Presentation is loading. Please wait.

Presentation is loading. Please wait.

Survey on Expert System Seung Jun Lee Dept. of Nuclear and Quantum Engineering KAIST Mar 3, 2003.

Similar presentations


Presentation on theme: "Survey on Expert System Seung Jun Lee Dept. of Nuclear and Quantum Engineering KAIST Mar 3, 2003."— Presentation transcript:

1 Survey on Expert System Seung Jun Lee Dept. of Nuclear and Quantum Engineering KAIST Mar 3, 2003

2 Korea Advanced Institute Science and Technology2 What is Expert System? Expert system is an intelligent computer program that uses knowledge and inference procedures to solve problems that are difficult enough to require significant human expertise for their solutions. Expert system is an assembly of computer programs or software to solve problems for a specific field. Expert system uses much knowledge which have high quality Expert System User Knowledge base Inference Engine Fact Expertise

3 Korea Advanced Institute Science and Technology3 What is Expert System? Expert system is a branch of AI system that makes extensive use of specialized knowledge to solve problems at the level of a human expert. AI System Knowledge Base System Expert System

4 Korea Advanced Institute Science and Technology4 What is Expert System? AI (Artificial Intelligence) A study to make computers act intelligently. A study to make computers act like they do in the movies. Intelligence An ability in knowledge acquisition from experiences. A learning and understanding ability. An ability to deal with unexpected or new status.

5 Korea Advanced Institute Science and Technology5 Knowledge used in AI Knowledge is ambiguous and changeable information. Knowledge cannot be described clearly. Knowledge used in AI Consist of rules and facts. Some facts and rules contain certainty factor, because facts and rules are not always expressed ‘TRUE’ or ‘FALSE’ Fact: The light is red. There is a frame. Rule: IF there is a frame with certainty 1.0 THEN there is a fire with certainty 0.7 IF the product was defective with certainty >0.5 THEN the theory of strict liability applies with certainty 1.0

6 Korea Advanced Institute Science and Technology6 Development of expert system Expert System Domain Expert Knowledge Engineer knowledge Policy rule Question Solution Knowledge engineers ask about a specific field to domain experts, and gain knowledge, policies and rules from them. Knowledge engineers develop expert system basis on these knowledge, policies, rules.

7 Korea Advanced Institute Science and Technology7 Development of expert system Relations among domain expert, knowledge engineer, expert system building tool, and user must be considered to develop expert system. Expert System Building tool Expert System User Domain Expert Tool Developer Knowledge Engineer Clerical Staff

8 Korea Advanced Institute Science and Technology8 Advantages of expert system Increased availability: Expertise is available on any suitable computer hardware. In a very real sense, an expert system is the mass production of expertise. Reduced cost: The cost of providing expertise per user is greatly lowered. Reduced danger: Expert systems can be used in environments that might be hazardous for a human. Permanence: The expertise is permanent. Unlike human experts, who may retire, quit, or die, the expert system’s knowledge will last indefinitely. Multiple expertise: The knowledge of multiple experts can be made available to work simultaneously and continuously on a problem at any time of day or night. The level of expertise combined from several experts may exceed that of a single human expert. Increased reliability: Expert systems increase confidence that the correct decision was made by providing a second opinion to a human expert or break a tie in case of disagreements by multiple human experts. Of course, this method probably won’t work of the expert system was programmed by one of the experts. The expert system should always agree with the expert, unless a mistake was made by the expert. However, this may happen if the human expert was tired or under stress.

9 Korea Advanced Institute Science and Technology9 Advantages of expert system Explanation: The expert system can explicitly explain in detail the reasoning that led to a conclusion. A human may be too tired, unwilling, or unable to do this all the time. This increased the confidence that the correct decision is made. Fast response: Fast or real-time response may be necessary for some applications. Depending on the software and hardware used, an expert system may respond faster and be more available than a human expert. Some emergency situations may require responses faster than a human and so a real-time expert system is a good choice. Steady, unemotional, and complete response at all times: this may be very important in real-time and emergency situations, when a human expert may not operate at peak efficiency because of stress of fatigue. Intelligent tutor: The expert system may act as an intelligent tutor by letting the student run sample programs and by explaining the system’s reasoning. Intelligent database: Expert systems can be used to access a database in an intelligent manner.

10 Korea Advanced Institute Science and Technology10 Heuristic method To find wrong records Stature : 70, Weight : 170 Human can easily think that the records are wrong and a smart person can inference that stature record and weight record may be exchanged. It is impossible to memory all rules about common sense knowledge.

11 Korea Advanced Institute Science and Technology11 Heuristic method A solution to find hijackers on an airport Algorithm Investigate all passengers and baggage. Heuristic check passengers and baggage by a metal detector, and investigate them in cases that some troubles are detected. Investigate passengers similar to records of hijacker list. The algorithmic method can certainly prevent hijacking. But it requires too much cost and time and it is impossible method in real. The heuristic method can prevent hijacking in almost cases, but not all cases. But it is efficiency.

12 Korea Advanced Institute Science and Technology12 Heuristic method Many rules used in expert system are heuristic. That is, they are obtained by experiences. Therefore they are not always right but suggest best solutions in almost cases. Responses of an expert system are always consistent. But responses of a human expert can be changed in even same situation according to his condition. For example, an expert can forget important rules in emergency situation. Algorithm: perfect solution Heuristic: best solution

13 Korea Advanced Institute Science and Technology13 The changes of expert system 1 st generation expert system Use rule knowledge expressed by “IF-THEN” statement 2 nd generation expert system Hybrid expert system: Use both rule knowledge and frame knowledge Blackboard expert system Solve problem by consultation of two expert Use two knowledge bases

14 Korea Advanced Institute Science and Technology14 Applications of expert system DENDRAL Developed in 1965 by HPP (Standford univ. research institute) The first expert system. An expert system for chemical molecular structure. MYCIN An expert system for medical diagnosis and advice PROSPECTOR An expert system to find mineral veins In fact, it found a mineral vein which was worth $100,000,000

15 Korea Advanced Institute Science and Technology15 Applications of expert system Fault diagnosis system Operator support system Have knowledge base including operating procedures and various knowledge about NPP operation. Advise operators which part has high failure probability in abnormal operation Emergency operation Operate a plant according to EOP Abnormal operation Diagnose a plant using operator’s knowledge and experiences. Use plant’s plans It take long in many cases to find a defected part from alarms. So, operator support system including an expert system can be efficiently used for abnormal operations.

16 Korea Advanced Institute Science and Technology16 Applications of expert system How can we make knowledge base? From experts’ experiences From documents From learning ability If knowledge base has a learning ability, it can find and generate knowledge from simulations of various operations performed by human operators.

17 Korea Advanced Institute Science and Technology17 Future study Expert system for NPP operating Fault diagnosis system Operator support system in abnormal operating Survey on learning systems


Download ppt "Survey on Expert System Seung Jun Lee Dept. of Nuclear and Quantum Engineering KAIST Mar 3, 2003."

Similar presentations


Ads by Google