6.8 : Expert systems

Question 1

what is the definition of an expert system ?

Answer 1

expert systems are computer software that are designed to mimic (copy) the expertise and knowledge of a human expert in different field and subjects.

Question 2

what are the different examples of an expert system ?

Answer 2

• prospecting for oils and minerals
• diagnostics ( engine faults and faults on a circuit board )
• medical diagnostics
• strategy games ( chess)
• tax and financial planning
• route Scheduling for delivery vehicles
• identification of plants , animals , and chemical compounds

Question 3

what are the general information about expert systems ?

Answer 3

• expert systems are often used to advice non-experts in situations where a human expert in unavailable.
• they all tend to work in the same way
• someone comes along and asks them advice about a problem within their specialty.
• the expert asks a number of questions to help them formulate an answer
• the dialogue continues until the expert can offer one or more solutions to the problem
• expert systems are a form of artificial intelligence
• the first expert system was created in the 1970s

Question 4

what are the advantages of an expert system ?

Answer 4

• 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 offer an unbiased reports and analysis of the facts
• they indicate a probability of any suggested solution to being correct
• they never forget to answer a question when determining the logic
• using expert systems reduces the time taken to solve a problem

Question 5

Disadvantages of expert systems ?

Answer 5

• users of the expert system need considerable training to ensure that the system is being used correctly
• the set-up and maintenance are very high
• they tend to give very cold responses which may not be appropriate in certain medical situations
• the system is only as good as the information/facts entered into the system
• errors in the knowledge base can lead to incorrect decisions being made.

Question 6

Explain the user interface ?

Answer 6

• this is the method by which the expert system to interact with a user
• it allows interactions through dialogue boxes, command prompts or other input methods
• the question being asked usually only has a yes / no answer and is based on responses to previous questions
• the user-interface is designed to be simple to use

Question 7

Explain the inference engine ?

Answer 7

this acts like a search engine , examining the knowledge base for information that matches the user’s query

• this is the main processing element of the expert system
• the inference engine acts like a search engine by examining the knowledge base for information / data that matches the queries
• it is responsible for gathering information from the user by asking a series of questions and applying responses where necessary , each question being asked is based on the previous response
• the inference engine is the problem-solving part of the expert system , which makes use of the inference rules in the rules base
• because the knowledge base is a collection of objects and attributes , the inference engine attempts to use the information gathered from the user to find an object that matches

Question 8

Explain what is the knowledge base ?

Answer 8

this is a collection of facts and rules , the knowledge base is created from information given by a human experts , it is used to provide a diagnosis or a set of recommendations.

• the knowledge base is a repository of facts
• it stores all knowledge about an area of expertise obtained from a number of expert resources
• it basically a collection of objects and their attributes

Question 9

Explain the rules base ?

Answer 9

• The rules base is a set of inference rules
• they are used by the inference engine to draw conclusions
• they follow logical thinking , usually involving a series of IF statements.

Question 10

Explain the explanation system ?

Answer 10

• this informs the user of the reasoning behind the expert system’s conclusion and recommended action
• and it also gives recommended action and the probability of the accuracy of its conclusion.

Question 11

how to set-up an expert system ?

Answer 11

• first information needs to be gathered from written sources such as textbooks , research papers and the internet
• then the information gathered is used to populate the knowledge base , which first needs to be created
• a rule base needs to be created , this is made of a set of instructions followed by the inference engine so it can draw conclusions
• the inference engine itself needs to be set-up , it is a complex engine since it is the main processing element , making reasoned conclusions from the data in the knowledge base
• they user interface system needs to be developed so the system and the user can communicate
• once the system is set-up , it needs to be tested by asking the system about a condition with known outcomes and so it can be compared and any changes are made to the system
  ]

Question 12

what are the three examples of expert systems ?

Answer 12

• medical diagnosis
• route scheduling for delivery vehicles
• oil prospecting

Question 13

how does the medical diagnosis expert system work ?

Answer 13

Input screen :

• first of all an interactive screen is presented to the user
• then the patient is asked questions about their illness
• the user will answer these question with a yes/no answers
• a series of questions are asked and they are based on the user’s response to the previous questions

Expert system processing :

• the inference engine will use the data that the user has entered to look for possible matches in the knowledge base
• the rules base is also used in the process
• once the match has been found the system will give a probability of how accurate the diagnosis wase
• the system will also give possible solution and remedies and recommendations on what to do next
• the system will also include reasons on why has the system gave this diagnosis so that the user can validate the symptoms or suggested treatments

output screen :
the diagnosis may be shown as text or images of the human anatomy to show where the symptoms may be
- the user may request further information from the expert system to narrow down the possible illness and tis treatment

Question 14

how does an oil prospecting expert system work ?

Answer 14

• an interactive screen asks questions ( either yes/no questions or multiple choice )
• questions are asked about geological profiles
• answers to question are typed by the operator
• the inference engine accesses the knowledge base using the rules base
• the system suggests the probability of finding oil deposits as an output
• it also indicates the probabilty of the depth of deposits ( %)
• the explanation system explains why did it come to theses conclusions
• it makes predictions about geolgical deposits above the soil
• it produces contour maps showing the concentration of minerals , rocks, oil etc.

Question 15

why is an expert system used for scheduling delivery trucks ?

Answer 15

• the fastest and cheapest route and the number of vehicles and drivers that should be used

Question 16

what are the inputs required for the route scheduling expert sytem?

Answer 16

• the number of drop-off points and their location
• the distance between the drop-off poutns
• the distance between the drop-off points
• the type vehicles used
• delivery times expected at each drop-off locations
• layout of the road network