• Contribute
• What's New
• Submit News

Introduction

An expert system is a computer program conceived to simulate some forms of human reasoning (by the intermediary of an inference engine) and capable to manage an important quantity of specialized knowledge.

A system that uses human knowledge captured in a computer to solve problems that ordinarily require human expertise (Turban & Aronson, 2001).

A computer program designed to model the problem solving ability of a human expert (Durkin, 1994).

An intelligent computer program that uses knowledge and inference procedures to solve problems that was difficult enough to acquire significant human expertise for their solutions (Feigenbaum).

An expert system is a computer application that solves complicated problems that would otherwise require extensive human expertise. To do so, it simulates the human reasoning process by applying specific knowledge and interfaces. This report explained on the expert system for decision making of giving the best solution to solve the PDA’s (Personal Digital Assistant) problems.

These capacities for reasoning and management allow the system to target a small number of relevant hypotheses in the mass of potential diagnoses and being able to find a satisfactory diagnostic conclusion. Two characteristics of the expert system are essential to accomplish this task:

• the aptitude to process an important mass of specialized knowledge and
• the aptitude to simulate the human reasoning (in an imperfect manner).

There are many well known advantages to using computerised tools and expert systems:

• reduction of missing data,
• better collection of data,
• no omission of questions,
• no data transcription,
• broader coverage of diagnoses

The idea to develop this system has arises base on the capabilities and the potential of the expert system as described above.  It can be use mainly for giving appropriate countermeasures according to the accurate and consistent diagnosis of PDA’s (Personal Digital Assistant) troubleshoots.  It is called PDAMum.

PDAMum is essential since the emergence of handheld devices, and now it is rapidly owned by various levels of peoples, there is somehow a need of a system that able to help them to manage their devices whenever necessary.  PDAMum is making its decision during the interview, looking for the optimal way to reach their conclusions: to make a diagnosis.

Problem Statement

Recently, there are various brands of PDA (Personal Digital Assistant).  Each of the brands HP, Sony, Palm and Xda produced by specific vendor.  Every vendor have their own website and users have to access to the respective website whenever they need any explanation or solution regarding their handheld problem.

Users are also able to get the advice through their care line.  But this will cost them a lot since they need to explain everything during the phone session and wait for the response from the technician.  Sometimes the given solution also not fulfilled the condition needs. Reporting through website and phone seldom create another problem to the user.  User preferred to say yes or no rather than give the entire explanation.  But the two methods above require sufficient details to response towards the problem.  PDAMumwith it’s capabilities as expert system will absolutely overcome these problems.

Literature Review

An expert system is a computer program designed to simulate the problem-solving behavior of a human who is an expert in a narrow domain or discipline.  An expert system is normally composed of a knowledge base (information, heuristics, etc.), inference engine (analyzes the knowledge base), and the end user interface (accepting inputs, generating outputs).

The path that leads to the development of expert systems is different from that of conventional programming techniques.  The concepts for expert system development come from the subject domain of artificial intelligence (AI), and require a departure from conventional computing practices and programming techniques.  A conventional program consists of an algorithmic process to reach a specific result.  An AI program is made up of a knowledge base and a procedure to infer an answer. 

Expert systems are capable of delivering quantitative information, much of which has been developed through basic and applied research (e.g. economic thresholds, crop development models, pest population models) as well as heuristics to interpret qualitatively derived values, or for use in lieu of quantitative information.  Another feature is that these systems can address imprecise and incomplete data through the assignment of confidence values to inputs and conclusions.

One of the most powerful attributes of expert systems is the ability to explain reasoning.  Since the system remembers its logical chain of reasoning, a user may ask for an explanation of a recommendation and the system will display the factors it considered in providing a particular recommendation.  This attribute enhances user confidence in the recommendation and acceptance of the expert system.

Basri (1999) noticed that an expert system attempts to emulate how a human expert solves a problem, mostly by the manipulation of symbols instead of numbers. Whereas conventional algorithmic programming replaced most of the sophisticated, analytical work of engineers, expert systems are especially suitable for the no-less important tasks of the ill-structured and less deterministic parts of planning and design.

Whereas Yang and Okrent (1991), stated that expert systems are cheaper compared to human experts in the long-term scenario.  However, expert systems are relatively costly to develop but easy and cheap to operate. In addition, expert systems allow automation of many tasks that could not be effectively handled by human experts.

Below are some diagrams that show the basis how an expert system works.

Figure 1: Major parts of an expert system

Figure 2: Typical knowledge acquisition processes for building an expert system

Expert systems should be viewed as a particular type of information system. Expert systems are distinct in terms of their approach to problem representation, as information systems process information, while expert systems attempt to process knowledge.  Knowledge in an expert system may originate from many sources, such as textbooks, reports, databases, case studies, empirical data, and personal experience. The dominant source of knowledge in today's expert systems is the dominant expert. A knowledge engineer usually obtains knowledge through direct interaction with the expert.

Figure 3: Expert System and User Interaction

In the expert system there are widely use in many application areas. There are few type of problem solving paradigm such as control, design, diagnosis, instruction, interpretation, monitoring, planning, prediction, prescription, selection and simulation.

Agricultural Expert systems

Rice-Crop Doctor

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.

The following diseases and pests have been included in the system for identification and suggesting preventive and curative measures. The diseases included are rice blast, brown spots, sheath blight, rice and zinc deficiency disease. The pests included are stem borers, rice gall midge, brown plant hopper, rice leaf folder, green leaf hopper and Gundhi bug.

Farm Advisory System

Punjab Agricultural University, Ludhiana, has developed the Farm Advisory System to support agri-business management. The conversation between the system and the user is arranged in such a way that the system asks all the questions from user one by one which it needs to give recommendations on the topic of farm Management.

AGREX

Center for Informatics Research and Advancement, Kerala has prepared an Expert System called AGREX to help the Agricultural field personnel give timely and correct advice to the farmers. These Expert Systems find extensive use in the areas of fertilizer application, crop protection, irrigation scheduling, and diagnosis of diseases in paddy and post harvest technology of fruits and vegetables.

Medical Expert System

HELP

The HELP (Health Evaluation through Logical Processes) System is a complete knowledge based hospital information system. It supports not only the routine application of an HIS including ADT, order entry/charge capture, pharmacy, radiology, nursing documentation, ICU monitoring, but also supports a robust decision support function.

The HELP system is an example of this type of knowledge-based hospital information system, which began operation in 1980 (Kuperman et al., 1990; Kuperman et al., 1991). It not only supports the routine applications of a hospital information system (HIS) including management of admissions and discharges and order entry, but also provides a decision support function.

The decision support system has been actively incorporated into the functions of the routine HIS applications. Decision support provides clinicians with alerts and reminders, data interpretation and patient diagnosis facilities, patient management suggestions and clinical protocols. Activation of the decision support is provided within the applications but can also be triggered automatically as clinical data is entered into the patient's computerized medical record.

PEIRS

PEIRS (Pathology Expert Interpretative Reporting System) appends interpretative comments to chemical pathology reports (Edwards et al., 1993).

The knowledge acquisition strategy is the Ripple Down Rules method, which has allowed a pathologist to build over 2300 rules without knowledge engineering or programming support. New rules are added in minutes, and maintenance tasks are a trivial extension to the pathologist's routine duties. PEIRS commented on about 100 reports/day. Domains covered include thyroid function tests, arterial blood gases, glucose tolerance tests, hCG, catecholamines and a range of other hormones.

Puff

The Puff system diagnoses the results of pulmonary function tests. Puff went into production at Pacific Presbyterian Medical Center in San Francisco in 1977. Several implementations and many thousands of cases later, it is still in routine use. The PUFF basic knowledge base was incorporated into the commercial "Pulmonary Consult" product. Several hundred copies have been sold and are in use around the world. The PUFF system for automatic interpretation of pulmonary function tests has been sold in its commercial form to hundreds of sites world-wide (Snow et al., 1988). PUFF went into production at Pacific Presbyterian Medical Center in San Francisco in 1977, making it one of the very earliest medical expert systems in use. Many thousands of cases later, it is still in routine use.

SETH

The aim of SETH is to give specific advice concerning the treatment and monitoring of drug poisoning. Currently, the data base contains the 1153 most toxic or most frequently ingested French drugs from 78 different toxicological classes.

The SETH expert system simulates expert reasoning, taking into account for each toxicological class, delay, clinical symptoms and ingested dose. It generates accurate monitoring and treatment advice, addressing also drug interactions and drug exceptions.

Between April 1992 and October 1994, 2099 SETH analyzed cases inputted by residents. Since that time three phases of evaluation have been performed. It was concluded that an expert system in clinical toxicology is a valuable tool in the daily practice of a Poison Control Center.  As seen from considering of existing ES's, many of medicine ES's are for the assistance to the physicians in making diagnosing. These ES's may shorten the time to make the correct diagnosis and may reduce the number of diagnostic errors. At the same time, physicians may obtain the information on the symptoms of each of the diseases and pathologic syndromes contained therein.

These circumstances are very important for the countries with large number of population where the number of physicians respecting to 1000 person is limited. It is necessary to take into consideration designing and using of medicine ES's. Thus, researchers have to do their investigations directly on this area.

Vithoulkas Expert System

Now, there is an expert system that has been developed by Whole Health Now. The system called, Vithoulkas Expert System (VES). VES brings the case analysis of George Vithoulkas about the remedy decisions. George himself impressed with this software’s uncanny precision that he used own practice. And, his success rate has climbed from 80-85% astounding 90-95% as a result.

Actually, VES is working with any RADAR package then will come out with the result. RADAR is Repertory software, based on the Synthesis Repertory first repertory to bridge the gap between repertories and clinic confirmed experience. RADAR allowed the user to create a report on own standards.

The VES interprets a homeopath’s input to suggest when remedy questions should be asked, and it further orients their study of material medica. VES developed by computerized case analysis and develop the expert system and build it on RADAR as a base. George Vithoulkas describes the process:

"The team of homeopaths and software programmers started by taking a case of mine and asking why I prescribed remedy X and not Z, or T or M. I explained that certain points featured in the case more strongly than other points did.

"They wrote down what I said and then translated my thinking into mathematical formulas. This went on until we had created thousands of rules and sub-rules. Then we worked further to refine each rule until, it was as precise as it could possibly be."

Computerized Prescription Reduce Errors: Electronic Medical Records. (CPOE-EMR)

Prescription errors were believed to have contributed to almost 20% of the 98,000 deaths in an Institute of Medicine (IOM) report on medical errors.  But while hospitals try to fund expensive CPOE systems to assist in prescription writing, physician practices have viable and affordable prescription writing alternatives.

The prescription writing application should have the following characteristics:

• Tracks past medications including effectiveness, dates of use, size, take, frequency, duration and amount
• Drug interaction checks for current medications and if there are adverse interactions for new medications
• Flexibility in prescribing medications, i.e. easily changing refill limits
• Adding patient instructions to prescriptions that automatically print when medications are prescribed
• Tracking allergies and intolerances to medications per patient
• Being able to renew all existing medications with the click of a mouse

Maintaining the patients' medications using electronic prescription writing not only minimizes errors by tracking medications and effectiveness, but saves time and potentially lives.

Project Significance

PDAMummainly develops for PDA’s users that will give a simple but descriptive explanation to guide the users to recognize their PDA’s problem and then provide them with appropriate solution base on the accurate diagnosis.  Therefore users will get the response instantly and they are able to use the advices to clarify and solve the problems.

Through PDAMum, user will get clear explanation that able to help them to recognize their synchronization problem.  They may trace the problem via several short questions and receive the conclusion with suitable reasons. 

No more costly care line call and slow web access.  They will soon find that PDAMum really meaningful especially in term of PDA synchronization troubleshooting.  PDAMum responds very instant towards user input and come out with reliable diagnosis report.

Methodology

PDAMum used Knowledge Engineering methodology to ensure it will meet its requirement, objectives and scopes.

Figure 4: Knowledge Engineering Methodology

Phase 1: Problem Assessment

Most organizations when considering any new technology will ask the very practical questions ‘Will it work?’ and ‘Why should we try it?’ Since PDAMum is relatively new, answers to these questions are at best educated guesses. However, it is important that a serious effort be made to answer these questions before the project begins. Failure to do so can result in undertaking a project that has a small chance to succeed or will offer little benefit to the organization.

Then, this is a methodology for assessing the applicability of PDAMum to a given problem.

It’s structured according to the following tasks:

Task 1: Determine motivation of organization

Task 2: Identify candidate problems

Task 3: Performs feasibility study

Task 4: Perform cost/ benefit analysis

Task 5: Select the best project

Task 6: Write the project proposal

Phase 2: Knowledge Acquisition & Analysis

This task is the most difficult challenge in the development of an expert system. Knowledge acquisition is inherently a cyclical process. PDAMum used these tasks of knowledge collection, its interpretation and analysis, and the design of methods for collecting additional knowledge. An expert system gains its power from the knowledge it contains (Durkin, 1994). One of the most difficult aspects of the KE’s task is helping the expert to structure the domain knowledge, to identify and formalize the domain concepts (Hayes-Roth, Waterman and Lenat).

Phase 3: Design and Implementation

This phase begin with the selection of the knowledge representation technique and control strategy. This is followed with the selection of a software tool that best meets the needs of the problem. A small prototype of PDAMum is then built to both validate the project and to provide guidance for future work. PDAMum is then further developed and refined to meet the project objectives.

This process is structured according to the following task:

Task 1: Select rules as Knowledge representation technique

Task 2: Select control technique

Task 3: Select Kawa as PDAMum development software

Task 4: Develop the prototype, interface, and product

A rule-based approach is suitable because PDAMum discusses the problem primarily using IF/ THEN type statements. This discussion will usually lack an in-depth description of the problem’s objects, which would justify the need for a frame-based approach. Classification problems are typical of this situation where the expert tries to classify the state of some issue according to available information.

The keys to effective interface design are consistency, clarify and control. Consistency is consistent on screen format. Various types of materials are presented on screen such as title, questions, answer, explanation and control functions. When presenting these materials, it supposes to be that the similar material is place in the same location. Clarify is to clarify of presented materials. PDAMum used screen to ask questions, provide explanation on the system’s reasoning and display intermediate or final results. These materials presented in a clear manner for two reasons; two ensure the user will be receptive to the system and to enhance the reliability of exchanging information between the user and the system. And lastly is to the screen control. It’s to ensure the user always feel in control when using the system, to convince the user that any mistake user might make couldn’t lead to disastrous consequences.

Phase 4: Testing

As the PDAMum will need to be periodically tested and evaluated to assure that its performance is converging toward established goals. It is important that these decisions be made early, at a time when the original project goals are established.

These are the evolution of testing or evaluation of testing for PDAMum:

Stage 1: Preliminary Testing

• Study the complete knowledge base
• Uncover deficiencies in the knowledge and reasoning strategies
• Validate knowledge representation and inference approach

Stage 2: Demonstration Testing

• Choose a problem of limited scope within the capabilities of PDAMum
• Use demonstration to validate the expert system approach
• Show off major PDAMum features
• Design interface to accommodate of the user

Stage 3: Informal Validation Testing

• Select typical past test cases
• Evaluate PDAMum’s ability in solving typical cases and
• Identify PDAMum deficiencies and obtain comments from user on the interface

Stage 4: Refinement Testing

• Select unusual past test cases
• Evaluate PDAMum’s ability in solving unusual cases
• Uncover deficiencies in PDAMum’s knowledge and control
• Identify PDAMum deficiencies

Stage 5: Formal Testing

• Select past test cases and define test criteria
• Run the PDAMum for each test case and ask evaluators to judge system’s performance for each test case
• Obtain comments on the interface
• Identify PDAMum strength and deficiencies

Stage 6: Field Testing

• Define test criteria for the field test
• Determine if PDAMum meets its original goals when applied to real problems

Phase 5: Documentation

This documentation serves as a personal diary of the project. It contains all the material collected during the project that needs to be reference for developing the system. If properly designed, it will also serve the later tasks of maintaining PDAMum and writing the PDAMum’s final report.

Phase 6: Maintenance

After finished all of the designing, implementing, testing and documentation, PDAMum may need to be refined or updated to meet current needs. It is extremely important to keep good records on any changes made to PDAMum. If this isn’t done, it is very easy to lose track of the PDAMum’s knowledge. And each time PDAMum is modified; the following critical pieces of information should be documented:

• What was modified and who performed the modification
• When the modification was made
• Why the modification was made

System Analysis and Design

PDAMum Structure

PDAMum expert system maintains the expert’s domain knowledge in a module known as knowledge base.  It uses rules technique to code the knowledge in the knowledge base.  A rule is an IF/THEN structure that logically relates information contained in the IF part to other information contained in the THEN part.

These are the rules that could be used for PDAMum:

Other characteristics of complete expert system are working memory and inference engine.  PDAMum will use two classes ExpertSystem and PDAMum that play roles as inference engine and use Vector userReport as working memory.

Figure 5: Class PDAMum

Figure 6: Class ExpertSystem

Figure 7: Class Relationship

PDAMum also have explanation facility.  Means that PDAMum can provide an explanation to the user about why it is asking a question and how it reached some conclusion.

User Interaction

Basically, user will use PDAMum for troubleshooting their PDA’s synchronization problem.

Figure 8: Collaboration Diagram

Figure 9: Flow Chart

The diagram below illustrated the interaction sequence between PDAMum and user.

Figure 10: Sequence Diagram

Discussion and Conclusion

Expert systems have been used to solve a wide range of problems in domains such as medicine, mathematics, engineering, geology, computer science, business, law, defense and education. Within each domain, they have been used to solve problems of different types. Types of problem involve diagnosis (e.g., of a system fault, disease or student error); design (of a computer systems, hotel etc); and interpretation (of, for example, geological data). The appropriate problem solving technique tends to depend more on the problem type than on the domain.

PDAMum as an expert system might make mistakes, but it is less than a human did.  Furthermore it always performs consistently, never become tired or bored.  Other clear different is PDAMum can be use anywhere anytime compared to human.

User may clarify their PDA synchronization problem with immediate response and retrieve such reliable diagnosis through PDAMum.  This feature will assist them to recognize the causes that disallow their PDA synchronization.  They may ask PDAMum why they being ask such question during the interaction process. 

In future, PDAMum can be improve by convert it as web base application.  Instead of working stand alone, PDAMum can be reach through website which wider the access location.  User from various PDA owners may solely use single expert system to overcome their PDA’s problem.

PDAMum also should have better explanation facility.  This can be achieve if it has more rules to deals with other PDA problem such as sound and power management.  With additional knowledge, PDAMum can solve and refine the problem deeper, so that user may consider other possibility that blocked their PDA from perform well.

Other rational expansions are image viewer and uncertainty factor.  PDAMum can be utilize better if it can view meaningful image that will support it’s diagnose and decision.  Uncertainty also crucial since user sometime cannot express their feels.  With Certainty Factor (CF) capability, PDAMum will increase user confidence and convince them to make right choice.

Conclusion

PDAMum like other expert system will go a tremendous phases from simple expert system to the complex multipurpose systems. Hybrid expert system and together with fuzzy expert system can be seen as a new techniques that be used by researchers lately.  Implementation of expert system in such fields is greatly influenced by techniques and methods from adaptive hypertext and hypermedia. Features of personalization, user modeling and ability of adaptive towards environment will become great challenges to settle. It can be used as a guideline to promote an expert system in various functions.

In future, PDAMum can be used together with artificial neural networks, fuzzy logic, genetic algorithms and other methods of Artificial Intelligence. These methods allow taking into account their advantages in the designed system and, therefore, new designed systems are more powerful instruments to facilitate various tasks that require instant, accurate and reliable results.

References

Aamodt, A., & Plaza, E., Case-Based Reasoning: Foundational issues, methodological variations, and system approaches, AICommunications, IOS Press, http://www.iiia.csic.es/People/enric/AICom.pdf

Cawsey A., “The Essence of Artificial Intelligence”, Prentice Hall Europe, 1998.

“Computerize Prescription Reduce Errors”, Electronic Medical Records, Expert System Application, Inc.

[online: www.emrs.com/PrescriptionWritingReducedErrors.htm ]

Durkin, J., “Expert System Design and Development”, New Jersey: Prentice-Hall. 1994.

George, F. Luger & William, A. Stubblefield, “Artificial Intelligence: Structures and Strategies for Complex Problem Solving”, Addison Wesley Longman, Inc., 1998.

H. Basri, “An Expert System for Planning Landfill Restoration”, Water Science and Technology, 1998.

Hevner, et al., “Design Research in Information System”, 2004, http:// www.isworld.org

Richard E. Plant, Nicholas D. Stave, “Knowledge based systems in Agriculture”, McGraw-Hill, 1991.

R. L. Hoskinson, J. R. Hess, R. K. Fink, “A Decision Support System for Optimum Use of Fertilizers”, 1992.

Rule-Based ES's in Medicine, http://alpha.cbmi.upmc.edu/courses/fall97/Sep25/ index.htm