ANDES: a phased-array antenna diagnostic expert system

The Antenna Repair Facility at McClellan Air Force Base, which has been responsible for the repair and maintenance of US Air Force antennas and radars over several decades, now faces the challenge of transferring their many years of expertise in antenna repair and maintenance from their closing base to an acquiring base. This is being done with the requirement of maintaining the in-house expertise and production levels, while manpower decreases.

To meet the challenge, an expert system called ANDES is being developed to help diagnose electronically steered phased-array satellite ground station antennas at McClellan AFB and the acquiring base. This paper discusses the key issues in the design and development of ANDES and focuses on its use as a tool to help human engineers improve the antenna diagnostic process. The ANDES’ experience indicates that during the times of downsizing, streamlining and restructuring, expert systems offer a viable and sometimes pivotal means to preserve expertise from a closing facility and also can be used as a training tool by an acquiring facility.     

ROGET: A knowledge-based system for acquiring the conceptual structure of a diagnostic expert system

This paper describes ROGET, a knowledge-based system that assists a domain expert with an important design task encountered during the early phases of expert-system construction. ROGET conducts a dialogue with the expert to acquire the expert system's conceptual structure, a representation of the kinds of domain-specific inferences that the consultant will perform and the facts that will support these inferences. ROGET guides this dialogue on the basis of a set of advice and evidence categories. These abstract categories are domain independent and can be employed to guide initial knowledge acquisition dialogues with experts for new applications. This paper discusses the nature of an expert system's conceptual structure and describes the organization and operation of the ROGET system that supports the acquisition of conceptual structures.     

A general expert system design for diagnostic problem solving

Existing expert systems have a high percentage agreement with experts in a particular field in many situations. However, in many ways their overall behavior is not like that of a human expert. These areas include the inability to give flexible, functional explanations of their reasoning processes, and the failure to degrade gracefully when dealing with problems at the periphery of their knowledge. These two important shortcomings can be improved when the right knowledge is available to the system. This paper presents an expert system design, called the integrated diagnostic model (IDM), that integrates two sources of knowledge, a shallow, reasoning-oriented, experiential knowledge base and a deep, functionally oriented, physical knowledge base. To demonstrate the IDM's usefulness in the problem area of diagnosis and repair, an implementation in the mechanical domain is described.     

A customized network diagnostic expert system based on general diagnostic strategies

The objective of this research is to investigate the common link in diagnostics of different networks. Are there any underlying common expertise and strategies that are applicable to various connection-based networks? If so, how is the general expertise related to network-specific expertise? Why is it significant to identify and figure out the general expertise? To support our method, we developed an expert system which helps to interpret the alarms delivered from a multiplexer network, determine the faulty behavior of the network, and offer recovery suggestions. Our work classifies the diagnostic expertise into (i) general expertise and (ii) customized or network-specific expertise. The former consists of certain general strategies and common sense in network diagnostics, while the latter consists of specific technology know-how of a network built with a particular product family of multiplexers. Since the general expertise is also applicable to other types of connection-based networks, it is hoped that our work can provide a foundation to build other network diagnostic expert systems.     

An ergonomic expert system for risk assessment of work-related musculo-skeletal disorders

A computer-based expert system (SONEX) was developed to identify ergonomic risks for work-related musculoskeletal disorders (WRMSDs) in a wide variety of jobs and provide expert prevention advice. SONEX uses a rule base and 6 knowledge base modules: WRMSD risk factors are grouped into two main knowledge base modules (symptoms, engaged body part) with four supplementary knowledge base modules (work environment, work chair, work tools, organization factors). SONEX uses a menu-based interface and a series of simple questions that lead a user through each of the two main modules. Based on user responses it then recommends other knowledge base modules that are relevant for a detailed analysis of work risks. The SONEX rule base has over 140 questions, the knowledge base includes over 200 risk factors, and around 500 possible answers can be generated. SONEX relates ergonomic shortcomings in the job with worker's subjective symptoms; it predicts possible WRMSDs; and it offers preventive suggestions for ergonomic improvements to the job to prevent WRMSDs. It has been tested in a variety of work places with known ergonomic problems and with known employee WRMSDs by comparing its performance with conventional analytical methods and results show that it accurately predicts possible WRMSD risks and identifies ergonomic shortcomings. The advantages of SONEX are that it is much faster than other ergonomic analysis methods and it can be used by ergonomists and other professionals and also by workers themselves.     

Privacy issues in a psychiatric context: applying the ISD privacy framework to a psychiatric behavioural monitoring system

Privacy issues are frequently discussed amongst researchers, practitioners and patients in healthcare. However, psychiatric patients’ privacy issues get less attention in information system development (ISD), whereby they are one of the most important stakeholders. This paper applies Carew and Stapleton’s ISD privacy framework to psychiatric monitoring systems to understand the issues that are related to monitoring psychiatric patients’ behaviour. By understanding the privacy issues amongst patients, the research will be able to provide guidance to system developers to produce a privacy-sensitive system that can contribute to the system engineering for international stability. We will elaborate each factor in the framework (physical, social, psychological and informational) and then explain the relationship to the privacy of psychiatric patient.     

An expert diagnostic program for dermatology

The first knowledge-based medical consultation program for dermatology is reported. This program uses SEEK, a new facility within the Rutgers University EXPERT system. Our current model gives a differential diagnosis for 13 different tumors with an overall accuracy of 84%. The model uses a formal criteria-based knowledge representation scheme. In addition, the first visually indexed database in dermatology has been developed.     

Small world network model of personal consumption: Demand-side management in an expert system

Representing personal consumption is important to a range of expert decision makers in academic, government and corporate settings. We cite the possible contribution of studying a system model of the use of information in personal consumption when agents are members of a small world network. Information has properties in non-rival borrowing and sensitivity to network memberships that individual agents do not typically include in heuristics they use in budget allocation. We use computational methods to show how an expert system in which a super agent using a model that includes properties of information and network parameters can define welfare maximizing allocation and policy to bring the allocation of individual agents closer to a welfare-maximizing allocation. Implications of systems with the dynamics we propose for representing demand-side management in expert systems are noted.     

An expert system for balance of payments analysis. A fault diagnostic approach

A rule based expert system, utilizing a decision tree of heuristic rules can be helpful in economic policy evaluations. With additional graphic interfaces and simulation, the tool can be used to bring the expertise of expert economists to non-expert, high-level decision makers in evaluating policy alternatives facing developing country governments.     

On the applicability of diagnostic criteria for the diagnosis of rheumatoid arthritis in an expert system

-2/ is a medical expert system developed to assist in the differential diagnosis of rheumatic diseases. Based on fuzzy set theory and fuzzy logic, it supports the formalization of vague and uncertain medical information (i.e., medical entities and relationships between them) and draws justifiable conclusions from these imprecise data. Given a patient's finding patter, -2 provides confirmed and excluded diagnoses, diagnostic hypotheses, and suggestions for further examinations. The knowledge base of -2 has been designed to contain simple finding/disease relationships as well as diagnostic rules of high complexity to confirm or hypothesize disease. We shall present results obtained with 300 clinical cases from a hospital for rheumatic diseases. Different rules for the diagnosis of rheumatoid arthritis based upon classification criteria issued by the American Rheumatism Association were tested against each other. That diagnostic rule which had shown the best results was then further improved by a rheumatology expert, which finally yielded a sensitivity of 83.3% and a specificity of 95.3%.     

AMRAPALIKA: An expert system for the diagnosis of pests,diseases, and disorders in Indian mango

This paper emphasizes application of expert system in Indian fruiticulture and describes development of a rule-based expert system, using Expert System Shell for Text Animation (ESTA), for the diagnosis of the most common diseases occurring in Indian mango. The objective is to provide computer-based support for agricultural specialists or farmers. The proposed expert system makes diagnosis on the basis of response/responses of the user made against queries related to particular disease symptoms. The knowledge base of the system contains knowledge about symptoms and remedies of 14 diseases of Indian mango tree appearing during fruiting season and non-fruiting season. The picture base of the system contains pictures related to disease symptoms and are displayed along with the query of the system. The result given by the system has been found to be sound and consistent.     

Framework for building rule-based machine diagnostic expert systems

In the endeavour to build an expert system called XBAK using Personal Consultant Plus for the diagnosis of sophisticated equipment used in microchip manufacturing, a rule-based machine diagnostic expert system architecture was developed. The approach, features and technical implementation of this application-independent problem-solving structure are described. The architecture can be used as a framework for solving similar problems in the area of machine diagnostics.     

Quantitative proteomics for investigating psychiatric disorders

The underlying pathophysiology of psychiatric disorders remains elusive. The use of quantitative proteomics to investigate disease-specific protein signatures holds great promise to improve the understanding of psychiatric disorders and identify relevant biomarkers. In this review, we discuss quantitative proteomic approaches for elucidating molecular mechanisms of psychiatric disorders, i.e. anxiety, schizophrenia, bipolar disorder and depression, by studying specimens from animal models and patients. We present gel-based, label-free and stable isotope-labeling methodologies and evaluate their strengths and limitations in the context of psychiatric research, with a focus on (15)N metabolic labeling of live animals due to its increased accuracy and potential for future applications. We also review biomarker candidate validation methods and present quantitative proteomic studies from the literature that aim to disentangle the molecular pathobiology of psychiatric disorders and identify candidate biomarkers. Finally, we explore the applicability of implementing proteomic methods as a routine diagnostic tool in the clinical laboratory.     

TRISTAR: an expert system for vegetation processes

Abstract: The TRISTAR expert system (TRIangular STrAtegic Rules for British herbaceous vegetation) is a PC-based consultancy tool designed to help bridge the gap between academic plant ecology and practical vegetation management. It is a 'what if facility, for use by students, naturalists, conservationists, planners, administrators; indeed anyone with an interest in environmental science and management, conservation or reconstruction of herbaceous vegetation. The system is written in Leonardo 3 (Creative Logic Limited, Uxbridge, UK). Release I of TRISTAR deals with the fundamental environmental and management processes which control the composition of British herbaceous vegetation. The system takes a specification of initial steady-state vegetation, asks the user to specify an altered environmental and/or management scenario, and predicts the composition of a new steady-state vegetation in terms of plant-strategic types. The high-level approach through plant strategies makes it possible to construct a very robust rulebase despite a lack of hard information in many areas of understanding.     

ESSE: an expert system for software evaluation

Solving software evaluation problems is a particularly difficult software engineering process and many different—often contradictory—criteria must be considered in order to reach a decision. This paper presents ESSE, a prototype expert system for software evaluation that embodies various aspects of the Multiple-Criteria Decision Aid (MCDA) methodology. Its main features are the flexibility in problem modeling and the built-in knowledge about software problem solving and software attribute assessment. Evaluation problems are modeled around top-level software attributes, such as quality and cost. Expert assistants guide the evaluator in feeding values to the decision model. ESSE covers all important dimensions of software evaluation through the integration of different technologies.     

ESOM: An expert system for multicriteria scheduling

There exist situations in operations scheduling where the parameters of the scheduling decision are nonquantifiable, or appear as nonnumerical entries in a database. Scheduling techniques based on numerical algorithms may be difficult to use in such situations. In many service industries, the nonnumerical character arises from constraints or preference parameters associated with service tasks, service agents, and the business operation itself. The agent to task assignment problem is one of satisfying multiple objectives, by taking into account the various constraints and preferences inherent in such problems. In this paper, we describe the development of an expert system prototype called ESOM, that aims to automate the assignment decision process of a childcare referral agency. We discuss some key research issues pertaining to service scheduling in general, and to the childcare assignment problem in particular. ESOM provides useful guidelines to future researchers and practitioners interested in building expert systems for service scheduling. We demonstrate assignments made by our prototype through an application scenario.     

基于基因组合模式挖掘的辅助诊断专家系统

在医疗领域中,基因芯片技术等高效核酸分析手段不断发展,使得临床诊断与医学研究中能够利用这一技术获取大量与肿瘤生成相关的基因信息。同时,近年来随着机器学习理论与技术的不断发展与应用,在各领域内出现了大量基于人工智能技术的专家系统。针对基因芯片信息的特点,描述了一种肿瘤辅助诊断专家系统的设计思路与实现方案;讨论了在专家系统实现过程中所采用的关键数据挖掘技术;重点叙述了系统的结构框架、工作机制与辅助诊断原理。在实验中,展示了临床获得的医疗数据在所论述系统中的测试结果。实验结果表明所论述的系统实现方案能够在一定程度上满足辅助诊断的需求。     

基于国际头痛诊断标准的原发性头痛辅助决策系统

针对原发性头痛在我国发病率较高但诊断准确率较低的问题,提出了一种将文本化的国际头痛诊断标准转换为计算机可执行推理的临床知识建模和知识库构建方法,该方法首先将基于诊断标准绘制的诊断思维流程图转换为规范化的临床知识表达模型,再将临床知识表达模型通过规则映射技术转换为计算机推理诊断所用的规则,形成知识库。并以此为基础开发了覆盖完整头痛诊断流程的原发性头痛辅助决策系统。临床评估显示,该系统可正确识别出91.3%的偏头痛、87.2%的紧张型头痛和90.0%的丛集性头痛病人,对常见的原发性头痛具有较高的诊断准确率。     

An expert system for sorting

Abstract: Sorting an internal list is an indispensable requirement in numerous data processing applications, and many algorithms have been devised for accomplishing those tasks. Furthermore, it is fairly simple to derive order of magnitude of effort measures for particular sorting strategies, and within classes of equivalent theoretical power, practice has shown which algorithms prevail in which circumstances. Thus there is a useful background for testing a system's ability to learn which problem solving technique should be applied in a given instance, for the expert knowledge is rather concise and structured and facilitates comparison to machine decisions. The paper describes the construction of such a system and analyzes the results.