Recall)
= 2 * (0.714 *0.5) / (0.714 + 0.5)
= 2 * (0.357 / 1.214)
= 2* (0.29406)
= 0.58
 KENDRIYA VIDYALAYA SANGATHAN HYDERABAD REGION
MODEL QUESTION PAPER-18
2024-25
CLASS:X TIME:02HOURS
SUBJECT: ARTIFICIAL INTELLEGENCE MAX.MARKS:50

SECTION A: OBJECTIVE TYPE QUESTIONS

Q. 1 Marks
Answer any 4 out of the given 6 questions on Employability Skills (1 x 4 = 4 marks)

1 Shreya works at a multinational company and often communicates with international 1M

clients through emails. She ensures her emails are clear, concise, and professional.
However, sometimes her emails are misinterpreted due to cultural differences, leading
to confusion among clients. What type of communication is Shreya using to interact
with international clients?
(a) Non-verbal communication
(b) Verbal communication
(c) Written communication
(d) Visual communication
2 Rohan is a high school student who is involved in various extracurricular activities like 1M
sports and music. However, he struggles to manage his time efficiently. Due to his busy
schedule, he often misses deadlines and feels stressed. His teacher advised him to
create a daily plan and prioritize tasks based on importance. What self-management
skill is Rohan struggling with?
(a) Self-awareness
(b) Time management
(c) Confidence building
(d) Goal setting
3 Assertion (A): Self-motivation plays a key role in achieving long-term success. 1M
Reason (R): Self-motivation drives individuals to persist through challenges and
maintain focus on their goals.
(a) Both A and R are true, and R is the correct explanation of A.
(b) Both A and R are true, but R is not the correct explanation of A.
(c) A is true, but R is false.
(a) (d) A is false, but R is true.
4 Which keys do you press to copy a file or a folder? 1M
(a) Ctrl + Z
(b) Ctrl + Y
(c) Ctrl + X
(d) Ctrl + C
5 Solution to these global problems like scarcity of clean water to drink, scarcity of pure 1M
air to breathe, scarcity of unadulterated food, rising issue of global warming is _____.
(a) Stop using these resources
(b) To better use of resource
 (c) Sustainability
(d) To make people aware
6 Ankit has a diamond factory. He pays his employees on the 1st of every month . What 1M
quality it shows:-
(a) Hard working
(b) Takes risk
(c) Manages the business
(d) Creates a new product
Q. 2 Answer any 5 out of the given 6 questions (1 x 5 = 5 marks)

1 Assertion (A): Artificial intelligence (AI) is the software that drives the fourth industrial 1M
revolution.
Reason (R): Its impact can be seen in homes, business and political processes.
(a) Both A and R are true and R is the correct explanation of A.
(b) Both A and R are true but R is not the correct explanation of A.
(c) A is true but R is false.
(d) A is false but R is true.
2 A software tool helps users calculate their taxes by following predefined rules. It 1M
doesn’t adapt or learn over time. Is this an example of AI?
(a) Yes, it makes decisions
(b) No, it doesn’t learn from new data
(c) Yes, because it automates a process
(d) Yes, because it performs calculations
3 The job of an input layer in Neural network is _______ 1M
(a) to acquire and feed data.
(b) to process data.
(c) to present data
(d) None of the above
4 Which of the following is a correct feature of a Neural Network? 1M
(a) Neural Network Systems are modeled on the human brain and nervous
system.
(b) They are able to automatically extract features without input from the
programmer.
(c) It is useful to solve problems for which the data set is very large.
(d) All of the above
5 _______is a simple file format that stores data separated by commas. 1M
(a) jpg
(b) doc
(c) csv
(d) png
6 _________, we put the document frequency in the denominator while the total number 1M
of documents in the numerator.
a. Inverse Frequency
b. Inverse Document
c. Inverse Document Frequency
d. Term Frequency
Q. 3 Answer any 5 out of the given 6 questions (1 x 5 = 5 marks)

1 Simran believes that all automated machines are AI-driven. Which of the 1M
following is NOT an example of artificial intelligence?
a) A robot that learns to navigate obstacles on its own
 b) A simple washing machine that follows a set program
c) A chatbot that adapts its responses based on user queries
d) A smart vacuum cleaner that maps and remembers room layouts
2 What is the main goal of reduction techniques? 1M
a) Increase model complexity
b) Reduce the number of features while retaining information
c) Classify data points
d) Collect more data
3 Which of the following is a source of data? 1M
a) Web scrapping, API, Research
b) Surveys, observations, Internet
c) Sensors, Cameras, Identity charts
a) d) All of these
4 Which of the following is a popular open-source library for Computer Vision? 1M
a) TensorFlow
b) OpenCV
c) PyTorch
d) Pandas
5 Which of the following words in a corpus has the highest value? 1M
a) Rare words
b) Punctuation
c) Stemming
a) d) Stop words
6 An AI model is used by a telecom company to predict which customers are likely to 1M
leave their service. The company wants to minimize the number of loyal customers
incorrectly flagged as potential churners. What evaluation metric should the company
prioritize to reduce the number of false positives when predicting customer churn?
a) Precision
b) Recall
c) Accuracy
d) ROC Curve
Q. 4 Answer any 5 out of the given 6 questions (1 x 5 = 5 marks)

1 A bank is using Data Science to identify suspicious transactions and prevent fraud. By 1M
analyzing transaction data in real time, they flag unusual behavior that could indicate
fraudulent activity. Which Data Science application is relevant for this banking case?
e) Predictive maintenance
f) Fraud detection
g) Speech recognition
h) Recommender system
2 Statement 1: Each element in Prediction is given a label that consists of two words: 1M
Positive and Negative.
Statement 2: The Recall is the probability that a randomly retrieved relevant document
is retrieved.
a) Statement 1 is correct but statement 2 is incorrect.
b) Statement 1 is incorrect but statement 2 is correct.
c) Both the statements are correct.
d) Both the statements are incorrect
3 Assertion: Data science combines domain expertise, programming skills, and knowledge 1M
of mathematics and statistics.
Reason: Data science is only concerned with data and does not require domain
 knowledge.
a) Both Assertion and Reason are true, and the Reason is the correct explanation
for the Assertion.
b) (b) Both Assertion and Reason are true, but the Reason is not the correct
explanation for the Assertion.
c) Assertion is true, but the Reason is false.
d) Assertion is false, but the Reason is true.
4 Which format represents a colored image in Computer Vision? 1M
a) Grey scale image
b) Binary image
c) RGB image
d) Alpha image
5 Select the correct features of Smart Bot: 1M
a) Smart bots work on bigger databases and other resources directly
b) Smart - bots are flexible and powerful
c) Coding is required to take this up on board
d) All of these
6 A hospital uses an AI system to classify medical images into categories such as 1M
"cancerous" or "non-cancerous." The hospital wants to ensure the AI is highly sensitive
in detecting cancerous cells. Which evaluation metric is most important for assessing
the AI's ability to detect all true cancerous cases?
a) Precision
b) Recall
c) Accuracy
d) F1-Score
Q. 5 Answer any 5 out of the given 6 questions (1 x 5 = 5 marks)

1 Consider the following data: 1M

Data, Image and Videos, Voice Speech.
To which field are these domains related?
a) Data Science, Computer Vison, NLP
b) NLP, Data Science, Computer Vison
c) Computer Vison, Data Science, NLP
d) NLP, Computer Vison, Data Science
2 Raunak was learning the conditions that make up the confusion matrix. He came 1M
across a scenario in which the machine that was supposed to predict an animal was
always predicting not an animal. What is this condition called?
(a) False Positive
(b) True Positive
(c) False Negative
(a) (d) True Negative
3 What is a key difference between an RGB image and a grey scale image? 1M
a) RGB uses three color channels, while grey scale uses one
b) Grey scale uses color, while RGB is black and white
c) Grey scale has better quality than RGB
d) None of the above
4 Which of the following tasks is commonly performed using NLP? 1M
(a) Image recognition
(b) Speech recognition
(c) Data visualization
(d) (d) Game development
 5 Vikram is building a robot that can navigate a room and interact with people using voice 1M
commands. Which domains of AI does this robot use?
(a) Natural Language Processing (NLP) and Computer Vision
(b) Only Natural Language Processing
(c) Only Computer Vision
(d) No AI is involved
6 ___________ is the process of understanding the reliability of any AI model, based on 1M
outputs by feeding test dataset into the model and comparing with actual answers.
(a) Evaluation
(b) Problem Scoping
(c) Data acquisition
(d) Data Exploration

SECTION B: SUBJECTIVE TYPE QUESTIONS

Answer any 3 out of the given 5 questions on Employability Skills (2 x 3 = 6 marks)
Answer each question in 20 – 30 words.
Q 6 What is the role of feedback in communication 2M

Q .7 Provide two examples each of positive stress and negative stress. 2M

Q 8 How does a command-line interface operating system differ from a graphical user 2M
interface operating system?
Q .9 Identify four myths associated with entrepreneurship 2M

Q 10 Write a brief overview of sustainable development. 2M

Answer any 4 out of the given 6 questions in 20 – 30 words each (2 x 4 = 8 marks)

Q 11 A retail business wants to gather data on customer preferences to improve its 2M

marketing strategies. They are considering various methods for data acquisition. What
are some effective methods the business can use to collect relevant data on customer
preferences?
Q .12 Dataset used in a supervised learning model is labeled - What does it mean? 2M

Q 13 Ajay wants to access data from various sources. Suggest him any two points that he 2M
needs to keep in mind while accessing data from any data source.
Q .14 Write four computer vison task 2M

Q 15 Differentiate between script bot and smart bot with example. 2M

Q 16 Differentiate between F1 Score and accuracy? 2M

Answer any 3 out of the given 5 questions in 50– 80 words each (4 x 3 = 12 marks)

Q.17 Explain any four misconceptions about AI? 4M

Q.18 Make a 4W Project Canvas. 4M

Risks will become more concentrated in a single network as more and more innovative
technologies are used. In such cases, cyber security becomes incredibly complex and is
no longer under the authority of firewalls. It won’t be able to recognise odd behaviour
 patterns, including data migration.
Consider how AI systems can sift through voluminous data to find user behaviour that is
vulnerable. To explicitly define the scope, the method of data collection, the model,
and the evaluation criteria, use an AI project cycle
Q.19 What is supervised learning? How Classification is different from regression. 4M

Q.20 What are the steps of text Normalization? Explain them in brief. 4M

Q.21 Calculate Accuracy, Precision, Recall and F1 Score for the following Confusion Matrix on 4M
Heart Attack Risk. Also suggest which metric would not be a good evaluation parameter
here and why?

KENDRIYA VIDYALAYA SANGATHAN HYDERABAD REGION

ARTIFICIAL INTELLIGENCE (SUBJECTCODE -417)
Class X
Model QuestionPaper–18(Solutions)
Q.No Answer

Q. 1 Answerany4outofthegiven6questionsonEmployabilitySkills(1 x4=4marks)
i. Answer: (c) Written communication
ii. Answer: (b) Time management
iii. Answer: (a) Both A and R are true, and R is the correct explanation of A.
iv. Answer: (d) Ctrl + C
v. Answer: (c) Sustainability
vi. Answer: (c) Manages the business

Q. 2 Answer any5out ofthegiven6questions(1x5=5marks)

i. Answer: (a) Both A and R are true, and R is the correct explanation of A
ii. Answer: (b) No, it doesn’t learn from new data
iii. Answer: (a) To acquire and feed data
iv. Answer: (d) All of the above
v. Answer: (c) CSV
vi. Answer: (c) Inverse Document Frequency

Q. 3 Answer any5out ofthegiven6questions(1x5=5marks)

i. Answer: (b) A simple washing machine that follows a set program
 ii. Answer: (b) Reduce the number of features while retaining information
iii. Answer: (d) All of these
iv. Answer: (b) OpenCV
v. Answer: (a) Rare words
vi. Answer: (a) Precision

Q. 4 Answer any5out ofthegiven6questions(1x5=5marks)

i. Answer: (b) Fraud detection
ii. Answer: (b) Statement 1 is incorrect but statement 2 is correct
iii. Answer: (c) Assertion is true, but the Reason is false
iv. Answer: (c) RGB image
v. Answer: (d) All of these
vi. Answer: (b) Recall

Q. 5 Answer any5out ofthegiven6questions(1x5=5marks)

i. Answer: (a) Data Science, Computer Vision, NLP
ii. Answer: (d) True Negative
iii. Answer: (a) RGB uses three color channels, while grayscale uses one
iv. Answer: (b) Speech recognition
v. Answer: (a) Natural Language Processing (NLP) and Computer Vision
vi. Answer: (a) Evaluation

SECTIONB:SUBJECTIVETYPEQUESTIONS
6. Feedback ensures the message is understood correctly and provides a chance for clarification.
It helps improve communication effectiveness.

7. Examples of positive and negative stress:

 Positive stress: Getting a promotion, Preparing for an event
 Negative stress: Overload of tasks, Job insecurity
8. Difference between CLI and GUI:
 CLI uses text-based commands to interact with the operating system.
 GUI uses graphical elements like windows and icons for interaction.

9. Four myths about entrepreneurship:

1. Entrepreneurs are born, not made
2. Entrepreneurs must take extreme risks
3. You need a lot of money to start
4. Entrepreneurs work less as the business grows

10. Sustainable development focuses on meeting present needs without compromising future
generations' ability to meet their own needs, ensuring a balance between economic growth,
environmental protection, and social well-being
11. Retail businesses can collect data using customer surveys, social media analytics, web traffic
analysis, and loyalty programs to gather preferences.

12. A labeled dataset in supervised learning means each input has an associated output or label,
which the model learns to predict during training.
13. Ajay accessing data from various sources - key considerations:
 Ensure data is relevant and reliable.
  Ensure proper permissions and licenses are obtained for using the data.

14. Four computer vision tasks:

1. Image classification
2. Localization
3. Object detection
4. Image segmentation

15.  A script bot follows predefined instructions (e.g., a customer service chatbot with
fixed responses).
 A smart bot can learn and adapt from interactions (e.g., an AI-powered chatbot that
personalizes responses based on user input).
16. Accuracy: Measures the proportion of correct predictions out of total predictions.
F1 Score: The harmonic mean of precision and recall, used when the class distribution is
imbalanced.
17.
a) AI will replace humans completely: AI is designed to augment human capabilities, not
replace them entirely. It automates repetitive tasks but requires human oversight for
decision-making.
b) AI can think like humans: AI mimics certain aspects of human intelligence, such as
learning and problem-solving, but lacks consciousness, emotions, and true reasoning.
c) AI is always accurate: AI systems depend on the quality of data they are trained on. If
the data is biased or incomplete, AI can produce inaccurate results.
d) AI can learn on its own: AI requires human intervention for programming, updating,
and improving models. It doesn't evolve without supervision.

18.

1. Who: The AI development team, cybersecurity experts, and network

administrators.
2. What: Developing an AI system to detect unusual user behavior for cybersecurity
purposes.
3. When: During real-time network monitoring and data analysis.
4. Where: Across interconnected networks with high cybersecurity risks.

19. Supervised learning is a type of machine learning where a model is trained on labeled data,
meaning each input comes with a corresponding output. The model learns from this data
 to make predictions or decisions when given new, unseen data. It is widely used in tasks
like image recognition, fraud detection, and language processing.
Classification and regression are two types of supervised learning:
 Classification predicts discrete labels (e.g., classifying an email as "spam" or "not
spam").
 Regression predicts continuous values (e.g., estimating house prices based on features
like size and location).Marking Scheme: 4 marks (2 marks for supervised learning and 2
marks for differentiation between classification and regression).

20.  Text Normalization: in Text Normalization, we undergo several steps to normalize

the text to a lower level.
 Sentence Segmentation - Under sentence segmentation, the whole corpus is
divided into sentences. Each sentence is taken as a different data so now the whole
corpus gets reduced to sentences.
 Tokenization- After segmenting the sentences, each sentence is then further
divided into tokens. Tokens is a term used for any word or number or special
character occurring in a sentence. Under tokenization, every word, number and
special character is considered separately and each of them is now a separate
token.
 Removing Stop words, Special Characters and Numbers - In this step, the tokens
which are not necessary are removed from the token list.
 Converting text to a common case -After the stop words removal, we convert the
whole text into a similar case, preferably lower case. This ensures that the case-
sensitivity of the machine does not consider same words as different just because
of different cases.
 Stemming In this step, the remaining words are reduced to their root words. In
other words, stemming is the process in which the affixes of words are removed
and the words are converted to their base form.
 Lemmatization -in lemmatization, the word we get after affix removal (also known
as lemma) is a meaningful one.
With this we have normalized our text to tokens which are the simplest form of words
present in the corpus.
Now it is time to convert the tokens into numbers. For this, we would use the Bag of
Words algorithm.

21.
 Accuracy: Accuracy = (TP + TN) / (TP + TN + FP + FN)
Accuracy = (50+20) / (50+20+20+10) = (70/100) = 0.7
 Precision: Precision = TP / (TP + FP)
 Precision: Precision = TP / (TP + FP)
Precision= (50 / (50 + 20)) = (50/70) = 0.714
 Recall : Recall = TP / (TP + FN)
Recall : 50 / (50 + 10) = 50 / 60 = 0.833
 F1 Score: F1 Score = 2 * (Precision * Recall) / (Precision + Recall)
F1 Score:- = 2 * (0.714 *0.833) / (0.714 + 0.833)
= 2 * (0.595 / 1.547)
= 2* (0.38462)
= 0.769
 KENDRIYA VIDYALAYA SANGATHAN HYDERABAD REGION
MODEL QUESTION PAPER-19
2024-25
CLASS:X TIME:02HOURS
SUBJECT: ARTIFICIAL INTELLEGENCE MAX.MARKS:50
SECTION A: OBJECTIVE TYPE QUESTIONS

Q. 1 Marks
Answer any 4 out of the given 6 questions on Employability Skills (1 x 4 = 4 marks)

1 Which of the following is not a form of written communication? 1M

a) Circulars b) Reports c) Discussion d) SMS
2 Pranjali gets up at 5 am and goes to her badminton classes. Then she comes home and 1M
finishes her homework before going to school. She does this all by herself. No one tells
her to do it. This is an example of
(a) Self-motivation
(b) External motivation
(c) Both self and external motivation
(d) Not any specific type of motivation
3 1.Which of the following activities helps in reducing stress? 1M
a) Yoga
b) Walking
c) Meditation
d) All of these
4 Manisha pressed a key on keyboard that moved the cursor to the beginning of a new 1M
line but she did not know which key has been pressesby her. Identify the key pressed by
her:
a. Enter
b. Shift
c. Ctrl
d. Windows
5 Green SkillsWhich of the following is/are the result of exploiting our Nature? 1M
a. Scarcity of clean water to drink.
b. Scarcity of pure air to breathe
c. Depletion of ozone layer
d. All of the above
6 Assertion(A): A doctor works for a renowned hospital. 1M
Reason(R): The statement given above is an example of wage employment.
(a) Both A and R are correct and R is the correct explanation of A
(b) Both A and R are correct but R is NOT the correct explanation of A
(c) A is correct but R is not correct
(d) A is not correct but R is correct
Q. 2 Answer any 5 out of the given 6 questions (1 x 5 = 5 marks)

1 1. Chatbots and smart bots are related to ______________ domain of AI. 1M

a. Data Science
 b. Machine Learning
c. Computer Vision
d. Natural Language Processing
2 Assertion (A): AI project cycle undergoes several phases and begins with aim and scope 1M
of the project.
Reason(R): In the problem scoping stage of AI project cycle, broadly the aim and scope
of the project are determined.
(a) Both A and R are correct and R is the correct explanation of A
(b) Both A and R are correct but R is NOT the correct explanation of A
(c) A is correct but R is not correct
(d) A is not correct but R is correct
3 Statement A: Neural networks are made up of layers of neurons. 1M
Statement B: Human brain consists of millions of neurons.
i)Only Statement A is correct (ii) Only Statement B is correct
(iii) Both the statements are correct (iv) None of the statements is correct
4 Neural Networks 1M

5 ________is a simple file format that stores data separated by commas. 1M

(a) jpg
(b) doc
(c) csv
(d) png
6 The higher the value, the more important the word in the document – this is 1M
True of which model?
(a) Bag of Words
(b)TF-IDF
(c) YOLO
(d) SSD
Q. 3 Answer any 5 out of the given 6 questions (1 x 5 = 5 marks)

1 In Weather forecasting system, to predict the temperature, rainfall and etc. The type of 1M
technology used is _________________.
a. Computer Vision
b. Interpersonal Intelligence
c. Natural Language Processing
d. Artificial Intelligence
2 The method of collecting correct and dependable data to work with is known as _____. 1M
a. Problem Scoping
b. Data Acquisition
c. Data Exploration
d. Modeling
3 What is the term for the process of reducing data dimensions? 1M

4 What does a pixel represent in an image? 1M

A) A segment of a video
B) The smallest unit of an image
C) The color depth of an image
D) The brightness of an image
5 TF-IDF in NLP is defined as: 1M
a. Term Frequency and Definite Frequency
b. Term Frequency and Indefinite Frequency
 c. Term Frequency and Inverse Document Frequency
d. Term Frequency and Integrated Document Frequency
6 Which of the following talks about how true the predictions are by any model? 1M
a. Accuracy
b. Reliability
c. Recall
d. F1 Score
Q. 4 Answer any 5 out of the given 6 questions (1 x 5 = 5 marks)

1 How did data science help banking companies in managing risk? 1M

a) By collecting customer profiles and past expenditures
b) By creating new banking products
c) By providing loans to customers with high purchasing power
d) By reducing bad debts and losses
2 Statement 1: F1 score is evaluated based on precision or recall. 1M
Statement 2: When the F1 score is 0, the model accuracy is 100%
a. Both statement1 and statement 2 are correct.
b. Both statement1 and statement 2 are incorrect.
c. Statement 1 is correct but statement 2 is incorrect.
d. Statement 1 is incorrect but statement 2 is correct.
3 Akash wants to understand how does AI contribute to the field of Data Science? Help 1M
him to choose the correct option.
a) It makes data collection easier and faster.
b) It provides predictions and suggestions based on collected data.
c) It eliminates the need for human involvement in analyzing data.
d) It enhances technological knowledge for data collection.
4 Which of the following is a common use of Computer Vision in medical imaging? 1M
A) Audio transcription
B) Image segmentation
C) Video streaming
D) Data encryption
5 What do we call the process of dividing a string into component words? 1M
a. Regression
b. Word Tokenization
c. Classification
d. Clustering
6 Aruna was confused with the terms used in the evaluation stage. Suggest her the term 1M
used for the percentage of correct predictions out of all the observations.
(a) Accuracy
(b) Precision
(c) Recall
(d) F1 Score
Q. 5 Answer any 5 out of the given 6 questions (1 x 5 = 5 marks)

1 Aaron is facing issue in his internet connectivity at home. He called customer care 1M
service, A virtual assistant took his complaint and replied with an acknowledgement
number. What is the AI technology used by Internet service provider?
a. Data Science
b. Machine Learning
c. Computer Vision
d. Natural Language Processing
 2 The result of comparison between the prediction and reality is recorded in 1M
a. F1 Score
b. Confusion matrix
c. Evaluation Model
d. All of these
3 Which format is typically used to store a color image in digital form? 1M
A) Grayscale
B) Binary
C) RGB
D) Indexed
4 Google Assistant, Alexa, Cortana, Siri are examples of 1M
a) Script Bot
b) Smart Bot
c) Sling Bot
d) None of these
5 The process of extracting the root form of the word is known as _________ 1M
a) Tokenisation
b) Stemming
c) Lemmatisation
d) Segmentation
6 When the prediction is False and reality is True, that condition is called……….. 1M
a. TN
b. TF
c. FP
d. FN

SECTION B: SUBJECTIVE TYPE QUESTIONS

Answer any 3 out of the given 5 questions on Employability Skills (2 x 3 = 6 marks)
Answer each question in 20 – 30 words.
Q 6 List different methods of communication. 2M
Q .7 What is stress? Enlist few simple stress management techniques. 2M
Q 8 What do you mean by ICT term? 2M
Q .9 Who is an entrepreneur? 2M
Q 10 What is the meaning of sustainable development? 2M
Answer any 4 out of the given 6 questions in 20 – 30 words each (2 x 4 = 8 marks)

Q 11 How do you understand whether a machine/application is AI based or not? Explain with 2M

an example.
Q .12 What precautions to be taken while acquiring data for developing an AI Project? 2M

Q 13 Explain the concept of overfitting in machine learning and how it can be prevented. 2M

Q .14 Consider a smart surveillance system that employs Computer Vision for security 2M
purposes. Explain how object detection and facial recognition are used in this system to
enhance security. What ethical considerations should be considered when
implementing such a system?
Q 15 Identify the stop words in the given sentence: 2M
Pollution is the introduction of contaminants into the natural environment that cause
 adverse change. The three types of pollution are air pollution, water pollution and land
pollution. Mail details pollu@gmail.com
Q 16 What is the need of AI model evaluation? 2M

Answer any 3 out of the given 5 questions in 50– 80 words each (4 x 3 = 12 marks)

Q.17 After class 12 Rahul wanted to join for AI course. His parents didn’t know much about 4M
its domains Explain them the domains of AI.
Q.18 The world is competitive nowadays. People face competition in even the tiniest tasks 4M
and are expected to give their best at every point in time. When people are unable to
meet these expectations, they get stressed and could even go into depression. We get
to hear a lot of cases where people are depressed due to reasons like peer pressure,
studies, family issues, relationships, etc. and they eventually get into something that is
bad for them as well as for others. So, to overcome this, Cognitive Behavioural Therapy
(CBT) is considered to be one of the best methods to address stress as it is easy to
implement on people and also gives good results. This therapy includes understanding
the behaviour and mindset of a person in their normal life. With the help of CBT,
therapists help people overcome their stress and live a happy life.
For the situation given above,
i. Write the problem statement template
ii.List any two sources from which data can be collected

Q.19 Identify and explain the types of the learning-based approaches in the figures given 4M
below.

Figure 1

Figure 2
Q.20 Normalise the text on the segmented sentences given below: 4M
Document 1: Diya and Riya are best friends.
Document 2: Diya likes to play guitar but Riya prefers to play violin
Q.21 Consider the scenario where the AI model is created to predict if there will be rain or 4M
not. The confusion matrix for the same is given below. Calculate precision, accuracy and
recall.
 KENDRIYA VIDYALAYA SANGATHAN HYDERABAD REGION
ARTIFICIAL INTELLIGENCE (SUBJECTCODE -417)
Class X
Model Question Paper–19(Solutions)
SECTION A: OBJECTIVE TYPE QUESTIONS
Q. 1
Answer any 4 out of the given 6 questions on Employability Skills (1 x 4 = 4 marks)

1 c) Discussion

2 (a) Self-motivation

3 d) All of these

4 a. Enter

5 d. All of the above

6 (a) Both A and R are correct and R is the correct explanation of A

Q. 2 Answer any 5 out of the given 6 questions (1 x 5 = 5 marks)

1 d. Natural Language Processing

2 (a) Both A and R are correct and R is the correct explanation of A

3 (iii) Both the statements are correct

4 Neural Networks

5 (c) csv

6 (a) Bag of Words

Q. 3 Answer any 5 out of the given 6 questions (1 x 5 = 5 marks)

1 (d) Artificial Intelligence

2 b. Data Acquisition

3 Dimensionality reduction.

4 B) The smallest unit of an image

5 c. Term Frequency and Inverse Document Frequency

6 Accuracy

Q. 4 Answer any 5 out of the given 6 questions (1 x 5 = 5 marks)

 1 d) By reducing bad debts and losses

2 c) Statement 1 is correct but statement 2 is incorrect.

3 b)It provides predictions and suggestions based on collected data.

4 B) Image segmentation

5 b. Word Tokenization

6 (a) Accuracy

Q. 5 Answer any 5 out of the given 6 questions (1 x 5 = 5 marks)

1 (d) Natural Language Processing

2 b. Confusion matrix

3 C) RGB

4 b) Smart Bot

5 c) Lemmatisation

6 FN

SECTION B: SUBJECTIVE TYPE QUESTIONS

Answer any 3 out of the given 5 questions on Employability Skills (2 x 3 = 6
marks)
Answer each question in 20 – 30 words.

Q 6 Different methods of communication are: face to face talk, e-mail, letters, Notice board.
Posters, meetings, phone call, video call, virtual meeting,writing blog e.t.c
Q .7 Stress can be defined as our emotional, mental, physical and social reaction to any
perceived demands or threats
Here are a few simple stress management techniques. (Any two)
a) Time management
b) Positivity
c)Physical Exercise and Fresh Air
d)Healthy Diet
e) Holidays with Family and Friends
f) Good Sleep
g) Organizing your work and not delaying
Q 8 ICT stands for Information and communication technology. It refers to all the tools
related to storing, recording and sending digital information.
Q .9 An entrepreneur is a person who is self-employed, is willing to take a calculated risk and
brings in a new idea to start a business.
Q 10 Sustainable development is the development that satisfies the needs of the present
without compromising the capacity of future generations, guaranteeing the balance
between economic growth, care for the environment and social well-being.
Q 11 Introduction to AI Cycle and Data requisition

Q .12 Data should be collected from an authentic source, and should be accurate. The
redundant and irrelevant data should not be a part of prediction.
Q 13 Overfitting occurs when a model is too complex and performs well on training data but
poorly on new data. Techniques to prevent overfitting include:
- Regularization (L1, L2)
- Early stopping
- Data augmentation
- Cross-validation
- Ensemble methods
Q .14 Object detection is used to identify and monitor objects within the surveillance area,
alerting security personnel to any suspicious activity. Facial recognition identifies
individuals by comparing captured images with a database of known faces, enhancing
security by recognizing potential threats. Ethical considerations include privacy
concerns, potential biases in recognition algorithms, and the need for transparency and
accountability in how the data is used and stored.
Q 15 is, the, of, that, into, are, and

Q 16 The primary purpose of evaluation in the AI project cycle is to check the reliability of the
AI model. It helps determine if the model is performing as expected and if it can make
accurate predictions or classifications based on the test dataset.
Q.17 Domains of AI:
Machine Learning: It involves algorithms that enable computers to learn from data and
make predictions or decisions.
Natural Language Processing (NLP): It focuses on enabling computers to understand,
interpret, and generate human language.
Computer Vision: This domain enables computers to interpret and analyze visual
information from the real world, such as images or videos.
Robotics: It involves the design and creation of robots capable of performing tasks
autonomously or with human assistance.
Q.18 i. The problem statement template for the given scenario would be

ii. Data can be collected from one of the following sources:

a. surveys b. observing therapist's sessionsc. databases available on the internet
d. interviews
Q.19 The learning-based approaches shown in the given figures are Supervised learning and
Unsupervised learning.
Figure 1: In a supervised learning model, the dataset which is fed to the machine is
labelled. In other words, we can say that the dataset is known to the person who is
training the machine only then he/she is able to label the data. A label is some
information which can be used as a tag for data.
Here, labelled images of dog and cat are fed into the model and trained. The model
 correctly identifies the given input as dog.

Figure 2: An unsupervised learning model works on unlabelled dataset. This means that
the data which is fed to the machine is random and there is a possibility that the person
who is training the model does not have any information regarding it. The unsupervised
learning models are used to identify relationships, patterns and trends out of the data
which is fed into it. It helps the user in understanding what the data is about and what
are the major features identified by the machine in it.
Here, images of a set of animals are fed into the AI model and the model clusters them
based on similar features
Q.20 Hint -Stopwords in the given sentence which should not be removed are: @, . (fullstop)
,_(underscore) , 123(numbers) These tokens are generally considered as stopwords, but
in the above sentence, these tokens are part of email id. removing these tokens may
lead to invalid website address and email ID. So these words should not be removed
from the above
Q.21 Accuracy =(70+50)/200=0.60
Recall=70/120=0.58
Precision=70/100=0.7
 KENDRIYA VIDYALAYA SANGATHAN HYDERABAD REGION
MODEL QUESTION PAPER-20
2024-25
CLASS:X TIME:02HOURS
SUBJECT: ARTIFICIAL INTELLEGENCE MAX.MARKS:50
SECTION A: OBJECTIVE TYPE QUESTIONS

Q. 1 Marks
Answer any 4 out of the given 6 questions on Employability Skills (1 x 4 = 4 marks)

1 Riya traveled to Japan from India to pursue her higher education. But she doesn't know 1M
how to speak Japanese (language of Japan). Because of this, she was unable to find a
part time job. This is an example of
(a) Interpersonal barrier
(b) Physical barrier
(c) Organizational barrier
(d) Linguistic barrier
2 “R D Singh started with a small shop with his focus, dedication and clear ideas, RDS 1M
became one of the most popular brands in India besides having a good reputation all
over the world”.
Which self-management skill is clearly visible in the given statement?
3 _______the work is all about identifying and noting how we spent our time, and 1M
analyzing how to spend our time effectively.
(a) Organizing
(b) Prioritizing
(c) Controlling
(d) Tracking
4 When you bring the mouse over a file in File Explorer, it will show the details of that 1M
file.
This is known as
(a) Drag and drop
(b) Double click
(c) Hover
(d) Single click
5 “Efforts are made to increase the solar power generation so that our electricity needs 1M
are met and at the same time we do not pollute the environment or use up natural
resources”.
Which SDG can you relate this statement to?
(a) Life on land
(b) Clean water and sanitation
(c) Affordable and clean energy
(d) Reduced inequalities
6 Assertion(A): A software engineer works for a renowned company. 1M
Reason(R): The statement given above is an example of wage employment.
(a) Both A and R are correct and R is the correct explanation of A
(b) Both A and R are correct but R is NOT the correct explanation of A
(c) A is correct but R is not correct
 (d) A is not correct but R is correct

Q. 2 Answer any 5 out of the given 6 questions (1 x 5 = 5 marks)

1 Assertion (A)– One can be a good singer while the other can be a great athlete. 1M
Reason(R) – Humans possess different types of intelligences but at different levels.
(a) Both A and R are correct and R is the correct explanation of A
(b) Both A and R are correct but R is not the correct explanation of A
(c) A is correct but R is not correct
(d) A is not correct but R is correct.
2 The Indian Government banned a few apps stating – “servers in the hostile nation are 1M
receiving and using the acquired data improperly”.
Which terminology suits best for this action?
(a) AI Ethics
(b) Data Privacy
(c) AI Bias
(d) AI Access
3 Statment1: There are four layers in a neural network. 1M
Statement2:The first layer of the neural network is known as the output layer.
(a) Both Statement1 and Statement2 are correct
(b) Both Statement1 and Statement2 are incorrect
(c) Statement1 is correct but Statement2 is incorrect
(d) Statement2 is correct but Statement1 is incorrect
4 Observe the given graph and fill in the blank: 1M

__________the neural network, better is the performance.

5 CSV stands for 1M

(a)Comma Separated Values
(b) Comma Separates Value
(c) Comma Separated Variable
(d) Common Separated Values
6 A corpus contains 4 documents in which the word ‘hello’ was appearing once in 1M
document1. Identify the term in which we can categorise the word ‘hello’.
(a) Stop word
(b) Rare word
(c) Frequent word
(d) Removable word
Q. 3 Answer any 5 out of the given 6 questions (1 x 5 = 5 marks)

1 Read the examples given below- 1M

i. Using Chat GPT to write an email
ii. Face unlock technology of mobile phones using camera
iii. Turning off lights with IoT device
iv. Hand sanitizer dispenser having sensor Choose the options that are not AI
(a) i and ii
 (b) iii and i
(c) iii and iv
(d) i, iii and iv
2 _________summarizes all of the important points in one place. 1M
a. Problem statement template
b. Problem statement document
c. Problem statement file
d. None of the above
3 What is the name of the popular programming language used in data science? 1M

4 ________is the process of finding instances of real-world objects in images or videos. 1M

(a) Instance segmentation
(b) Object detection
(c) Classification
(d) Image segmentation
5 Nidhi, a student of class XII developed a chatbot that clarifies the doubts of Biology 1M
students. She trained the software with lots of data sets catering to all difficulty levels.
If any student would type or ask questions related to Biology, the software would give
an instant reply. Identify the domain of AI in the given scenario.
(a) Computer Vision
(b) Data Science
(c) Natural Language Processing
(d) None of these
6 What is the value of F1 score if the model is 100 % accuracy? 1M
a. 100
b. 1
c. 0
d. 50
Q. 4 Answer any 5 out of the given 6 questions (1 x 5 = 5 marks)

1 Sachin has made a model which predicts the performance of Indian Cricket players in 1M
upcoming matches. He collected the data of players’ performance with respect to
stadium, batsman, opponent team and health. His model works with good accuracy and
precision value. Which of the statement given below is incorrect?
(a) Data gathered with respect to stadium, batsman, opponent team and health is
known as Testing Data.
(b) Data given to an AI model to check accuracy and precision is Testing Data.
(c) Training data and testing data are acquired in the Data Acquisition stage.
(d) Training data is always larger as compared to testing data.
2 Statment1: The output given by the AI model is known as reality. 1M
Statement2:The real scenario is known as Prediction.
(a) Both Statement1 and Statement2 are correct
(b) Both Statement1 and Statement2 are incorrect
(c) Statement1 is correct but Statement2 is incorrect
(d) Statement2 is correct but Statement1 is incorrect
3 Srishti learnt about AI terminologies but was not able to recollect the term that is used 1M
to refer to machines that perform tasks with vast amounts of data using neural
networks. Help her with the correct term.
4 How many channels does a colour image have? 1M
 5 Which feature of NLP helps in understanding the emotions of the people mentioned 1M
with the feedback?
(a) Virtual Assistants
(b) Sentiment Analysis
(c) Text classification
(d) Automatic Summarization
6 Anuj made a face mask detector system for which he had collected the dataset and 1M
used all the dataset to train the model. Then, he used the same data to evaluate the
model which resulted in the correct answer all the time but was not able to perform
with unknown dataset.
Name the concept.
Q. 5 Answer any 5 out of the given 6 questions (1 x 5 = 5 marks)

1 An organization is using a AI enabled Security surveillance system. Surya works as a 1M

Security guard in the Organization. Due to usage of AI enabled security system he has a
feeling that he may not be needed in the near future. What is this situation?
a. Data Privacy b. AI Bias
c. AI Accessd. AI is creating Unemployment
2 Which evaluation parameter takes into consideration all the correct predictions? 1M

3 _______means a picture element which is the smallest unit of information that makes 1M
up a picture.
(a) Vision
(b) Pics
(c) Pixel
(d) Piskel
4 ________are the words which occur very frequently in the corpus but do not add 1M
any value to it.
a. Special Characters
b. Stopwords
c. Roman Numbers
d. Useless Words
5 What do you mean by syntax of a language? 1M
(a) Meaning of a sentence
(b) Grammatical structure of a sentence
(c) Semantics of a sentence
(d) Synonym of a sentence
6 Which one of the following scenario result in a high false positive cost? 1M
(a) viral outbreak
(b) forest fire
(c) flood
(d) spam filter

SECTION B: SUBJECTIVE TYPE QUESTIONS

Answer any 3 out of the given 5 questions on Employability Skills (2 x 3 = 6 marks)
Answer each question in 20 – 30 words.
Q 6 Enumerate any two ways to overcome barriers to effectivecommunication. 2M
Q .7 In SMART goals, what does ‘S’ stand for? Explain. 2M

Q 8 How can we increase the performance of a computer? 2M

Q .9 How do entrepreneurs help in growing the area and society they live in? 2M

Q 10 “With increasing population and income, the consumption of goods is increasing day by 2M
day.” – Comment
Answer any 4 out of the given 6 questions in 20 – 30 words each (2 x 4 = 8 marks)

Q 11 All of us use smartphones. When we install a new app, it asks us for several permissions 2M
to access our phone’s data in different ways. Why do apps collect such data?
Q .12 Sneha and Devika want to make a model which will organize the unlabeled input data 2M
into groups based on features. Which learning model should they use and why?
Q 13 Describe the steps involved in the data science workflow. 2M

Q .14 In the healthcare industry, Computer Vision is utilized for analysing medical images 2M
such as MRI and CT scans. Describe how Computer Vision can assist in detecting
abnormalities such as tumours, and discuss the advantages of using this technology in
early diagnosis and treatment planning.
Q 15 Explain the key steps of NLP – based text analysis 2M

Q 16 Draw the confusion matrix for the following data 2M

• the number of true positive = 100
• the number of true negative 47
• the number of false positive = 62
• the number of false negative = 290
Answer any 3 out of the given 5 questions in 50– 80 words each (4 x 3 = 12 marks)

Q.17 Your grandfather watches you use AI applications. He wants to understand more about 4M
it. Help him to understand the term artificial intelligence by giving the right definition
and explain to him with an example how machines become artificially intelligent.
Q.18 Vidhyuth wants to learn how to scope the problem for an AI Project. Explain him the 4M
following:
(a) 4W Problem Canvas
(b) Problem Statement Template
Q.19 Explain Rule-based AI modelling approaches. 4M

Q.20 List out the applications of Natural Language Processing. 4M

Q.21 A binary classification model has been developed to classify the information spread 4M
through social media is as either “Fake ” or “Real ”. The model was tested on a dataset
of 300 information, and the resulting confusion matrix is as follows:

Calculate Accuracy, precision, recall and F1 score.

 KENDRIYA VIDYALAYA SANGATHAN HYDERABAD REGION
ARTIFICIAL INTELLIGENCE (SUBJECTCODE -417)
Class X
Model Question Paper–20(Solutions)
SECTION A: OBJECTIVE TYPE QUESTIONS
Q. 1
Answer any 4 out of the given 6 questions on Employability Skills (1 x 4 = 4 marks)
1 (d) Linguistic barrier
2 Self-Motivation
3 (d) Tracking
4 (c) Hover
5 (c) Affordable and clean energy
6 (a) Both A and R are correct and R is the correct explanation of A
Q. 2 Answer any 5 out of the given 6 questions (1 x 5 = 5 marks)
1 (a) Both A and R are correct and R is thecorrect explanation of A.
2 (b) Data Privacy
3 (a) Both Statement1 and Statement2 areincorrect.
4 Larger
5 (a) Comma Separated Values
6 (b) Rare word
Q. 3 Answer any 5 out of the given 6 questions (1 x 5 = 5 marks)
1 (c) iii and iv
2 a. Problem statement template
3 Python (or R, SQL, etc.).
4 (b) Object Detection
5 (c) Natural Language Processing
6 b. 1
Q. 4 Answer any 5 out of the given 6 questions (1 x 5 = 5 marks)
1 (a) Data gathered with respect to
2 stadium, batsman, opponent
(b) Both Statement1 team and
and Statement2 health is known as Testing Data.
areincorrect.
3 Deep Learning
4 Three Channels
5 (b) Sentiment Analysis
6 Overfitting
Q. 5 Answer any 5 out of the given 6 questions (1 x 5 = 5 marks)
1 (d) AI is creating Unemployment
2 Accuracy
3 (c) Pixel
4 b. Stopwords
 5 (b) Grammatical structure of a sentence
6 (d) spam filter

SECTION B: SUBJECTIVE TYPE QUESTIONS

Answer any 3 out of the given 5 questions on Employability Skills (2 x 3 = 6 marks)
Answer each question in 20 – 30 words.
Q 6 Ways to Overcome Barriers to Effective Communication (Any Two)
a) Use simple language
b) Do not form assumptions on culture, religion or geography
c) Try to communicate in person as much as possible
d) Use visuals
e) Take help of a translator to overcome differences in language
f) Be respectful of other’s opinions
Q .7 We can use SMART method to set goals. SMART stands for:
• Specific: A specific and clear goal answers six questions. Who is involved in the goal? What do
I want to do? Where do I start? When do I start and finish? Which means do I use? Why am I
doing this? Not a specific goal: “I would learn to speak English.”

Specific goal: “I would learn to speak English fluently by joining coaching classes after my
school every day, and in six months I will take part in the inter-school debate competition.”
Q 8 We can increase the performance of system by:
1. Using an updated Antivirus
2. Removing unnecessary files and data such as temporary files and images.

Q .9 Entrepreneurs run their businesses in a market. The market has people who buy products and
services and people who sell them also. When people are buying and selling from each other, it
is helpful for everyone because everyone involved makes money. This is how entrepreneurs
help in growing the area and society they live in.
Q 10 “With increasing population and income, the consumption of goods is increasing day by day.”
This has led to increase in production and utilisation of natural resources, which are required
for producing goods. Society must thus change its development strategy to a new form where
development will not destroy the environment.

Answer any 4 out of the given 6 questions in 20 – 30 words each (2 x 4 = 8 marks)

Q 11 1. To provide customized notifications and recommendations.

2. To improve the efficiency and accuracy of the app.
Q .12 Clustering model/Unsupervised learning is used to organize the unlabeled input data into
groups based on features.
Clustering is an unsupervised learning algorithm which can cluster unknown data according to
the patterns or trends identified out of it. The patterns observed might be the ones which are
known to the developer or it might even come up with some unique patterns out of it.
Q 13 The data science workflow typically involves:
- Problem definition and hypothesis formation
- Data collection and cleaning
- Data exploration and visualization
- Modeling and evaluation
- Deployment and maintenance
Q .14 Computer Vision algorithms can analyze medical images to detect abnormalities like tumors by
identifying unusual patterns and shapes that indicate the presence of disease. The advantages
include faster and more accurate diagnosis, early detection of diseases, and improved
treatment planning. This technology reduces the workload on medical professionals and
increases the chances of successful treatment by identifying issues at an early stage.
Q 15 Key steps of NLP – based text analysis are following :
i) Sentence Segmentation
ii) Tokenization
iii) Removing Stop words, Special Characters and Numbers
iv) Stemming
v) Converting Text to common Case
vi) Lemmatization
Q 16

Answer any 3 out of the given 5 questions in 50– 80 words each (4 x 3 = 12 marks)

Q.17 When a machine possesses the ability to mimic human traits, i.e., make decisions, predict the
future, learn and improve on its own, it is said to have artificial intelligence. In other words,
you can say that a machine is artificially intelligent when it can accomplish tasks by itself -
collect data, understand it, analyse it, learn from it, and improve it.
Machines become intelligent once they are trained with some data which helps them achieve
their tasks. AI machines also keep updating their knowledge to optimise their output. For
example, Netflix gives us recommendations on the basis of what we like. Whenever we start
liking a new genre, it
updates and gives better suggestions.
Q.18 The 4Ws Problem canvas helps in identifying the key elements related to the problem. The
4Ws are Who, What, Where and Why
● The “Who” block helps in analysing the people getting affected directly or indirectly due to
the problem.
● The “What” block helps us to determine
the nature of the problem.
● The “Where” block helps us to look into the situation in which the problem arises, the
context of it, and the locations where it is prominent.
● The “Why” block suggests to us the benefits which the stakeholders would get from the
solution and how it will benefit them as well as the society

Q.19 Rule Based Approach: It refers to the AI modelling where the relationship or patterns in data
are defined by the developer. The machine follows the rules or instructions mentioned by the
developer, and performs its task accordingly. For example, suppose you have a dataset
comprising of 100 images of apples and 100 images of bananas. To train your machine, you
feed this data into the machine and label each image as either apple or banana. Now if you test
the machine with the image of an apple, it will compare the image with the trained data and
 according to the labels of trained images, it will identify the test image as an apple. This is
known as Rule based approach. The rules given to the machine in this example are the labels
given to the machine for each image in the training dataset.
Q.20 Chatbots are a form of artificial intelligence that is programmed to interact with humans in
such a way that they sound like humans themselves.
Depending on the complexity of the chatbots, they can either just respond to specific keywords
or they can even hold full conversations that make it tough to distinguish them from humans.
Chatbots are created using Natural Language Processing and Machine Learning, which means
that they understand the complexities of the English language.
a. NLP is used in search engines they suggest the text to be typed automatically
b. Siri, Alexa, or Google Assistant uses NLP. They use a complex combination of speech
recognition, natural language understanding, and natural language processing to understand
what humans are saying and then act on it.
c. Language Translator - Google Translate and other translation tools as well as use Sequence
to sequence modelling that is a technique in Natural Language Processing. It allows the
algorithm to convert a sequence of words from one language to another which is translation.
d. Sentiment Analysis - companies can use sentiment analysis to understand how a particular
type of user feels about a particular topic, product, etc. They can use natural language
processing, computational linguistics, text analysis, etc. to understand the general sentiment of
the users for their products and services and find out if the sentiment is good, bad, or neutral
e. Grammar Checkers - They use not only correct grammar and check spellings but also suggest
better synonyms and improve the overall readability of your content. The NLP algorithm is
trained on millions of sentences to understand the correct format. Some of the most popular
grammar checkers that use NLP include Grammarly, WhiteSmoke, ProWritingAid, etc.
Q.21 Accuracy=(150+60)/300=0.7
Recall=150/200=0.75
Precision=150/190=0.789
F1 score=2*0.75*0.789/(0.75+0.789)=0.76