Computer Science

Teacher: Maruf Ahmed

Chapter 6 (Automated and emerging technologies)

Automated systems:
- An automated system is a combination of software and hardware that is designed and programmed to
work automatically without the need of any human intervention.
- However, such systems often involve human monitoring.

The hardware needed in an automated system are:

- Sensor: input devices that take reading from their surroundings and sends this data to a
microprocessor or computer. If the data is analogue (for example, temperature, density etc.), it is first
converted into digital format by an analogue to digital (ADC) converter
- Microprocessor: It processes the received input from the sensors. It compares input values with pre-
set values. If necessary, it will send instructions to other components such as actuators based on
programming
- Actuators: This will involve some form of output. Actuator turns electrical signals sent by
microprocessor into physical outputs such as turn on / off a valve, controls motors, rotate steering,
and so on.

Distributed control system (DCS): At the centre of an automated system is a distributed control system
(DCS). DCS is essentially a powerful computer that has been programmed to monitor and control the whole
process with no human interaction required.
The DCS will have access to a large database containing operational data and parameters. If any action
needs to be taken, then signals will be sent to the appropriate actuators to operate pumps, valves or even an
emergency shutdown system. The key here is that the system is fully automated.

How automated systems work:

- Data from a number of sensors is sent to a DCS (computer)
- If the data is analogue, it must first be converted into digital format using an ADC
- The DCS will have access to a large database containing operational data and parameters
- If any action needs to be taken, then signals will be sent from the microprocessor to the appropriate
actuators to operate pumps, valves or even an emergency shutdown system

Advantages and disadvantages of automated system (These are generic points. You have to give the answer
based on the scenario):

The main advantages of automated system are:

• much faster than a human operator to take any necessary action
• much safer (an automated system is more likely to make timely interventions than a human; it also
keeps humans away from a dangerous environment)
• the process is more likely to run under optimum conditions since any small changes needed can be
identified very quickly and action taken
• in the long run, it is less expensive (an automatic system replaces most of the workforce who would
need to monitor the process 24 hours a day).

The main disadvantages of automated system are:

• expensive to set up in the first place and needs considerable testing
• always possible for a set of conditions to occur that were never considered during testing which
could have safety implications (hence the need for a supervisor)
• any computerised system is subject to cyber-attacks no matter how good the system (one way round
this is to have no external links to the DCS; although the weak link could potentially be the
connection to the supervisor)
• automated systems always need enhanced maintenance which can be expensive

Page 1 of 9
Areas where automated systems are used:
• industrial
• transport
• agriculture
• weather
• gaming
• lighting
• science

Industrial:
Automated systems can be used in industrial areas such as: in nuclear power station, manufacturing of
paracetamol, manufacturing fizzy drinks etc.
Manufacturing of fizzy drinks scenario is described below.

A company manufactures fizzy drinks that are then labeled and bottled. Describe how the sensors, actuators
and central computer would be used to monitor and control this bottling plant automatically.

• Sensors are needed to detect the presence of a bottle

• Level sensor is used in mixing tank to ensure the required volume is maintained
• Other sensors such as temperature and pH may be needed
• Bottle arrives at bottling station
• Sensor sends data back to central computer continuously
• If a bottle is present, the computer sends signal to the actuator to open a valve to allow liquid to fill
the bottle. Level sensors are used to check the correct amount of liquid is added. Once level sensor
reading indicates bottle is full, a signal is sent to computer which then sends a signal to an actuator to
close the valve
• Computer then sends signal to actuator to open valve and add measured amount of carbon dioxide
gas
• After for example, two seconds, the gas valve is closed
• Next empty bottle arrives and process continues
• Bottle now moves to capping station
• Again, sensor detects bottle and computer sends signal to robot arm to place cap on bottle and tighten
it and then robot arm retracts
• Bottle moves to labeling station
• Sensor detects bottle and computer sends signals to actuator to rotate table through 360 degree as
label is glued to bottle
• Whole process is continuous

Transport (Automated cars):

- Automated cars use sensors, cameras, microprocessor and actuators to carry out their actions safely.
- Microprocessors process the data received from cameras and sensors and send signals to actuators to
perform physical actions such as change gear, apply the brakes, turn the steering wheel etc.

Advantages of autonomous cars:

Page 2 of 9
 - Safer because human error is removed due to fewer accidents
- Better for the environment since vehicle will operate more efficiently
Disadvantages of autonomous cars:
- Very expensive system to set up in the first place
- The ever-present fear of hacking into the vehicle’s control system

Agriculture (Automatic harvesting of crops):

- Sensors detect optimal times for harvesting based on factors such as weather conditions
- Microprocessors using the values from the sensors determine where exactly you should do the
harvesting
- Actuators are used to carry out the extraction of goods from the ground
Advantages:
- Delivery of chemicals (pesticides and fertilizers) can be given accurately which is important to the
success of farming and crops
Disadvantages:
- Fewer job opportunities as humans are increasingly replaced by machinery.

Weather (at airport):

- Automated monitoring of weather at airports to help predict poor flying and landing conditions
- Sensors check for potentially dangerous weather such as wind, rain, fog or snow
- Microprocessors are programmed to issue relevant warnings as a result of the data gathered
- Actuators activate emergency system such as lighting wherever required
Advantages:
- Information about the overhead weather conditions is fed constantly to air traffic controllers
Disadvantages:
- Predictions can sometimes be incorrect, for example, if snow is forecast and does not arrive

Gaming:
- The introduction of artificial intelligence as opponents in computer games
- Sensors are built into gaming environments where characters interact with human controllers
- Microprocessors determine game outcomes and decisions
- Actuators are activated in controllers to give haptic feedback such as vibrations
Advantages:
- The depth of gaming challenge has increased with computer generated opponents who behave in a
human way
Disadvantages:
- Decreases real social interactions with other humans and can create an almost fictional life

Lighting:
- Lighting control systems in a house where routines can be present based on behaviours
- Sensors can detect ambient light levels
- Microprocessor runs routines based on human requirements
- Actuators can activate home equipment
Advantages:
- System can be taught to react to environmental factors, such as switching lights on and off when the
conditions are correct
Disadvantages:
- Systems can become complex as they are different from traditional switches. The light bulbs and
technology also tend to be expensive to maintain

Science:
- Automated laboratory experiments that can be carried out continuously over many days
- Sensors detect changes in environmental conditions
- Microprocessors can calculate required alterations to the experimental settings
- Actuators can turn on heaters, coolers or water suppliers as required
Page 3 of 9
Advantages:
- Many more repetitions of experiments and reading of data can take place than when human carry out
tests manually
Disadvantages:
- If something goes wrong it can be several hours before this is discovered, which could ruin any
results collected

Use of artificial intelligence (AI) in automated systems:

There are many automated systems being used in both industry and scientific research that incorporate
artificial intelligence (AI).
It is therefore worth considering the generic advantages of using AI in these automated systems:
• ability to access and store vast amounts of facts (very important in research)
• they are able to learn from huge amounts of available data that would overwhelm humans (or at the
very least take them many months/years to do the same analysis)
• they are able to see patterns in results that could be missed by humans

While all of this is positive, there are a few disadvantages in this approach:
• a change in skills set (is it the human or the AI that controls the research?)
• AI is dependent on the data which trains it

Robotics:
Robotics is a branch of computer science that incorporates
- the design of robots
- the construction of robots and
- the operation of robots

Examples include factory equipment, domestic robots and drones etc.

Characteristics of a robot:
To be correctly called a robot, they need to have the following characteristics:
- It has a mechanical structure or framework
o They are mechanical structures made up of many parts (for example, motors, hydraulic pipes,
actuators and circuit boards)
o It should be a machinery that has movable parts
o They can make use of wheels, cogs, pistons, gears etc. to carry out functions such as turning,
twisting, moving backwards/forwards, gripping or lifting
- It has electrical components, such as sensors, microprocessors and actuators
o Sensors sense the surrounding and provide the input to the processor
o Microprocessor processes the input data
o Actuators do the work
- It is programmable
o They have ‘brain’ known as a controller that determines the action to be taken to perform a
certain task (the controller relies on data sent from sensors or cameras, for example).
o Controllers are programmable to allow the robots to do certain tasks
- It has the ability to sense their surroundings
o this is done via sensors (such as light, pressure, temperature, acoustic, and so on)
o sensors allow a robot to recognise its immediate environment and gives it the ability to
determine things like size, shape or weight of an object, detect if something is hot or cold,
and so on; all sensor data is sent to a microprocessor or computer

Types of robots:
Independent robots:
- have no direct human control (they are said to be autonomous, for example, an autonomous vehicle)

Page 4 of 9
 - can replace the human activity totally (no human interaction is required for the robot to function
fully).

Dependent robots:
- have a human who is interfacing directly with the robot (the human interface may be a computer or a
control panel)
- can supplement, rather than totally replace, the human activity (for example, in a car assembly plant
where both humans and robots work together to produce a car).

Use of robots in different areas:

- industry
- transport
- agriculture
- medicine
- domestic (home) use
- entertainment

Advantages and disadvantages of using robots (These are generic points. You have to give the answer based
on the scenario):

Advantages of using robots:

- more efficient than a human
- more accurate than a human
- can lift larger and heavier equipment than a human
- can replace humans working in a dangerous environment
- reduces running costs, such as wages and overheads
- can produce consistent results/output
- can work 24 hours a day // do not need to take breaks

Disadvantages of using robots:

- The use of robots can create economic problems if they replace human jobs
- Robots can only do what they are told to do – they can’t improvise
- Often robots are very costly – in terms of the initial cost, maintenance, the need for extra components
and the need to be programmed to do the task.

End effector: In robotics, an end effector is a device or tool that's connected to the end of a robot arm where
the hand would be. The end effector is the part of the robot that interacts with the environment. The structure
of an end effector and the nature of the programming and hardware that drives it depend on the task the
robot will be performing.

Scenario based question:

How Robotic technology used in car manufacturing industry:
• Use of robotic arms to move heavy/delicate parts into places where humans would have difficulties
• Use of robotic end effectors to carry out (repetitive) tasks e.g., fitting wheels/tightening bolts/nuts
• Used to install delicate/breakable items e.g., such as suction pads to install windshields/screens
• Used to weld/spot weld body panels with consistent accuracy/same orientation each time
• Used to remove unwanted materials/trim fittings consistently
• Used to paint areas following consistent path/using same amount of paint on each item
• Used to move dangerous/hot mouldings / materials such as pouring metal into engine
blocks/moulds/removing items from injection moulds
• Use of force sensing technology when polishing surfaces

Page 5 of 9
 • Collaboration between robotic devices to carry out complex tasks e.g. placing object and then
welding it
• Use of robotic vision/cameras/lenses to inspect items/jobs/tasks
• Combining with artificial intelligence to inspect components during manufacture/assembly

Scenario based question:

How Robotic technology used in space exploration:
• Can be used to aid/augment/replace humans in space exploration
• Assist/used for tasks in hazardous conditions e.g., high radiation/extreme temperatures where
humans cannot go/work
• Automatic/autonomous spacecraft for space exploration/research at long distances/time
• Automatic/autonomous spacecraft for delivery of resources to/return of materials from e.g., ISS
• Automatic/autonomous machines for repair of space objects/satellites
• Robotic arms fitted to space craft to move (large) objects
• Automatic/autonomous vehicles for exploration of other worlds/space objects

Artificial intelligence:
- Artificial intelligence (AI) is a branch of computer science dealing with the simulation of intelligent
human behaviour (reasoning, speech, sight etc.) by a computer. This is often referred to as the
cognitive functions of the human brain. Essentially, AI is really just a collection of rules and data,
and the ability to reason, learn and adapt to external stimuli.
- When we are designing an AI system, we are essentially instilling our thought process onto a
machine

Cognition: the mental action or process of acquiring knowledge and understanding through thought,
experience, and the senses
Reasoning: the action of thinking about something in a logical, sensible way

Describe what is meant by AI.

• The simulation of intelligent behaviours by computers
• A collection of data and the rules for using that data
• Has the ability to reason
• Has the ability to learn/adapt

Characteristics of AI:
• The ability to learn/adapt // machine learning abilities
• The collection of data and the rules for using that data
• The ability to reason // has problem solving abilities // makes predictions
• Simulates intelligent/human behavior
• Analyses patterns

AI can be split into three categories:

General AI – this occurs when a machine is similar (not superior) in its performance to a human doing a
specific task
Narrow AI – this occurs when a machine has superior performance to a human when doing one specific
task
Strong AI – this occurs when a machine has superior performance to a human in many tasks

Applications of AI include:
- news generation based on live news feeds
- smart home devices (such as Amazon Alexa, Google Now, Apple Siri and Microsoft Cortana)
- use of chatbots that interact through instant messaging
- autonomous cars
- facial expression recognition
Page 6 of 9
AI systems:
- Expert system
- Machine learning

Expert system – a computer system that mimics the decision-making ability of a human; expert systems use
AI to simulate the judgment and behaviour of a human or organisation that has expert knowledge and
experience.

What makes up an expert system?

Components of an Expert system:

- Interface
- Knowledge base
- Rules base
- Inference engine

Interface:
• Allows user to enter problems
• Questions are output by the system
• Allows user to input answers to the questions
• Further questions are output to the user interface based on the previous answers
• Outputs explanation of findings
• Outputs suggestions/probabilities of possible solutions

Inference engine:
• The inference engine compares data with that held in the knowledge base
• It makes decisions by applying the inference rules/logic to the facts/knowledge base to provide a
result/diagnosis
• Produces suggestions/probabilities of possible solutions
• Uses explanation system to produce explanations as to how solutions were arrived at

Knowledge base:
• Knowledge base holds the database of facts that the inference engine searches
• These facts are obtained from a number of expert resources
• Contains the rules base which consists of IF … THEN … constructs

Rules base:
• Stores the rules for the system usually involving a series of ‘IF…THEN’ statements
• These rules are used by the inference engine to draw conclusions
• Used to link the facts in the knowledge base
• they follow logical thinking; for example: IF continent = “South America” AND language =
“Portuguese” THEN country = “Brazil”
Page 7 of 9
Explanation system:
• Suggests action to take
• It could also provide the accuracy of its prediction

Explain how an expert system operates.

- It has an interface which is used to input data
- Decides what to ask next based on the data input
- An expert system has a knowledge base that contains a list of facts
- The Inference engine applies the Rule base to the Knowledge base to provide
output/diagnosis/result/solution/decision
- Uses an interface to view output

Explain why an expert system needs a knowledge base.

- It needs facts to generate the rules and to make the decisions
- The data it contains is essential to the decision-making process

There are many applications that use expert systems:

- oil and mineral prospecting
- diagnosis of a patient’s illness
- fault diagnostics in mechanical and electronic equipment
- tax and financial calculations
- strategy games, such as chess
- logistics (efficient routing of parcel deliveries)
- identification of plants, animals and chemical/biological compounds.

Expert systems have many advantages:

- they offer a high level of expertise
- they offer high accuracy
- the results are consistent
- they have the ability to store vast amounts of ideas and facts
- they can make traceable logical solutions and diagnostics
- it is possible for an expert system to have multiple expertise
- they have very fast response times (much quicker than a human expert)
- they provide unbiased reporting and analysis of the facts
- they indicate the probability of any suggested solution being correct.

Expert systems also have disadvantages:

- users of the expert system need considerable training in its use to ensure the system is being used
- the set up and maintenance costs are very high
- they tend to give very ‘cold’ responses that may not be appropriate in certain medical situations
- they are only as good as the information/facts entered into the system
- users sometimes make the very dangerous assumption that they are infallible.

Scenario based question:

In a medical expert system, the inference engine receives symptoms from the user interface.
Explain how the inference engine uses these inputs to produce possible diagnoses
• Inference engine finds possible diagnoses by using a form of reasoning
• The inference engine uses the data or facts in the knowledge base to reason through the symptoms
• The reasoning involves forward chaining, backward chaining or a combination of both
• Inference engine compares symptoms to those in the knowledge base
• Inference engine uses the rules base of IF…THEN… rules/comparisons

Forward chaining and backward chaining: As the name imply, forward chaining begins with known facts
and moves forward by applying inference rules to extract more data, and it continues until it reaches the
Page 8 of 9
goal, whereas backward chaining begins with the goal and moves backward by applying inference rules to
determine the facts that satisfy the goal.

Scenario based question:

Many computer hardware companies use expert systems to diagnose computer faults. The inference engine
is a key component in an expert system.
Describe, in detail, the other components of an expert system.
• Knowledge base consists of a database of facts and a rules base
• Database of facts is built up by the engineer on information and knowledge of the subject specialists
(experts)
• Database of facts is also built up from databases that may exist for the topic
• Rules base is a set of rules which are usually of the form IF . . . THEN
• The shell often includes the user interface, explanation system, inference engine and knowledge base
editor
• User interface is how the computer interacts with the user
• User interface displays questions/options/results/information on a screen
• User interface enables the user to type in answers to the questions/data
• Knowledge base editing software/knowledge base editor enables the knowledge engineer to edit
rules and facts within the knowledge base
• Explanation system explains to a user the chain of reasoning used to arrive at a particular conclusion

Machine learning:
- this is the science of training computers with sample data so that they can go on to make predictions
about new unseen data, without the need to specifically program them for the new data.
- Machine learning is a sub-set of artificial intelligence (AI), in which algorithms are ‘trained’ and
learn from their past experiences and examples. It is possible for the system to make predictions or
even take decisions based on previous scenarios.
- They can offer fast and accurate outcomes due to very powerful processing capability. One of the
key factors is the ability to manage and analyse considerable volumes of complex data; some of the
tasks would take humans years to complete without the help of machine learning techniques.

What is meant by machine learning?

- When a program has the ability to automatically adapt to its own processes and/or data

Describe what is meant by machine learning capabilities.

• It is a form of artificial intelligence
• Means it can adapt/change (its own processes) // It can edit its own algorithms
• It can edit its own data
• It can be trained
• this can be supervised/unsupervised meaning it can learn with/without human interaction
• Analyses patterns and stores successful/unsuccessful results to influence future decisions
• Supervised means a user tells the system the input and output
• Unsupervised means the system is given the input and needs to work out the output

Uses of machine learning:

- Used in search engine
- Categorising email as spam
- Detection of fraudulent activity

Difference between Expert system and machine learning

- The expert systems are rule based systems while machine learning is based on statistical modeling of
data. That is, an expert system uses IF-THEN statements when doing inference while a machine
learning system projects the input into some model space

Page 9 of 9