7 Expert Systems

• An expert system is a computerized system that attempts to reproduce the decision making process of an expert human being
• An expert system operates by prompting the user to enter certain data using the user interface, referring to the knowledge base and using the inference engine to aid the decision making process it is designed to stimulate
• Expert systems can be used as a diagnostic tool, in financial planning and risk analysis
• Components of an expert system

  USER INTERFACE: this is the way a user interacts with the expert system

  the user interface will guide the user about what data they need to input into the expert system and will then display any output from the expert system
• Examples of the user interface

  using a keyboard

  choosing options by pressing offered choices on a touch screen
• Without the user interface:

  a user would need to know how to program each of the interactions they want to make with the expert system
• The quality of the design of the user interface is very important
• Components of an expert system

  KNOWLEDGE BASE: this is a database of related information about a particular subject
• When an expert system is developed, several experts contribute the knowledge they have of a given field

  this knowledge is then used to build a database that is the knowledge base for the expert system
• In an expert system, 2 types of knowledge is needed

  factual is knowledge that is definitive and widely shared amongst experts in the field

  heuristic knowledge is acquired through personal experiences and built on reasoning
• Part of the knowledge base is

  THE RULES BASE: is a set of rules that will be used to produce an output or decision by the expert system

  these rules are used by the inference engine as a base for reasoning, to obtain a solution to a problem or decision
• In the rules base, each rule contains two parts: IF and THEN
• A rule can have multiple IF parts that will be joined together by Boolean operators such as OR and AND
• Components of an expert system

  INFERENCE ENGINE: this part makes judgements and reasoning using the knowledge base and user responses

  it is designed to produce reasoning based on the rules and the knowledge base
• An inference engine asks the user questions and based on their answer, it will follow a line of logic

  this may lead to further questions and eventually to a final result
• The inference engine is mostly a problem-solving tool
• The 2 main methods that an inference engine can use to stimulate reasoning is backward chaining and forward chaining
• Backward chaining is based on goal driven reasoning. this means that it is dependent on finding a desired goal

  this type of chaining is used when the possible outcomes are limited and definitive in nature
• In backward chaining, the system tries to take a goal and repeatedly split it into sub-goals that are simpler to achieve

  the nature of this type of system is that it moves backward from the goal to be achieved
• Backward chaining


  Sub goals <- Rules <- Goal
• Forward chaining is based on data driven reasoning. this is dependent on the data that it is provided with

  this type of system is used when a problem is more open ended, and the outcome is not necessarily definitive in nature
• In forward chaining, the system will take data input by the user and move forward from rule to rule to suggest a possible outcome

  it will then ask the user for more data and repeat this process until it can suggest an outcome
• Forward chaining


  Data -> Rules -> Outcome
• Components of an expert system


  EXPLANATION SYSTEM: the conclusion or decision an expert system provides may not always make sense to a user which leads to them wanting to gain an understanding of how the conclusion or decision was determined
• Components of an expert system



  METHOD OF OUTPUT: the output method is the method the user will use to view any results produced by the expert system

  this will often be in the form of a display screen that will allow them to see the results on a screen or may include an output such as a printer that allows the results to be printed and viewed
• Advantages of an expert system

  can provide answers to questions that are outside the knowledge you currently have

  can aid professionals by guiding them to look at areas of knowledge they may not have considered or remembered

  are consistent in responses they produce as they are arrived at in a logical way

  can be used at any time - don't need to contact a human at an unsuitable timing

  can arrive at a solution quicker than a human would
• Disadvantages of an expert system

  do not have the intuition that humans have - responses will only be logical

  are only as good as the rules and data they are provided with. error in data = incorrect results

  are expensive to create. many experts need to be consulted and high level of skill is required to build the components parts
• Expert systems are used in:

  medical diagnosis

  car engine fault diagnosis

  digital opponent in chess

  providing financial planning and investment advice

  providing insurance planning advice

  plant and animal identification

  planning and scheduling routes for delivery vehicles