Introduction to Expert Systems Session 1 Course : T0273 EXPERT SYSTEMS Year : 2016 Introduction to Expert Systems Session 1

Learning Outcomes After taking this course, students should be able to explain and discuss the importance of Expert Systems. Bina Nusantara University

Lecture Outline What is an Expert System Advantages of Expert Systems State of the Art Characteristics of An Expert System Application of the Expert Systems Elements of the Expert Systems Bina Nusantara University

Lecturer Dr. Widodo Budiharto HP: 08569887384 Email:wbudiharto@binus.edu Quiz 3x, TM dan Final project di sessi 13 Bina Nusantara University

Introduction https://www.youtube.com/watch?v=cf6xSx2d6ts Bina Nusantara University

What is An Expert System The earliest popular definition of AI is : “Making computers think like people” Expert systems were developed as research tools in the 1960s as a special type of AI to successfully deal with complex problem sin a narrow domain such as medical disease diagnosis. An expert system is a computer system that emulates, or acts in all respects, with the decision-making capabilities of a human expert. Bina Nusantara University

AI Prehistory Philosophy Logic, methods of reasoning, mind as physical system foundations of learning, language, rationality Mathematics Formal representation and proof algorithms, computation, (un)decidability, (in)tractability, probability Economics utility, decision theory Neuroscience physical substrate for mental activity Psychology phenomena of perception and motor control, experimental techniques Computer building fast computers engineering Control theory design systems that maximize an objective function over time Linguistics knowledge representation, grammar Bina Nusantara University

History of AI 1943 McCulloch & Pitts: Boolean circuit model of brain 1950 Turing's "Computing Machinery and Intelligence" 1956 Dartmouth meeting: "Artificial Intelligence" adopted 1952—69 Look, Ma, no hands! 1950s Early AI programs, including Samuel's checkers program, Newell & Simon's Logic Theorist, Gelernter's Geometry Engine 1965 Robinson's complete algorithm for logical reasoning 1966—73 AI discovers computational complexity Neural network research almost disappears 1969—79 Early development of knowledge-based systems 1980-- AI becomes an industry 1986-- Neural networks return to popularity 1987-- AI becomes a science 1995-- The emergence of intelligent agents Bina Nusantara University

State of the Art Deep Blue defeated the reigning world chess champion Garry Kasparov in 1997 Proved a mathematical conjecture (Robbins conjecture) unsolved for decades No hands across America (driving autonomously 98% of the time from Pittsburgh to San Diego) During the 1991 Gulf War, US forces deployed an AI logistics planning and scheduling program that involved up to 50,000 vehicles, cargo, and people NASA's on-board autonomous planning program controlled the scheduling of operations for a spacecraft Proverb solves crossword puzzles better than most humans Bina Nusantara University

USER Basic Function of an ES The knowledge in expert systems (ES) may be either expertise, or knowledge that is generally available from books, magazines and knowledgeable persons. Facts Expertise KNOWLEDGE-BASED USER INFERENCE ENGINE Bina Nusantara University

Advantages of ES Increased availability Reduced cost Reduced danger Permanence Multiple expertise Increased reliability Explanation Fast response Intelligent tutor Bina Nusantara University

Bina Nusantara University

Bina Nusantara University

Characteristics of an ES High performance Adequate response time Good reliability Understandable Flexibility Bina Nusantara University

General concepts The knowledge of an expert system may be represented in a number of ways. One common method of representing knowledge is in the form of IF THEN type rules, such as : IF the car doesn’t run and The fuel gauge reads empty THEN fill the gas tank Bina Nusantara University

Interpret a protein’s 3D structure Interpret molecular structure Applications Interpret a protein’s 3D structure Interpret molecular structure Diagnose telephone network faults Diagnose lug disease Diagnose blood disease Instruct in bacterial infection Diagnose/remedy drilling problems Diagnose bad parts in switching net. Bina Nusantara University

Elements of an Expert System User Interface Explanation facility Working memory Inference engine Agenda Knowledge acquisition facility Bina Nusantara University

Inference Engine Makes inferences by deciding which rules are satisfied by facts or objects. Prioritizes the satisfied rules, and executes the rule with the highest priority Merupakan otak dari sistem pakar, berupa perangkat lunak yang melakukan tugas inferensi pelanaran sistem pakar Bina Nusantara University

Knowledge acquisition facility An automatic way for the user to enter knowledge in the system rather than by having the knowledge engineer explicitly code the knowledge Bina Nusantara University

Working Memory A global database of facts used by the rules Menyimpan fakta yang diperoleh saat dilakukan proses konsultasi Fakta fakta ini akan diolah oleh mesin inferensi berdasar pengetahuan yang disimpan di dalam basis pengetahuan untuk menentukan suatu keputusan pemecahan masalah Bina Nusantara University

Agenda A prioritized list of rules created by the inference engine, whose patterns are satisfied by facts or objects in working memory Bina Nusantara University

Examples of expert system applications, such as : Loan evaluators and technical support systems Farm Advisory System Intelligent Tutoring systems (ITS) : Bina Nusantara University

example Bina Nusantara University

MYCIN – Medical Diagnosis ES Diagnosis of meningitis and bacteremia Bina Nusantara University

Aplikasi Android ES Bina Nusantara University

1. Gather information from experts. 2. Create the knowledge base. Exercise An expert system is being developed to help engineers diagnose faults in aero engines. Describe the steps taken to develop this new expert . ANSWER: 1. Gather information from experts. 2. Create the knowledge base. 3. type/put information into computer . 4. Create rules / rules base. 5. Create / design inference engine. 6. Fully test the system. Bina Nusantara University

Summary The problem that expert systems are used to solve are generally not solvable by conventional program. The advantages and disadvantages of expert systems were also discussed in the context of selecting an appropriate problem domain for an expert systems application. The essentials of an expert system shell were discussed with reference to rule-based expert systems. Bina Nusantara University

References Textbooks: Joseph Giarratano, Gary Riley,. 2005. Expert systems : principles and programming. THOCO. Australia. ISBN:0-534-38447-1 Stuart Russell Peter Norvig. 2010. Artificial Intelligence, A Modern Approach. PE. New Jersey. ISBN:978-0-13-207148-2 Web : www.widodo.com Bina Nusantara University