You are on page 1of 11

LECTURE NO: 7 EXPERT SYSTEM WHAT IS AN EXPERT? They possess specialized knowledge in a certain area.

. They possess experience in the given area. They can provide, upon elicitation, an explanation of their decisions. They have a skill set that enables them to translate the specialized knowledge gained through experience into solutions. EXPERT SYSTEM . An Expert system (ES) is A computer program designed to model the problem solving ability of a human expert. . An Expert system is an artificial intelligence program incorporating a knowledge base and an inferencing system. . ES is a highly specialized piece of software that attempts to duplicate the function of an expert in some field of expertise. . The program acts as an intelligent consultant or advisor in the domain of interest, capturing the knowledge of one or more experts. . Non-experts can then tap the expert system to answer questions, solve problems, and make decisions in the domain. FAMOUS EXPERT SYSTEMS MYCIN Designed by Edward Shortliffe of the Atandford University in the mid 1970s. A medical expert system that diagnoses bacterial infections and recommends antibiotic therapy. How it work..? The physician sits down at the computer and enters the patients age and medical history, results of laboratory tests, and any additional relevant information. With this information plus its knowledge of the domain, MYCIN attempts to diagnose the cause of the infection. Then it recommends the type of drug and the dosage that might be used to cure the infection. It was not intended to replace a physician. It can assist physicians who have little practical experience with specific infections or diseases involded. It is also designed to help physicians check their diagnoses and therapy recommendations against those of a known expert or experts involved in creating the system.

The final decision on treatment is the responsibility of the physician DENDRAL (1960s) A product of researchers at Standford University. Using its knowledge of molecular structures and chemistry, DENDRAL attempts to identify the molecular structure of unknown compounds. Giving the mass spectral data, molecular structures were determined. In the laboratory, the generate and test method was used. Possible hypothesis about molecular structures were generated and tested by matching to actual data. XCON Also kown as RI. It helps configure large computer systems. Developed jointly by Digital Equipment Corporation (DEC) and researchers at Carnegie Mellon University (CMU). Xcon helps translate a customers order for a DEC VAX !!/&* series computer system into complete specifications. Large systems like VAX are made up of hundereds of different components that can be mixed and matched to produce the exact configuration required by the customers.in additond there are thousands of ways in which these items may be assembled into useful configurations. Days or weeks are spent in identifying all of the parts needed to assemble a system to meet customers specifications. Xcon does it in minutes. It was one of the most successful expert systems in routine use, bringing an estimated savings of $25 million per year to DEC. Prospector Help geologists locate ore deposits. Its knowledge base contains rules and heuristic data derived from empirical data. It also contains taxonomy of various kinds of minerals and rocks.

Many geologists were interviewed and their expertise with particular types of ore deposits was captured. Working of Prospector: The geologists searching for an ore deposit provide input information about a particular geological area, going into the field to observe the terrain and collect whatever evidence exists. Relevant geological features are noted and soil and rock samples are collected. Given this information, the ES can evaluate the area in question and determine whether the potential exists for a particular kind of ore. Prospector gives a recommendation that indicates how particular site might be for further exploration or drilling. EL This expert system analyses electronic circuits made up of transistors, diodes and resisters. A schematic diagram of the circuit is entered into the computer and EL performs a steady state analysis of it. The ES works through the circuit and determines the characteristics of the circuit as well as the value of voltages and currents at all points in the circuit. ELs knowledge base contains general principles of electronics, such as Ohms Law, component characteristics and theory of transistors operations. It is an excellent tool for assisting the design engineer. Problems can be spotted quickly and design changes cab be made to achieve the desired circuit characteristic. Can also be used as an aid in learning electronic circuit operation and design. Assignment Expert systems XSEL SOPHIE

DELTA FOLIO First like many other traditional forms of software, expert system offer some of the following advantages: Permit non-experts to do the work of experts. Improve productivity by increasing work output by improving efficiency. Saves time in accomplishing a specific objective. Simplify some operations. Automate repetitive, tedious, or overly complex processes. Second, some ES offer some additional benefits over conventional s/w. such as: Permit new kinds of problems to be solved thereby making the computer more useful. Capture and store valuable knowledge that might be lost due to the resignation, retirement, or death of an expert. Make expert knowledge available to a wider audience, thus increasing the problem solving ability of more people.

Development of Es is extremely difficult, more difficult than creating more conventional s/w. good experts are hard to find. Extracting their knowledge is a long, tedious job and coding that knowledge into s/w is a major chore. Expert systems are expensive. It costs a lot to develop one, test it, and deliver it to the end user. Most ES still must be implemented and delivered on a big mainframe or minicomputers. ES can be developed and used on the personal computers, of course. But these are smaller, less sophisticated, and often less useful systems. The memory size and speed of a personal computer limits its usefulness. ES are not 100% reliable. Even with best experts contributing to their design, expert system arent perfect. For that reason, their output recommendation must be weighted, tested. A human being should always provide the final judgment. There are two basic types of Expert systems: The stand-alone system The embedded type

Stand-Alone This is a software package that runs on a personal computer, minicomputer, or mainframe. While the computer is running that program, it is totally dedicated to it. It stand alone in that application. Embedded Here ES is just a portion of another larger program. The program may use conventional algorithmic techniques but access the expert system as a subroutine when a particular type of information is required. In another form of embedded system, an algorithmic program such as a mathematical subroutine is built into an expert system. During the reasoning or inferencing process, the expert system may need the subroutine to perform a mathematical operation. Links to Other Software Es that links to an external software package such as spreadsheet, data base management system (DBMS), or graphics program. During the inferencing process, the ES may reach out and access data in the spreadsheet or DBMS to get enough knowledge to reach a solution. On the graphics program may be called upon to display a visual output. While these programs are not really embedded, the effect is the same. They usually share memory with the ES and have program links to it. Dedicated Systems Another kind of embedded system is the closed or dedicated system. Here the ES is part of a special purpose computer dedicated to a single function. It may help analyze radar data in a fighter aircraft or make an intelligent decision about how to modify the process in a chemical plant. Regardless of the application, this kind of embedded system usually combines an ES with conventional s/w to deal with a single or very narrow application.

The main people involved in an ES development project are Domain expert The knowledge engineer The end user Domain Expert A domain expert is A person who posses the skill and knowledge to solve a specific problem in a manner superior to others (Durkin) An expert should have expert knowledge in the given domain, good communication skills, availability and readiness to co-operate. Knowledge Engineer A knowledge engineer is a person who designs, builds and tests an Expert System. (Durkin) A knowledge engineer plays a key role in identifying, acquiring and encoding knowledge. End-User The end user are the people who will use the Expert System. Correctness, usability and clarity are important ES features for an end user. An Es consists of the following components: Knowledge base Working memory Inference engine User interface Knowledge Base The knowledge base is the part of an ES that contains the domain knowledge, i.e Problem facts, rules Concepts Relationships The power of an ES lies to a large extent in its richness of knowledge. As a knowledge engineer, the designer must overcome the knowledge acquisition bottleneck and find an effective way to get information from the expert and encode it in the knowledge base. Working memory The working memory is the part of the expert system that contains the problem facts that are discovered during the session according to Durkin.

One session in the working memory corresponds to one consultation. During a consultation: User presents some facts about the situation. These are stored in the working memory. Using these and knowledge stored in the knowledge base, new information is inferred and also added to the working memory. Inference Engine The inference engine can be viewed as the processor in an ES that matches the facts contained in the working memory with the domain knowledge contained in the knowledge base, to draw conclusions about the problem. If the knowledge of an ES is represented in the form of IF-THEN rules, the Inference Engine has the following strategy: Match given facts in working memory to the premises of the rules in the knowledge base. If match found, fire the conclusion of the rule i.e add the conclusion to the working memory. Do this repeatedly, while new facts can be added, until you come up with the desired conclusion. Assignment Forward chaining and Backward chaining in Inference mechanism of ES User Interface This is a piece of software that lets the user communicate with the system. The user interface asks questions or presents menu choices or entering initial information in the data base. Expert systems may be used application areas including Diagnosis interpretation prescription design planning control instruction prediction and

simulation Control applications Used to adaptively govern/regulate the behavior of a system, e.g. controlling a manufacturing process, or medical treatment. The ES obtains data about current system state, reasons, predicts future system states and recommend (or executes) adjustments accordingly. Design Used for design applications to configure objects under given design constraints, e.g. XCON. Diagnosis And Prescription An ES can serve to identify system malfunction points. To do this it must have knowledge of possible faults as well as diagnosis methodology extracted from technical experts . E.g. diagnosis based patients symptoms, diagnosing malfunctioning electronic structures. Most diagnosis ES have a prescription subsystem. Such systems are usually interactive, building on user information to narrow down diagnosis. Instruction and Simulation ES may be used to guide the instruction of a student in some topic. Tutoring applications include GUIDON (Clancey 1979), which instructs students in diagnosis of bacterial infections. Its strategy is to present user with cases (of which it has solution). It then analyzes the students response. It compares the students approach to its own and directs students based on differences. Interpretation Interpretation is Producing an understanding of situation from given information. An example of a system that provides interpretation is FXAA (1998). This ES provides financial assistance for a commercial bank.

It looks at a large number of transactions and identifies irregularities in transaction trends. Planning and Prediction ES may be used for planning applications, e.g. recommending steps for a robot to carry out certain steps, cash management planning. SMARTPlan is such a system, a strategic market planning expert (Beeral 1993). It suggests appropriate marketing strategy required to achieve economic success. Similarly prediction systems infer likely consequences from a given situation. Ten basic steps in creating an ES Identify the problem Your first step in developing an expert system should be to examine your situation and clearly decide what the problem is or why such a system may be helpful. Determine the suitability of the problem Once the problem is clearly identified, you can then examine it in more detail to see if it is right for an expert system solution. Although you may be excited about the concept of ES and are looking for a way to apply them to your own work, keep in mind that only certain types of problems can successfully solved with an ES. Consider the Alternatives Although your problem may fit the criterion for an ES, dont overlook what might be simpler or equally as satisfactory alternative solutions. A non-computer solution may be not only the best solution, but also the simplest and least expensive. Consider the software alternatives. A DBMS software package might better fit the problem than an expert system. The ability of the computer to reason may not be necessary!!!! Finally, dont overlook a conventional software solution. A straightforward algorithmic solution might be better than AI solution. Having now looked at the alternatives, you can make your final decision. If an ES is your choice, then you can begin the next steps. Compute the ROI Next step is to determine whether or not it is economically feasible. You must compute the return on your investment (ROI) by performing a cost/benefit analysis.

This will help you estimate the cost of creating the ES and determine whether its cost can be justified in terms of savings or other benefits it produces. Select a Development tool An ES development tool is a software package that allows you to enter an experts knowledge into the computer without having to program. Most ES development tools are rule based. Some permit the implementation of frames and semantic networks, but they are usually more expensive and generally operate only on the large computers. Your next job is to identify the available tools and choose one that fits your needs. Perform the Knowledge Engineering At this point in the development process, you are finally ready to do some real creative work. Development of ES begins with knowledge engineering, that is, acquiring the knowledge. The format of the knowledge will guide you in selecting a particular knowledge representation scheme. Design the System Using the knowledge you have acquired and tool you have selected, you can now begin the design of the ES. First you will need to create an outline, a hierarchal flow chart, a matrix, decision table, or other format that will help you organize and understand the knowledge. Using these aids, you will convert the knowledge into IF-THEN rules. Once the basic design is complete, you can begin using the tool to create a prototype of one segment of the system. Translate a portion of the knowledge into rules and test the newly created segment. Your job here is to test the concept before going ahead with the entire program. Complete the Development

Once you have satisfied yourself that system is going to work satisfactorily, you can begin to expand the prototype into the final system. The best way to go about this is to expand the prototype one segment at a time. Typically, the knowledge will divide itself conveniently into logical chunks, each with a block of rules. Test each new segment as it is added to see that it works with the original prototype. In this way you will make good progress, and end up with a final workable system without major bugs. Test and Debug the System After the ES has been developed, you will need to spend some time testing and debugging it. No ES will be perfect the first time, and a considerable amount of work will be required to validate it. Take your ES to the field and try it out on its intended users. User feedback will show you where to make final changes, corrections, and addition to achieve the desired performance. Maintain the System An important part of expert system development is ongoing maintenance, updating the system with new knowledge, removing knowledge that is no longer applicable, and otherwise fine tuning the system to keep it fully current and applicable to the problem. Dont overlook this vital step, if your system is not periodically updated, it will quickly become worthless and your investment in its development will be wasted. Be sure your ROI calculations take this into consideration. The end

You might also like