Artificial Intelligence Expert Systems Research Articles

Enhancing User Understanding in a Decision Support System: A Theoretical Basis and Framework

:The primary purpose of decision support systems (DSS) is to help the decision maker develop an understanding of the ill-structured, complex environment represented by the model. This paper concentrates on understanding the modeled environment through model analysis. Specifically, the purpose of this paper is to propose a framework for model analysis based on Perkins’s theory of understanding and its basic premise (knowledge as design) and basic components (purpose, models, and arguments). This framework encourages enhanced user understanding in a DSS via the synergistic combination and integration of: (1) cognitive science (theory of understanding), (2) artificial intelligence (machine learning, knowledge extraction, and expert systems), (3) model analysis (deductive and inductive), and (4) DSS (model management, instance management, and knowledge-base management).

An Overview of Recent Expert System Applications in Analytical Chemistry

Abstract A review is presented with references to the most important work dealing with the applications of artificial intelligence (expert systems, knowledge-based systems) in both qualitative and quantitative analytical chemistry. Contributions from January 1990 to date are briefly described together with some reviews and monographs on this matter. Topics covered include instrumental analysis, especially spectroscopy and chromatography, data management, chemometrics, process automation, and spectrum interpretation.

Techniques in Evaluating Nursing Expert Systems: A Case Study

This study addresses the problems in evaluating nursing diagnostic artificial intelligence (AI) expert systems. Two separate experiments (N = 49) were conducted using a computer expert system. The first experiment, the "white box" experiment (n = 9), compared the diagnostic techniques applied by experience RNs against the programmed techniques used by the expert system. The second experiment, the "black box" experiment (n = 40), compared diagnostic results of beginning nurses against the computer expert systems results. In some cases the computer outperformed the nurses and vice versa. The evaluation techniques, as applied in both experiments, enhance the ability of nurses to evaluate and select AI expert systems to be used in computer-assisted diagnosis of nursing problems.

Similarity and complementarity of molecular shapes: applicability of a topological analysis approach.

Developments based on a topological analysis approach of electron density maps are presented and applied to two different fields: the interpretation of electron density maps of proteins and the description of shape complementarity between a cyclodextrin host and a guest molecule. A global representation of the electron density distribution, through the location, identification and linkage of its critical points (points where the gradient of the density vanishes, i.e., peaks and passes), is generated using the program ORCRIT. On one hand, the interpretation of protein electron density maps is based on similarity evaluations between graphs of critical points and known structures. So far, the method has been applied to 3 A resolution maps for the recognition of secondary structure motifs using a procedure relevant to expert systems in artificial intelligence. Satisfying matches between critical point graphs and their corresponding protein structure depict the ability of the topological analysis to catch the essential secondary structural features in electron density maps. On the other hand, mapping the accessible volume of a host molecule is achieved by representing the peaks as ellipsoids with axes related to local curvature of the electron density function. Related energies of the interacting species can also be estimated. A qualitative comparison is made between the results generated by the topological analysis and energy values obtained by conventional molecular mechanics calculations. A positive comparison and a close complementarity between cyclodextrin and ligands shows that the topological analysis method gives a good representation of the electron density function.

Knowledge-based hybrid expert system for automated interferometric data reduction

In order to accomplish the ultimate goal of automated interferogram evaluation, the utilization of artificial neural networks or expert systems in artificial intelligence has been expected. In this paper, a new PC-based fringe evaluation technique, which is based on hybridization of an expert system and a conventional fringe tracking method, is presented together with some test results of noise-ridden interferograms in high-speed aerodynamics. This technique incorporates algorithmic image processing with expert-system-driven knowledge manipulation in a single structure to provide an optimal solution for noisy interferogram evaluation. A new approach for regional phase unwrapping based on the technique is also proposed. This concept is applicable to interferometry such as phase shifting and Fourier transform that provides phase-wrapped information. It is based on conservative decision making in defining phase-wrapped regions by utilizing global/regional knowledge in the expert system. The approach is thus believed to reduce computation time and memory space in processing complex or noisy interferograms that require frequent operator interactions.

An analysis of the need for ES and AI in accounting education

Through a survey of the membership of the Artificial Intelligence/Expert Systems (AI/ES) section of the American Accounting Association, this study examines the opinions of a subset of accounting educators about the inclusion of ES and AI in the accounting curriculum. The majority of these educators indicated that at the undergraduate level, they supplement texbook materials with readings which discuss ES and AI systems currently in use in accounting and auditing practice, while at the graduate level they use both supplemental readings and hands-on projects. A comparison between what the respondents felt to be important topics and what is currently included in a selection of accounting information systems textbooks found the texbooks to be inadequate and somewhat misdirected. This group of accounting educators were evenly split on whether or not an ES/AI course should be a required part of 150-hour accounting programs.

PROCESS AND DESIGN TOLERANCE IN RELATION TO MANUFACTURING COST: A REVIEW & EXTENSION

ABSTRACT Tolerance is an important aspect in comparing alternative designs and manufacturing processes. This paper presents a brief review of the previous work in the area of tolerance as it relates to manufacturing strategies and technologies. In addition, models for the economic selection of part tolerance that consider reworking are developed. The models can be helpful in augmenting some of the current artificial intelligence modules and expert systems to improve their performance.

NMRES: an artificial intelligence expert system for quantification of cardiac metabolites from 31phosphorus nuclear magnetic resonance spectroscopy.

The application of high-resolution 31Phosphorus Nuclear Magnetic Resonance (31P NMR) Spectroscopy in biology and medicine has provided new insights into biochemical processes and also a unique assessment of metabolites. However, accurate quantification of biological NMR spectra is frequently complicated by: (a) non-Lorentzian form of peak lineshapes, (b) contamination of peak signals by neighboring peaks, (c) presence of broad resonances, (d) low signal-to-noise ratios, and (e) poorly defined sloping baselines. Our objectives were to develop an expert system that captures and formalizes 31P NMR spectroscopists' expert knowledge, and to provide a reliable, efficient, and automated system for the interpretation of biological spectra. The NMR Expert System (NMRES) was written in the C and OPS5 programming languages and implemented on a Unix-based (Ultrix) mainframe system with XWindows bit-map graphics display. Expert knowledge was acquired from NMR spectroscopists and represented as production rules in the knowledge base. A heuristic weights method was employed to determine the confidence levels of potential peaks. Statistical and numerical methods were used to facilitate processing decisions. NMR spectra obtained from studies of ischemic neonatal and immature hearts were used to assess the performance of the expert system. The expert system performed signal extraction, noise treatment, resonance assignment, intracellular pH determination, and metabolite intensity quantitation in about 10 s per 4 KB (kilobyte) spectrum. The peak identification success rate was 98.2%. Peak areas and pH estimated by the expert system compared favorably with those determined by human experts. We conclude that the expert system has provided a framework for reliable and efficient quantification of complex biological 31P NMR spectra.

Three-hinge arch and asteroid trusses programmed in logic

Classical methods of structural analysis use the conditions of equilibrium and compatibility in a distinct and explicit way, offering a better insight and understanding of the behaviour of structures. Although algorithmic programming of these methods is not straightforward, because the implemented strategies are problem dependent, logic programming can be used effectively to implement classical methods of structural analysis. This can formulate the problem on a modern base from which design considerations can be tackled by using artificial intelligence methods and expert systems. It is anticipated that classical methods, more physical and conceptually clear, will provide the required information in a more flexible way. In this paper three-hinge arch and asteroid trusses are analysed on the basis of logic programming. These statically determine topologies are also important for the analysis of statically indeterminate configurations.

Rule based artificial intelligence expert system for determination of upper extremity impairment rating

Quantitative evaluation of upper extremity impairment, a percentage rating most often determined using a rule based procedure, has been implemented on a personal computer using an artificial intelligence, rule-based expert system (AI sytem). In this study, the rules given in Chapter 3 of the AMA Guides to the Evaluation of Permanent Impairment (Third Edition) were used to developed such an AI system for the Apple Macintosh. The program applies the rules from the Guides in a consistent and systematic fashion. It is faster and less error-prone than the manual method, and the results have a higher degree of precission, since intermediate values are not truncated.

Statically Determinate Trusses Programmed in Logic

Classical methods of structural analysis play an important role in the understanding of the behavior of structures because, during the process of solution, the conditions of equilibrium and compatibility are used explicitly. Computationally, these methods are problem dependent and, thus, are not suitable for algorithmic programming. Logic programming can be used to implement classical methods of structural analysis. This approach can help students understand the conditions of equilibrium and compatibility for structures and, at the same time, formulate the problem on a modern base from which design considerations can be tackled by using artificial intelligence methods and expert systems. The analysis of statically determinate trusses is employed to demonstrate the logic approach. The goal of solving a truss problem is achieved through the same subgoals followed when solving the truss problem by hand calculations. The procedure can be traced in a transparent way and alternative paths of solution can be determined. A program written in Turbo Prolog is presented and the logic approach is illustrated with some examples.

A multilayer perceptron solution to the match phase problem in rule-based artificial intelligence systems

In rule-based artificial intelligence (AI) planning, expert, and learning systems, it is often the case that the left-hand-sides of the rules must be repeatedly compared to the contents of some working memory. Normally, the intent is to determine which rules are relevant to the current situation (i.e., to find the conflict set). A technique using a multilayer perceptron to solve the match phase problem for rule-based AI systems is presented. A syntax for premise formulas (i.e., the left-hand-sides of the rules) is defined, and working memory is specified. From this, it is shown how to construct a multilayer perceptron that finds all of the rules which can be executed for the current situation in working memory. The complexity of the constructed multilayer perceptron is derived in terms of the maximum number of nodes and the required number of layers. A method for reducing the number of layers to at most three is presented. >

Teaching Artificial Intelligence and Expert Systems: Concepts in Library Curricula

A survey of artificial intelligence/expert systems (AI/ES) instruction was made of schools offering a degree in a library field at the bachelor's level or higher. Some consensus of opinion on what to include under AI/ES was found. The higher the level of program, the more relevant AI/ES was perceived. This was reflected in more course offerings, more hours of AI/ES instruction, and a higher average number of courses per institution. Teaching methods emphasized lectures, readings, reports, and demonstrations over hands-on use and program writing. Non-ALA programs expected a greater impact by AI/ES on the library profession within the next ten years than ALA programs, but the general feeling was that any impact will be low.

PERFORMANCE-DRIVEN AUTONOMOUS DESIGN OF PATTERN-RECOGNITION SYSTEMS

The closed-loop design experiment described in this paper demonstrates a three-phase automated design approach to pattern recognition. The experiment generates morphological feature detectors and then uses a novel application of genetic algorithms to select cooperative sets of features to pass to a neural net classifier. The self-organizing hybrid learning approach embodied in this closed-loop design methodology is complementary to conventional artificial intelligence (AI) expert systems that utilize rule-based approaches and a specific set of design elements. This experiment is part of a study directed to emulating the nondirected processes of biological evolution. The approach we discuss is semiautomatic in that initialization of computer programs requires human experience and expertise to select representations, develop search strategies, choose performance measures, and devise resource-allocation strategies. The hope is that these tasks will become easier with experience and will provide the means to ...

On-line artificial intelligence diagnostics for utility generating stations

The system architecture and functional operation are described in a centralized state-of-the-art artificial intelligence (AI) expert system for utility application. Experience gained has proven to be invaluable in refining the expert system knowledge bases and has led to other developments which have expanded the coverage of the system. The increased ability of on-line customers to implement predictive maintenance planning has proven to be a cost-saving tool for scheduled maintenance outages. In addition, this paper addresses the elements involved in the installation and operation of the generator AI diagnostic (GenAID) system from the customer's vantage point, such as its economic justification, required system installation activities, and training and operating procedure changes needed to integrate the GenAID system into the existing plant operations.

PROSPECTS AND TRENDS IN THE DEVELOPMENT OF CARTOGRAPHIC DATA BANKS

As automated cartography in the USSR enters a more advanced phase of its development, the author surveys the level of utilization of cartographic data banks and data retrieval systems which represent important links in the functioning of automated mapping systems. Among the topics discussed are types of source information and approaches to data organization, the potential application of knowledge bases and intelligent systems and their organization for cartographic purposes, and developments in the field of artificial intelligence (expert systems) and computer analysis of symbolization systems. Translated by Elliott B. Urdang, Providence, RI 02906 from: Izvestiya Akademii Nauk SSSR, seriya geograficheskaya, 1990, No. 3, pp. 31-37.

The structure of expert diagnostic knowledge in occupational medicine

Development of an artificial intelligence expert system for diagnosing occupational lung disease requires explicit specification of the structure of knowledge necessary in clinical occupational medicine independent of the process by which the knowledge is utilized. Furthermore, explicit recognition of sources of uncertainty is necessary. Seven categories of knowledge define the diagnostic knowledge base in occupational pulmonary medicine. These include four objects (jobs, industries, exposures, and diseases) and three relationships between pairs of objects. This analysis demonstrates some of the unique aspects of occupational medicine expertise.

Recent publications

Knowledge‐Based Systems: Markets, Suppliers and Products, Tim Johnson et al.The European Market for Expert Systems, Artificial Intelligence Systems and Expert Systems Used in Medical Laboratory Applications

RADA—A research and development advisor incorporating artificial intelligence techniques and expert system approaches

Abstract This paper describes the system RADA (Research and Development Advisor) which is an intelligent information system for use by researchers within a research and development environment. The fundamental concept behind RADA is the incorporation of artificial intelligence techniques and expert system approaches to “overcome” some of the shortcomings of the more traditional information retrieval systems, such as keyword-based retrieval, the need for specific retrieval languages, and the need for human intermediaries. RADA uses a graphical browser to display a conceptual semantic net (CSN) which represents graphically the user's information needs. To tailor the information to a specific user, RADA will have a user-modeling component. The user-modeling functions of RADA will ensure that the documents retrieved will be at the correct level of user comprehension and requirements, thus reducing the number of redundant documents retrieved. RADA is implemented in an object-oriented environment called LOOPS on a Xerox workstation.

An expert system for experimental design in off‐line quality control

Abstract: Robust design is an efficient method for designing high quality products at low cost. The method examines the effect of a large number of design factors on the variability of a product's response due to various sources of disturbance. This effect can be observed efficiently by studying a large number of variables simultaneously through balanced, orthogonal array experiments, and by analyzing the resulting data using variance decomposition methods. In this paper we describe an expert system prototype for designing efficient experiments. Given the information on various parameters and their levels, the system designs an experiment using orthogonal arrays. This expert system is implemented in Prolog, which is a logic programming language for artificial intelligence research and expert systems development. The system was implemented under the P‐Shell knowledge programming environment on UNIX.