Scribd
Upload
10 views4 pages

594 Assignment 3

Uploaded by

namanwho
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
10 views4 pages

594 Assignment 3

Uploaded by

namanwho
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 4

University of Illinois at Chicago

Department of Mechanical and Industrial


Engineering

IE 594 - Industrial AI and Applications for Machine Health


Diagnosis and Prognosis

Assignment: 3
03-27-2024

By: Instructor:

Naman Sreyas G – 657659623 Dr. David He

Jaswin Sriraj D - 663470838


Image Classification with Convolution Neural Networks:

Data Preparation: We prepared a dataset containing 60 images of different shapes. The


5 different classes of the shapes here are: Circle, Pentagon, Square, Star, and Triangle.
There are 15 images in each class for the training dataset.

Model Training: To train the AI model, we implemented CNN using Rapidminer and
classified the images into their respective classes. This classified dataset is from the
training dataset. We used the Softmax activation function in the output layer under the
deep learning (tensor) operator.
Model Evaluation: in this image classification, we tested the model using the classes
Circle, Pentagon, and Square. We used 6 images in each class for the testing dataset.
The goal of the model evaluation was to test the trained CNN AI model to check its
capability to predict unknown images and categorize them into the trained image
classes. The accuracy metric is used here to measure the efficiency and performance of
the trained model.
Report: We have successfully implemented CNN using Rapidminer to obtain an
accurate image classification deep learning model. We used 5 classes of images and
trained the model to classify them into their respective classes. Then testing dataset
was used to test the model performance in which 3 classes were chosen with 6 images
each. The role of neurons in the development of a deep learning model is observed in
the deep learning model. Neurons receive one or more input signals and send output
signals to neurons deeper in the neural network. The activation function calculates the
output value for the neuron. The activation function calculates the output value for the
neuron.

Depending on the data preparation, the accuracy of the classification model fluctuates.
In this assignment, we have used different shapes to make it easy for the machine to
identify the differences and categorize the images into their respective classes.

The model was designed with different layers of deep learning with convolution layer,
pooling layer, dropout layer, activation layer, fully-connected layer, and the output layer.
The accuracy metric was selected to measure the model performance. An epoch in
machine learning means one complete pass of the training dataset through the
algorithm. The number of epochs specifies the number of complete passes of the entire
training dataset passing through the training or learning process of the algorithm. We
have set the number of epochs to 100.

Testing the model with test image classes, gave us 100% accuracy of the performance
displaying the efficiency of the deep learning model. The model was able to classify the
test images circles, pentagons, and squares accurately.

You might also like

pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy