• Contribute
• What's New
• Submit News

Introduction

"An expert system is regarded as the embodiment within a computer of a knowledge-based component from an expert skill in such a form that the system can offer intelligent advice or take an intelligent decision about a processing function. A desirable additional characteristic, which many would consider fundamental, is the capability of the system, on demand, to justify its own line of reasoning in a manner directly intelligible to the enquirer."

(The British Computer Society's Specialist Group on Expert Systems (BCS SGES))

The term ``expert system'' refers to a system that uses contemporary computer technology to store and interpret the knowledge and experience of a human expert in a specific area of interest. By accessing this database of knowledge stored in a computer, a non-expert can get the benefit of expert advice in that area.

An expert system is an interactive computer-based decision tool that uses both facts and heuristics to solve difficult decision problems, based on knowledge acquired from an expert.

These statements may give the impression that an expert system is most likely to be inferior to the individual whose expertise was used in developing it, or can at the most be as good as that individual. However, this may not always be the case. For instance, there are chess-playing systems that demonstrate a much higher proficiency in chess than the humans who helped design them. This example shows that it is not fair to characterize a computer-based expert system as necessarily being inferior to a human expert. Of course, expert systems do have some characteristics that distinguish them from other computer-based tools

(The University of Missouri Rolla)

An expert system is Artificial intelligence software that mimics a person problem solving abilities in a specific field.

(¡§Expert system¡¨, by target tech)

An expert system "is a system that uses human knowledge captured in a computer to solve problems that ordinarily require human expertise."

(Turban, E., and J. Aronson.(1988) Decision Support Systems and Intelligent Systems. Upper Saddle River, NJ: Prentice Hall, Inc.)

There are many well known advantages while using the expert system:

1. The principal reasons expert systems are developed to replace a human expert are:

• Make available expertise after hours or in other locations.
• Human expert is expensive.
• Expertise is needed in a hostile environment.

2. The principal reasons expert systems are developed to assist an expert are:

• Aiding expert in some routine task to improve productivity
• Aiding expert in some difficult task to effectively manage the complexities.
• Making available to the expert information that is difficult to recall.

An Expert System is a computer system which emulates the decision-making ability of a human expert.  Books and manuals have a tremendous amount of knowledge but a human has to read and interpret the knowledge for it to be used.  However, the expert systems represent the expertise knowledge as data or rules within the computer.

Regarding to the usability and the important of the computers to the users, and the least number of the expertise in this field, a system called MobES been develop to help the MSI¡¦s motherboard users to recognize, manage and fix the small problems of their own personal computer.  Knowledge of computer troubleshoot was collected from the expert by interviewing them, and also from the motherboard manual book and from the MSI¡¦s website, so that MobES can identify and give a accurate solution to the users.

Problem Statement

Motherboard is the main components of a personal computer (PC), all the PC¡¦s components need to direct link to the motherboard.  From the motherboard we can recognize the problems happen with the PC.  But when things happened, users are requested to access to the vendor¡¦s website to list down their problems and wait for the reply from the staff.

Secondly, the users have to call to the service center to ask for the solution from the technician.  When they are doing so, they will be charge.  Lastly, the users have to refer to the motherboard manual which the users who are without any computer hardware knowledge are hard to understand the terms written in the manual. 

Although the users can have solution from reporting the problems through the website and customer care line, but when the users have further questions like they need to know how the technician recognize such problems happen, and request to have further explanation.  From the two methods users may not get what they need.  But with MobES, systems which have the capabilities of an expert system can easily overcome these kinds of problems and it can provide the solution users need.

Literature Review

As noted by Stylianou, Madey, and Smith (1992), the selection of an adequate Expert System Shell is often the difference between a successful and an unsuccessful industrial application. This observation is just as applicable to instructional uses of Expert Systems Shells as it is to industrial uses of such software packages.

Industrial Technology classes in Computer Integrated Manufacturing, Construction Management, Industrial Maintenance and Supervision, Occupational Health and Safety, and other areas often include computer laboratory exercises or projects based on implementing Decision Support Systems or some other type of Artificial Intelligence applications. These applications are often implemented on Expert System Shells. Some examples of such applications include the works of Koo and Aw (1992) and Roschke (1994) that have described applications of Decision Support Systems to construction management problems. El-Najdawi and Stylianou (1993) and Larsson (1996) have described the use of Decision Support Systems to problems in manufacturing and plant maintenance. Larsson (1996) describes a Decision Support System that uses an Expert System Shell to implement industrial maintenance on sensor systems in a manufacturing setting. Tait and Mehta (1997) give a detailed description of a Decision Support System called WORKBOOK that implements a complete chemical exposure analysis for industrial workplace chemical safety compliance. Xenakis (1990) gives a number of examples of the use of Expert System Shells to managerial/supervisory tasks.

According to two articles by Van Name and Catchings (1990), due to the large number of Expert System Shell packages on the market¡Xand the lack of any standardized nomenclature for describing the features and capabilities of such products¡Xselecting an appropriate package for an application can be very difficult even for experienced users. Head (1992) gives the sage advice to those contemplating the selection of an Expert System Shell to ¡§think big¡¨ but to ¡§start small.¡¨ Current product reviews of Expert System Shells in the software trade literature are of very limited use as they assume that the reader is already familiar with the current version of the shell and the author or authors only provide details of changes and improvements to that shell¡¦s latest version. In order to get details of the basic structure of the shell it is often necessary to go to archival sources like Pallatto (1991), Rasmus (1989), Coleman (1989), Shepherd (1988), who respectively describe the basic functions of first-generation Expert System Shell packages from IBM, Nexpert, Xi-Plus, and Texas Instruments.

Expert systems are computer programs that use artificial intelligence strategies such as symbolic representation, inference, and heuristic search (Buchanan, 1985) to perform sophisticated tasks once thought possible only for human experts. 

Feigenbaum, (1977) stated the expert systems differ from earlier artificial intelligence programs based on general problem-solving strategies such as the General Problem Solver (Newell and Simon, 1963).  In contrast, expert systems are "knowledge-based" systems that rely on domain-specific knowledge.

The basic architecture of an expert system is the inference engine and the knowledge base containing the domain knowledge usually stored in the form of rules.' Another component, called the user interface, which provides a means of communicating with an expert system is also part of the basic architecture.  The relationship between these components is shown in figure 1.

Figure 1: The basic architecture of an expert system

The pie chart shown in figure 2 indicates the distribution of expert system development software tools as used in the UK.' The chart clearly indicates the dominance of shells for expert system development.

Figure 2: Types of Expert System development tools used in the UK

Rice-Crop Expert System

National Institute of Agricultural Extension Management (MANAGE) has developed an expert system to diagnose pests and diseases for rice crop and suggest preventive/curative measures. The rice crop doctor illustrates the use of expert-systems broadly in the area of agriculture and more specifically in the area of rice production through development of a prototype, taking into consideration a few major pests and diseases and some deficiency problems limiting rice yield.

This prototype is a result of joint effort by the experts from NIIT and computer professionals of MANAGES while the subject matter expert knowledge on rice pathology and entomology, has been obtained from Scientists of Andhra Pradesh Agricultural University (APAU), Directorate of Rice Research (DRR).

The brief logic flow of the expert system is as follows:   

1. The part of the plant where symptoms have been the observed is given by the extension officer
2. The basic symptoms are given as input;
3. Considering these symptoms the user is expected to give further information based on other visual symptoms
4. At this step the disease and pest are identified
5. The user is then given the option to either stop or further diagnose and other disease / pest or get preventive or curative measures on these.

Course Inventory Expert System

The Course Inventory Expert System is a logical representation of the decision rules for classifying undergraduate courses, which have been converted to a step-by-step process. The Course Inventory Expert System utilizes a series of decision trees to guide users (i.e., institutional and Regents staff) through the decision-making process. The goal is to achieve consistent treatment of all undergraduate courses across the system based on existing decision rules and policies.

There are four stages in the Course Inventory Expert System. Each stage is designed to narrow the universe of courses under consideration. This "process of elimination" forms the basis for achieving consistent assignments of courses to subject codes and levels among institutions.

• Stage One--courses for which credit is not awarded, courses specifically identified for funding at particular levels, developmental courses, and Transfer Module courses (for technical colleges only)
• Stage Two--courses required for technical degree programs
• Stage Three--courses to which general decision rules apply regardless of field of study, including capstone courses, General Education Requirements, personal enrichment or general interest courses, survey courses, student teaching course, teaching methods courses, calculus-based courses, skill/medium courses, first-year introductory courses, and courses for non-majors only
• Stage Four--courses to which "discipline-specific" decision rules apply

Whale Watcher Expert System

Whale Watcher Expert System is developing by Fisheries and Oceans Canada.  This expert system is not yet fully complete.  Whale watcher is a system that helps users to identify the whale that the users have observed, by answer few questions of the expert system.  The figure 3 below are the interface and some sample of the questions to identify the whale, and the output from the information that the users input.

Question 1:

Question 2:

Question 3:

Question 4:

Output:

Figure 3: Whales Watcher Expert System

Objective

To develop an expert system for MSI¡¦s motherboard users that capable to help them recognize, manage and fix their motherboard¡¦s problem, and provide them with appropriate solution base on the accurate diagnosis. 

Project Significance

MobES is developing to guide and help the MSI¡¦s motherboard users with their PC¡¦s problems.  With this expert system users can easily recognize, manage and fix the basic problems of the pc.  This expert system also will provide simple and understandable solution base on the accurate diagnosis.   Therefore users can get a clear respond at any time when they are needed.

Although MobES is developed in a web based programming language, but users can download it and run as a stand along program on their desktop.  It is very helpful for the users while MobES will generate the user¡¦s input, and give a accurate problem solving to the users, regarding to the result, this system also will give advice to the users so that they know what to do in the next move.

Methodology

The methodology which will be use to ensure the system meet its goals is called Knowledge Engineering, and generally it has the following phases:

Phase 1: Problem Assessment

In this phase, the problems which faced by the users will be identify and assemble, it is to make sure that the data are suitable to be solved by expert system.  It is important that to gather all the information for the previous related project of the Expert System as a reference, identify the requirements, identify the goals and the scope o the project before MobES has been developed.  Failure of the previous project are mostly undefined their goals before they start developing their projects.

Phase 2: Knowledge Acquisition and Analysis

These is a very important phase of the whole system, which an expert system are gathering the knowledge of the expertise and convert directly to the computer version.  Therefore, the sources from the expertise have to be analyzed and make sure all the sources are same as the expertise.

The collection of knowledge for the MobES has done with interviewing those who are experience in the MSI motherboard structure, and collection data from the user manual books and the data from the MSI¡¦s website (refer appendix B).

Analyses on gathered knowledge are important to make sure the accuracy of the data, so that the system can work as same as the expert while giving solution and the advices to the users.

Phase 3: Design and Implementation

This is the phase where to design the Motherboard Expert System (MobES) which included the rules, system programming part and the system interface.  This phase is very important to the system by judging the successfulness of the whole project.  Users will fill bored and disappointed to the system if the system interfaces are not user friendly.

The inference engine works by selecting a rule for testing and then checking if the conditions for that rule are true.  The conditions may be found from questions to the user, or they may be facts already discovered during the consultation.  When the conditions of the rule are found to be true, then the rule conclusion is true.  This conclusion will then be added to the knowledge base or may be displayed via the user interface for information. 

There are many input devices for effective communication between the user and the expert system.  The most common are: mouse, keyboard, light pen, touch-sensitive screen, and voice input, but for MobES, mouse and keyboard are used to answer the question from the expert system.  An expert system user interface will normally take the form of a set of questions, using one or more such input devices, usually followed by some advice from the system.  The expert system user interface will not only enable the user to answer questions, but allow the user to interrupt its operation by asking for explanations (refer appendix A).

Phase 4: Testing

System Testing is crucial as to validate and verify the operations of the system at each stage of the system process.  The test planning is concern with setting out standard for testing process that serve as a guideline for the system developers when they carry out the system testing.

There are few stages of testing have done for the MobES:

Stage 1: Knowledge Acquisition test

In this stage, testing on the accuracy of the knowledge has done to make sure all the knowledge and rules in the system are totally accurate with the knowledge that collected from the expertise.

Stage 2: Structure and Design test

In this stage, the structure of the knowledge and the user interface are been tested to ensure the ability¡¦s of MobES on solving the user¡¦s problems.  Besides that, the test on the system interface also done in this stage, it is to ensure that the users are comfortable with the design.

Stage 3: Full Prototype test

In this stage, testing of the whole system been done to ensure it reach the goals, where it will provide solution and advice to the users so that the users can handle their own computer problems.

Phase 5: Documentation

Documentation is the phase that to documented all the reports which will consist of the whole process of the MobES development, as well as the elements involve. A well documentation will give guide to the users and the programmers, so that it is easier to make any adjustment or correction on the system in future. 

Phase 6: Maintenance

The last phase of the project is the system maintenance.  This is the phase that to maintained and to make sure that the system is working properly.  The system may have to be updated from time to time, depends on the changes of the knowledge sources.

Scopes and Limitation

Scope

The functions of the MobES are:

• To figure out the main problems of the MSI¡¦s motherboard.
• To give solution regarding to the accurate diagnosis.

Limitation

This Motherboard Expert System is still under development, so it has limited knowledge and solutions about the MSI¡¦s motherboard, such as sound card, monitor and display, mouse and keyboard, BIOS setting and other PC problems.  MobES should collect more knowledge so that more rules can create and to have a better service for the users.

Conclusion

To develop MobES, it not only has to go through the basic steps and phases of software development method, it also needs the support from the expert in the knowledge acquisitions part.  In developing an expert system, user interface and programming skills are very important, but the most important part is the knowledge from the expertise.  To collect the knowledge, we can interview the expert, observe their response when dealing with the users, and lastly is collect the knowledge from the printed hard copy, like books, or user manual.

MobES actually is still under development status, and it still need time and support from the expert to reach it goals.

In future, MobES may be able to apply with other methods of Artificial Intelligence like artificial neural networks, fuzzy logic and genetic algorithms to improve the design of the system so that it can provide more accurate results to the users.

References

• Alberico, Ralph. (1990). AI/expert systems: The library connection. In Nancy Melin Nelson (Ed.), Technology for the '90s: Microcomputers in Libraries (pp. 65-95). Westport, CT: Meckler. 
• An Intelligent Strategy Discriminator for an Automated Guided Vehicle System, Ruby D. Lathon, Master's Thesis, University of Alabama in Huntsville, 1995.
• http://whatis.techtarget/definition/0,,sid9_gci212087,00.html
• http://www.aiinc.ca/demos/whale.html
• Keith Darlington MSc, MBCS.The Knowledge Based Systems Centre, SCISM, South Bank University, 103 Borough Rd., London SE1 0AA (http://www.scism.sbu.ac.uk/~darlink)
• G2 - Gensym Intelligent Systems Software Products, (http://www.gensym.com)
• Charles K Mann, Stephen R.Ruth, (1992). Expert System in Developing Countries Practice and promise.
• Richard E. Plant, Nicholas D. Stave McGraw-Hill (1991). Knowledge based systems in Agriculture
• R. L. Hoskinson, J. R. Hess, R. K. Fink. A Decision Support System for Optimum Use of Fertilizers
• A. Keyton Weissinger (1999). ASP in A Nutshell. United States of America O¡¦Reilly & Associates, Inc.
• J. Kauffman (1999). ASP Databases. Birmingham Wrox Press Ltd.
• H.M. Deitel, P.J. Deitel, T.R. Neito (2002).Internet & World Wide Web: How to Program. Upper Saddle River, New Jersey Prentice Hall.