Chapter 6 - Automated & Emerging Technologies
Chapter 6 - Automated & Emerging Technologies
(Chapter 6)
Syllabus Content:
1
Syllabus Content:
2
6 Automated & Emerging Technologies
NOTE: Automated Systems is a newly added topic in the Computer Science (2210)
syllabus for the session 2023–2025.
Automated System:
It is a combination of software and hardware (sensors, microprocessors, and actuators). It is
designed and programmed to work automatically without the need for human intervention.
However, such systems often involve human monitoring.
The sensors are input devices that measure/take physical readings of the surrounding
environment and records, indicates, and sends this data to a microprocessor.
If the data is analogue, it is first converted into a digital format (binary values) using an
analogue to digital converter (ADC).
The microprocessor will process this data and compare it to a pre-set/stored value.
It will then send a signal and take an action based on its programming.
This whole process will involve some form of output, usually involving signals sent to
actuators to control motors, wheels, solenoids, and so on.
1. Industrial 5. Gaming
2. Transport 6. Lighting
3. Agriculture 7. Science
4. Weather
3
1) Industrial Applications:
There are many examples of the use of automated systems in industry but only two examples are
given below. These two examples can be applied to many other industrial processes with the same
keywords and steps/sequence of answering but slight changes can be made according to scenario
asked in examination question.
A human operator will monitor the process in a remote-control room (monitoring station) where a
schematic of the processes will be shown on a large screen. While the process is fully automatic,
the human operator can still override the system if necessary.
4
2) Manufacture of Paracetamol Tablets (locally called Panadol):
A human operator will monitor the process in a remote-control room (monitoring station) where a
schematic of the processes will be shown on a large screen. While the process is fully automatic,
the human operator can still override the system if necessary.
5
2) Transportation Applications:
There are many examples of the use of automated systems in transport but only four examples are
given below. These four examples can be applied to many other transportation applications with
the same keywords and steps/sequence of answering but slight changes can be made according to
scenario asked in examination question.
The transport automated systems are still used in manually controlled transport, which includes
cars, buses/lorries, trains, and aircraft (autonomous buses/cars, autonomous trains, and unpiloted
aircraft).
1) Autonomous Trains:
The modern trains will use an automatic signal control system. If the driver of the train goes
through a red (stop) light, then the microprocessor will automatically stop the train.
2) Autonomous Airplanes:
A human pilot will sit in a cockpit (control room/monitoring room) where a schematic of the
processes will be shown on different screens. While the process is fully automatic, the human pilot
can still override the system if necessary.
6
3) Self-parking Cars (Autonomous Cars):
The driver goes along the row of parked cars. The on-board sensors and cameras measure the size
of any parking spaces and microprocessor warns the driver if a suitable space has been found. The
driver then selects auto-parking, and the on-board microprocessor takes over.
A human driver will sit in the car to monitor the process. While the process is fully automatic, the
human driver can still override the system if necessary.
1. The over-reliance on automated systems by the driver can result in loss of driver’s skills.
2. The faulty/dirty sensors or cameras can send false data/images to the microprocessor which
could lead to a malfunction.
3. The kerbing of wheel is a common problem since the sensors may not pick-up low kerbs.
4. It is an expensive option that doesn’t really save the driver any money.
5. It requires additional maintenance to ensure it functions correctly at all times.
7
4) Adaptive Cruise Control (Autonomous Cars):
It maintains the set/safe distance between vehicles. A proximity sensor is used to detect how close
the vehicle is to the vehicle in front.
A human driver will sit in the car to monitor the process. While the process is fully automatic, the
human driver can still override the system if necessary.
8
3) Agricultural Applications:
There are many examples of the use of automated systems in agriculture but only one example is
given below. This example can be applied to many other agricultural processes with the same
keywords and steps/sequence of answering but slight changes can be made according to scenario
asked in examination question.
A human operator will monitor the process in a remote-control room (monitoring station) where a
schematic of the process will be shown on a large screen. While the process is fully automatic, the
human operator can still override the system if necessary.
1. It reduces labor costs since the system only needs a human operator to monitor vast areas.
2. It ensures better and more efficient control of the irrigation process.
3. It allows better control of precious resources such as water.
4. It has faster response than a human having to manually check many kilometers of irrigation
channels.
5. It is safer as temperatures in the fields could be 40oC and other risks could exist.
6. It is possible to program the microprocessors so that different growing conditions can be
maintained simultaneously as different crops may require different irrigation requirements.
9
4) Weather Applications:
There are many examples of the use of automated systems in weather but only one example is
given below. This example can be applied to many other weather processes with the same
keywords and steps/sequence of answering but slight changes can be made according to scenario
asked in examination question.
A human operator will monitor the process in a remote-control room (monitoring station) where a
schematic of the process will be shown on a large screen. While the process is fully automatic, the
human operator can still override the system if necessary.
10
5) Gaming Applications:
The gaming devices involve sensors to give a degree of realism to games:
6) Lighting Applications:
There are many examples of the use of automated systems in lighting but only one example is
given below. This example can be applied to many other lighting processes with the same
keywords and steps/sequence of answering but slight changes can be made according to scenario
asked in examination question.
It involves lights in the garden which are turned on automatically when someone enters the
garden or it turns dark. It also involves a lighting show that is a part of the microprocessor-
controlled water fountain display where the lighting only comes on when it becomes dark.
11
Advantages of this Automated System:
7) Science Applications:
There are many examples of the use of automated systems in scientific research but only one
example is given below. This example can be applied to many other scientific processes with the
same keywords and steps/sequence of answering but slight changes can be made according to
scenario asked in examination question.
An experiment is carried out in a pharmaceutical laboratory where two chemicals are reacted
together in a vessel. One of the chemicals is being added from a piece of equipment known as a
burette (which has a tap operated automatically using a small actuator to control flow of liquid) to
a reaction vessel. Once the reaction is complete, it turns a bright orange color (measured by
colorimeter) and the whole process is under microprocessor control.
A human operator will monitor the process in a remote-control room (monitoring station) where a
schematic of the process will be shown on a large screen. While the process is fully automatic, the
human operator can still override the system if necessary.
12
Advantages of this Automated System:
There are many automated systems being used in both industry and scientific research that
incorporate Artificial Intelligence (AI).
1. They have the ability to access and store vast amounts of facts which are very important in
research.
2. They are able to learn from huge amounts of available data that would overwhelm human
(or at the very least take humans many months/years to do the same analysis).
3. They are able to see patterns in results that could be missed by humans.
13
A few examples are given below which will help you better understand the pattern of answering
the Automated System questions and how to make changes in your answer according to question
statement and the scenario asked.
The answer to each question is very similar and consists of statements and the same keywords in a
sequence. However, the situation would change, and the examiner can give you any scenario and
question about the functioning of any Automated System accordingly.
Example 1:
Controlling an automatic cooker:
Example 2:
Controlling a burglar alarm:
14
Example 3:
Controlling a car parking barrier (where a light sensor is used to detect the presence of a car
and prevent the barrier from dropping onto the car):
Example 4:
Controlling/maintaining the set distance between autonomous vehicles (where a proximity
sensor is used to detect how close the vehicle is to the vehicle in front):
Example 5:
Controlling/operating an automatic heater (to switch on at the set time of 16:00 for two
hours):
The microprocessor constantly checks the current time against the start time.
If the current time is less than the set time nothing happens.
If they are the same, then the microprocessor sends a signal to the actuator to turn the
heater on.
It calculates the end time by adding 2 hours to the start time.
It constantly checks the current time against the end time.
When they are the same, it sends a signal to the actuator to turn the heater off.
15
6 Automated & Emerging Technologies
6.2 | Robotics
NOTE: Robotics is a newly added topic in the Computer Science (2210) syllabus for the
session 2023–2025.
Examples of Robots:
The robots can be found in:
1. Factories (equipment)
– welding parts together
– spray-painting panels on a car
– fitting windscreens to cars
– cutting out metal parts to a high precision
– bottling and labeling plants
– warehouses (automatic location of items)
2. Home (domestic)
– autonomous floor sweepers
– autonomous lawn mower
– ironing robots (‘dress man’)
– pool cleaning
– automatic window cleaners
– entertainment (‘friend’ robots)
16
3. Drones
– unmanned aerial vehicles (UAVs) are drones that are either remotely controlled or totally
autonomous using embedded systems.
– can be used in reconnaissance (observation/examination/inspection by for example,
taking aerial photographs)
– can be used to make parcel deliveries (for example, Amazon)
3. It is programmable.
It has a microprocessor (controller) that determines the action to be taken to perform a
certain task and the microprocessor (controller) relies on data sent from sensors or cameras
etc.
The microprocessor (controller) is programmable to allow the robot to do certain tasks.
17
Physical & Software Robots:
The physical robots and software robots are different.
Software Robots:
The software robots are not true robots. Their examples include:
The search engine bots or WebCrawlers roam the internet scanning websites, categorizing
them for search purposes.
The chat bots are programs that pop up on websites that seem to enter some form of
conversation with the web user.
Physical Robots:
The physical robots are the true robots. They can be classified as independent or dependent:
They have no direct human control and they are said to be autonomous (e.g., autonomous
vehicle).
They can replace the human activity totally and no human interaction is required for the
independent robot to function fully.
They have a human who is interfacing directly with the dependent robot and the human
interface may be a computer or a control panel.
They can supplement, rather than totally replace, the human activity (e.g., in a car assembly
plant where both humans and robots work together to produce a car).
Controlling of Robot:
The control of robots is either through embedded (built-in) microprocessors or directly
linked to a computer system.
Programming of Robot:
The robot is programmed to do a series of tasks in following two methods:
The robot is programmed with a sequence of instructions which allow it to carry out a series
of tasks (e.g., spraying a car body with paint).
18
Programming of Robot (method 2):
A human operator manually carries out the series of tasks. This can be done using two ways.
We will assume an object is being painted using a robot arm in this method 2. A robot arm is
equipped with a spray gun end-effector. The different end-effectors allow the robot arm to carry
out many different tasks.
(i) Programming of Robot using human operator manually carrying out tasks (way 1):
The robot arm is guided manually by a worker when spraying the object.
Each movement of the arm is stored as an instruction on the computer.
(ii) Programming of Robot using human operator manually carrying out tasks (way 2):
The worker straps sensors to his own arm and sprays the object.
Each movement is stored as a set of instructions on a computer.
The sensors send back information such as position relative to that object, arm rotation
and so on.
This information forms part of the instructions stored on the computer.
Whichever method is used for programming of robot, once the instructions have been saved, each
series of tasks can then be carried out by a robot arm automatically.
Each instruction will be carried out identically every time (e.g., assembling parts in a television)
giving a consistent product.
Sensors in Robot:
The robot is equipped with sensors so it can gather important information about its
surroundings.
It also prevents the robot from taking foolish or unintelligent measures such as stopping a
robot spraying a car if no car is present or stop the spraying operation if the supply of paint
has run out, and so on.
Advantages of using an existing Robot device rather than developing new one:
1. It is more likely to be reliable as it is known that the device will work.
2. It is cheaper than paying full development costs.
3. It is quicker to get into operation as the device has been built.
4. It has lower maintenance costs as faults will be known.
5. It has lower costs for training staff.
19
Use of Robots:
The robots are used in a number of areas. We will now consider the use of robots, together with
the advantages and disadvantages of using robots in each of the following areas:
1. Industry
2. Transport
3. Agriculture
4. Medicine
5. Domestic (home)
6. Entertainment
NOTE: The Robots are used in a number of areas and they have many advantages and
disadvantages in each area accordingly.
However, this makes the list of advantages and disadvantages numerous and it is really
difficult for a student to memorize all of them.
Apart from these, the students should generally memorize 2-3 advantages and disadvantages
which specifically belong to that particular area where robots are used.
20
General/Common Disadvantages of using Robots rather than humans:
21
1) Industry:
Role of Robots:
22
10. If they break down, then they are difficult/impossible to repair and the whole process stops.
11. The abilities of robots are suitable only for simple activities in which no major difficulties are
met.
Advantages to the Company of using Robots rather than humans in car factories:
Disadvantages to the Company of using Robots rather than humans in car factories:
23
6. If a change is made in the process the robot needs to be reprogrammed, which takes time
and increases cost (difficult and expensive to re-program).
7. It is expensive to train staff for operating the robots.
8. The factories can now be moved to anywhere in the world where operation costs are lower,
leading again to unemployment.
9. The robots are not capable of performing tasks autonomously without guidance from
humans and they cannot think for themselves.
10. If they break down, then they are difficult/impossible to repair and the whole process stops.
11. The abilities of robots are suitable only for simple activities in which no major difficulties are
met.
Advantages to the Workers of using Robots rather than humans in car factories:
Effects of using Robots on the job roles and working conditions in a car production factory:
How the use of Robots has affected nature of employment in the car production industry:
1. The introduction of robots has reduced the number of car production factory workers.
2. The vehicle production factories work 24/7 continuously with the use of robots.
3. The workers could be working unsociable hours.
4. The staff become de-skilled as robots reduce the level of skill needed for a job by humans.
5. The use of robots requires an increase in training for the staff.
6. The use of robots has increased the number of supervisors/quality control workers.
7. The use of robots has increased the number of maintenance staff.
8. The use of robots has increased the job sharing/part time jobs.
9. The use of robots has increased the number of staff compressing hours.
10. The use of robots has increased the number of engineers/designers/programmers to build
the robots.
24
(ii) Mining Industry:
The robots are being used in the mining industry to dig up minerals from under the surface
of the Earth.
1. They can replace humans working in a dangerous environment and hazardous conditions.
2. They can work 24/7 continuously and do not need to take breaks.
3. They are less expensive/cheaper in the long run as they reduce running costs, such as wages
and overheads because they don’t get paid.
4. They have a higher/greater productivity than a human.
5. They are more accurate than a human and make fewer mistakes.
6. They can produce consistent standard results/output.
7. They allow humans to do more skilled work/other tasks.
8. The tasks/job can be carried out much quicker/faster.
25
Disadvantages of using Robots rather than humans to do this task:
1. They can work in sterile areas where humans would need protective clothing.
2. They can easily be used for transferring large delicate items.
3. They can work 24/7 continuously and do not need to take breaks.
4. They are less expensive/cheaper in the long run as they reduce running costs, such as wages
and overheads because they don’t get paid.
5. They are more accurate than a human as the lens needs to be precise and higher quality.
6. They ensure better/more frequent checking of the equipment/lens.
7. They do the boring/laborious work.
8. The issues can be found quicker.
9. The tasks/job can be carried out much quicker/faster.
26
(v) Computerized Postal Delivery System:
The robots are used as a computerized postal delivery system.
It drives around the corridors of a set of offices picking up and delivering post.
If the robot is close to a worker, it stops and waits until the worker moves away.
The robots are being used more and more in offices to carry out menial (unskilled) tasks,
like delivering post.
1. They reduce the overall wage bill as there are fewer workers.
2. They have a greater productivity than a human.
3. They are more efficient as they can work all day long.
4. The robot has a set path/route to follow which means that staff know when it is due.
5. The GPS can be used to show where the robot is in the building.
6. They are less expensive/cheaper in the long run as they reduce running costs, such as wages
and overheads because they don’t get paid.
7. They are more accurate and make less mistakes.
8. They allow humans to do more skilled work than delivering post.
9. They can work 24/7 continuously and do not need to take breaks.
27
(vi) Automatic Warehouses:
There is a port which handles a large number of shipping containers.
The containers are automatically transferred between ships, storage areas and lorries at the
port.
The whole system is operated by robots.
28
2) Transport:
(i) Role of Robots in Autonomous Cars & Buses:
1. The autonomous cars use sensors, cameras, actuators, and microprocessors together with
very complex algorithms to carry out their actions safely.
2. The radar and ultrasonics sensors and cameras allow the control systems in car to perform
critical functions by sensing dynamic conditions on a road.
3. The microprocessor processes the data received from cameras and sensors and send signals
to actuators to perform physical actions such as:
1) Change gear
2) Apply the brakes
3) Turn the steering wheel
4. The cameras catch visual data from surroundings, while radar and ultrasonics allow the
vehicle to build up a 3D image of its surroundings.
5. The control system in the car recognizes the road sign and then checks its database as to
what action to take.
1) If the traffic light shows red, the microprocessor sends signal to actuators to apply
brakes and put the gear into ‘park’.
2) It constantly monitors the light until it changes to green.
3) If the traffic light shows green, the microprocessor sends signal to actuators to put the
car into first gear, release the brakes and operate the accelerator (throttle).
4) The microprocessor must constantly check all sensors and cameras to ensure moving off
is safe, for example, if a car in front is broken down or a pedestrian is crossing the road,
and so on.
1. They are safer since human error is removed leading to fewer accidents.
2. They are better for the environment since vehicles will operate more efficiently.
3. They result in reduced traffic congestion.
4. They ensure increased lane capacity due to better braking and acceleration responses
together with optimized distance between vehicles.
5. They result in reduced travel times and therefore less commuting time.
6. They allow stress-free parking for drivers as car will automatically find parking and self-park.
1. They are very expensive system to set up in the first place as high technology requirements.
2. They are always susceptible to cyber hacking of vehicle’s control system.
3. They have security and safety issues as software glitches could be disastrous.
29
4. They have security and safety issues as software updates must be carefully controlled to
avoid potential disaster.
5. They must be well-maintained at all times (cameras need to be kept clean, sensors could fail
to function in environmental conditions).
6. The driver and passenger are reluctant to use this new technology.
7. They reduce the need for taxis which could lead to unemployment of cab drivers.
1. They are a very expensive system to set up in the first place as high capital costs and
operational costs initially for buying trains, signaling & control equipment and staff training.
2. They are always susceptible to cyber hacking of vehicle’s control system.
3. The system does not work well with very busy services.
4. They cannot ensure that the passenger behavior is acceptable particularly during busy times
(jamming doors open on trains or standing too near the edge of platforms and so on).
5. The passengers are reluctant to use this new technology.
6. There will be a need for CCTV to monitor railway stations as there is no driver.
7. They reduce the need for drivers which could lead to unemployment of train drivers.
30
(iii) Role of Robots in Autonomous (unpiloted) Airplanes:
The airplanes use autopilots to control flights and human pilots only take over during take-off and
landing.
1. The autonomous (pilotless) airplanes use sensors, actuators, and microprocessors to control
all stages of the flight.
2. They have sensors to detect turbulence to ensure smooth flights.
3. They have an increase in self-testing of all circuits and systems.
4. They have sensors that automatically detect depressurization in the cabin thus allowing for
quick stabilization of the airplane.
5. They use GPS for navigation and speed calculations.
6. They use actuators to control throttle, flaps (on the wings) and the rudder.
1. They have security issues such as handling terrorist attacks with no pilots on-board.
2. The emergency situations during the flight may be difficult to deal with.
3. They are always susceptible to cyber hacking of vehicle’s control system.
4. The passengers are reluctant to use this new technology.
5. They have security and safety issues as software glitches could be disastrous.
6. They reduce the need for pilots which could lead to unemployment of airplane pilots.
31
3) Agriculture:
Role of Robots:
32
Advantages of using Robots rather than humans:
Weed control:
Phenotyping:
13. They can work automatically without the need for human intervention.
14. They can considerably save labor costs.
15. They can be turned off automatically to save power in case the weather conditions are bad.
33
(i) Automated Farms:
A large farm uses a robotic system to milk and feed animals.
This would recently have been carried out by farm workers.
1. They can work in areas of the farm that could be dangerous/harmful for a farm worker.
2. They are better at ensuring a continuous supply of feed.
3. They are available to milk and feed 24/7 continuously and do not need to take breaks.
4. They are less expensive/cheaper in the long run as they reduce running costs, such as wages
and overheads because they don’t get paid.
5. They have a higher/greater productivity due to cows being milked at times of their choice.
6. They are quicker to see illness in animals due to a system checking a number of factors
against stored values, so is more objective.
7. They have greater consistency as the same measurements are taken on all the animals every
time the robot checks them.
8. They ensure better/more frequent checking of the animals.
9. The robotic tractors can carry out more tasks in a short time.
10. They free up farmers and allow them to do more skilled work.
34
4) Medicine:
Role of Robots:
35
Disadvantages of using Robots rather than humans:
Advantages to the hospital of using Robots rather than humans to do this task:
1. They can work in environments where humans would have difficulty such as cooler
environment and less light.
2. They can work 24/7 continuously and do not need to take breaks.
3. They are less expensive/cheaper in the long run as they reduce running costs, such as wages
and overheads because they don’t get paid.
4. They reduce the overall wage bill as there are fewer workers.
5. They have a higher/greater productivity than a human.
6. They are more accurate and make fewer mistakes.
7. They allow humans to do more skilled work than picking the tablets.
8. They have greater consistency.
Disadvantages to the hospital of using Robots rather than humans to do this task:
36
5) Domestic:
Role of Robots:
37
Disadvantages of using Robots rather than humans:
6) Entertainment:
Role of Robots:
1. The autonomous robots are used in theme parks to entertain visitors to the park.
These robots are often dressed as cartoon characters and can interact with visitors.
2. The robots are used in music festivals for controlling lighting (including laser
displays), visual effects and animation.
This includes superimposing an actor’s image onto a robotic cartoon and synchronizing the
mouth movements.
The visual performances can be fully synchronized with the music.
3. The robots are used to control cameras.
They keep the cameras steady and allows auto-focusing when moving around a scene
during shooting of a movie/show.
They are used to give an actor the appearance of moving around in the vacuum of space
uncontrollably.
The robot arms are used to stimulate human behavior and produce life-like moving images.
4. The humanoid robots (resembling the human body in shape) are used to perform
stunt actions in movies/shows.
They are either remote-controlled or pre-programmed and they can perform stunt actions
tasks that are impossible for a human to do.
They use computer-generated imagery (CGI) and image capture techniques to generate
special effects.
5. The robots are used to produce special effects.
The actions and special effects can be synchronized to within a millisecond and produce
fully coordinated/synchronized sound effects such as movement of the mouth to match the
sounds produced in a realistic manner.
38
Advantages of using Robots rather than humans:
1. They can interact with visitors and allow them to engage safely with theme park attractions.
2. They can make the whole theme park experiences more realistic and fun.
3. They can make music festivals much more immersive for the audience.
4. They can create better shots when used to control cameras during shooting of movie/show.
5. They can perform stunt actions which are dangerous and life threatening for the actors to
perform themselves.
6. They are capable of producing special effects with a precision, speed and coordination
which is beyond human capabilities.
7. They allow synchronization of special effects and actions for producing realistic shots.
Disadvantages of using Robots rather than humans:
39
Exam Style Questions:
Question 1:
Answer:
Question 2:
40
Answer:
Question 3:
Answer:
41
2
Question 4:
Answer:
42
Question 5:
Answer:
43
Question 6:
Answer:
44
Question 7:
Answer:
45
Question 8:
Answer:
46
6 Automated & Emerging Technologies
NOTE: Artificial Intelligence (AI) is a newly added topic in the Computer Science (2210)
syllabus for the session 2023–2025.
6.3.1 Introduction:
Artificial Intelligence (AI) is a branch of computer science dealing with the simulation of
intelligent human behaviors by computers.
It is often referred to as the cognitive functions of the human brain.
Cognitive functioning refers to multiple mental abilities, including learning, thinking,
reasoning, remembering, problem solving, decision making, and attention.
All of these cognitive functions can be replicated in a machine.
1. The collection of data and the rules for using that data.
2. The ability to reason, and the ability to learn and adapt to external stimulation.
Categories of AI:
AI can be split into three categories:
1. Narrow AI:
This occurs when a machine has superior performance to a human when doing one specific
task.
2. General AI:
This occurs when a machine is similar (not superior) in its performance to a human when
doing one specific task.
3. Strong AI:
This occurs when a machine has superior performance to a human in many tasks.
47
Reasoning:
Deductive Reasoning:
Examples of AI:
1. It is used in news generation based on live news feeds.
2. It is used in smart home devices such as Amazon Alexa, Google Now, Apple Siri & Microsoft
Cortana:
3. It is used in chatbots:
The algorithms identify key facial landmarks such as the corners of the eyebrows,
corners of the mouth and so on.
A combination of these landmarks can be used to map emotions such as anger, fear,
joy & surprise.
48
6.3.3 Operation & Components of AI Systems:
There are basic operations and components of AI system to simulate intelligent behavior.
This section considers two types of AI system which are Expert System & Machine Learning.
1) Expert Systems:
They have a knowledge base, a rule base, an inference engine, and an interface.
It mimics the decision-making ability of a human by using AI to simulate judgement and
behavior of a human/organization that has expert knowledge and experience.
2) Machine Learning:
It is when a program has the ability to automatically adapt its own processes and/or data.
It involves training computers with sample data so they can make predictions about new
unseen data based on previously learnt sample data.
They don’t have to be specifically programmed for the new unseen data.
49
1) Expert Systems:
They mimic human knowledge and experiences.
They use human knowledge and inference to solve problems or answer questions which
normally require a human expert.
They basically ask a series of questions to gather knowledge from answers.
Then they provide a conclusion and any suggested actions to take.
They also give the percentage probability of the accuracy of its conclusions.
1. The users of the expert system need considerable training in its use to ensure the system is
being correctly used.
2. They have very high set up and maintenance costs.
3. They tend to give very cold responses that may not be appropriate in certain medical
situations.
4. They are only as good as the information/facts entered into the system.
5. The users sometimes make the very dangerous assumption that they are error-free.
50
Components of an Expert System:
The expert systems are made up of the following components:
It is a method of displaying/outputting results and inputting data through which the expert
system interacts with a user.
This interaction is through dialogue boxes, command prompts or other input methods.
The questions being asked usually only have ‘Yes’ or ‘No’ answers and further questions are
based on previous responses/answers to previous questions.
2) Inference engine:
The inference engine compares data with that held in the knowledge base using rules
base/set of rules until it finds a match for the queries.
It gathers information/data from users by asking a series of questions and applying
responses where necessary and each further question being asked is based on previous
responses.
It solves problems by making use of inference rules in the rules base and examining
knowledge base and then uses information gathered from user to find an object that
matches.
51
3) Knowledge base:
4) Rules base:
IF grade = “A*” AND subject = “Computer Science” THEN teacher = “Haseeb Gilani”
52
Setting-up/Creation of Expert System:
The data is gathered/collected from the human experts or from written sources.
A knowledge base is designed/created from information gathered.
A structure to relate each item in the knowledge base is created.
The rules base is designed/created.
The inference engine is designed/created.
A user interface is designed/created to allow the user and the expert system to
communicate (a method of displaying results/inputting data).
An interrogation technique to access the data is created.
The system is fully tested once it is set up.
It is tested by running the system with known outcomes so results can be compared and
any changes to the expert system made.
NOTE: The working/use of expert system given below consists of statements and keywords in
a sequence which is generally applicable to all type of scenarios. Memorizing the steps given
below will earn you complete marks, but the situation would be changed.
The examiner can give you any scenario and ask the working/use of expert system
accordingly. However, the steps stated below will always be the same; you only need to make
slight changes in answer according to question statement/scenario.
53
Example Questions of Expert System:
NOTE: 4 questions of expert systems are given below with their answers so you can realize
the pattern of answering those questions and learn how to make changes in your answer
according question statement/scenario given.
Q1. How an expert system works in oil prospecting to help decide where to drill for oil. [6]
It uses an interactive user interface which asks questions about geological profile.
The answers to those questions are typed in such as geological profile is typed in.
Further questions are asked based on previous responses.
The expert system analyses the data, and the inference engine compares data.
It compares data with that held in the knowledge base using rules base/set of rules and
then matches are found accordingly.
The system suggests the probabilities of oil being present.
The depths of likely deposits are suggested.
The predictions of geological layer/level above the deposits of oil are output.
Q2. How an expert system can be used to help identify newly discovered type of animal. [4]
Q3. How an expert system can be used to suggest car engine fault diagnoses. [5]
54
Q4. How an expert system can be used to diagnose illness. [5]
55
Exam Style Questions:
Question 1:
Answer:
Question 2:
56
Answer:
Question 3:
1. An expert system may help the doctor make a more accurate diagnosis.
2. An expert system uses data from many experts therefore it contains more knowledge than a
single doctor.
3. It is cheaper than regularly re-training the doctor.
4. The expert system’s knowledge may be more up to data than the knowledge of a single
doctor.
5. It is cheaper than employing many specialists.
6. The diagnoses given are more consistent.
57
Question 4:
Answer:
58
Question 5:
59
Answer:
60
Question 6:
Answer:
61
Question 7:
Answer:
62
2) Machine Learning:
The following is a recap of the AI family:
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/experience.
They can offer fast and accurate outcomes due to very powerful considerable volume of
complex data.
When the user keys in their search criteria into the search engine, the search engine uses
search bots to locate websites matching the user’s search criteria.
If the user selects one of the websites found on Page 1 of the search engines hit, then
search engine classes this as a success (since the relevant pages were found on Page 1).
If the user has to navigate to Pages 2, 3 or 4 to find information they are looking for, then
search engine classes this as a failure (since the relevant pages were not found on Page 1).
The search engine will learn from its past performance and so its ability to carry out
searches becomes more and more sophisticated and accurate with more experience.
63
2) Categorizing email as spam:
A machine learning algorithm collects data about emails, such as email content, headers,
senders name/email address and so on.
It carries out a cleaning process by removing stop words (e.g. the, is, and) and punctuation,
leaving only the relevant data.
The certain words/phrases are frequently used in spam (e.g. lottery, earn, full-refund) and
indicate that the incoming email is very likely to be spam.
The machine learning model is built and a ‘training data set’ is used to train the model and
make it learn using past email known to be spam.
Once it is evaluated, the model is fine-tuned and tested live.
The machine learning establishes a user’s buying characteristics from collaboration filtering,
which is the process of comparing customers who have similar shopping behavior/pattern
to a new customer who has similar shopping behavior/pattern.
The customer ‘A’ is very interested in an activity and bought some items.
The customer ‘B’ who is also very interested in an activity bought some of the same items as
customer ‘A’.
The machine learning algorithms will then recommend that customer ‘B’ might like to buy
some other similar items as ‘A’ due to similarities between ‘A’ and ‘B’ shopping behavior.
This technique is particularly popular when asking your mobile phone to generate a playlist
from your music library based on a few criteria you might select.
The data is gathered by a survey or web scraping, for example, to detect a credit card fraud,
information about customers is gathered, such as types of transactions, shopping habits
and certain personal data. (Data Collection)
The redundant data is then removed carefully so there is no possibility of wrong predictions.
(Data Cleaning)
The machine learning algorithm is trained through real examples of customer purchasing
behavior. (Exploration & Analysis)
A model is built based on learning from the training data, and the machine learning
algorithm can then be used to detect fraud (e.g. if a customer spends an unusual amount
on a piece of jewelry, there is a high chance a fraudulent activity has taken place). (Building
a Model)
The machine learning model is then fully tested with known data and known outcomes and
the system is modified if it hasn’t met its criteria to detect fraudulent activity. (Model
Evaluation)
64
Differences between Artificial Intelligence (AI) & Machine Learning
The following table summarizes the differences between AI and Machine Learning:
65
Sample/Model Exam Style Questions (according to new & updated Syllabus):
NOTE: These questions are not actual examination questions. This new topic is recently
introduced for 2023-2025 session and there are no either past paper questions or specimen
paper questions available for this. These questions are not officially taken from any
Cambridge examination or resource.
The following questions are just sample/model questions which you may expect in your
upcoming examination, and they have been designed for your practice.
Question 1:
66
Possible Answer:
67