Connecting expert system features to a multiple criteria programming based decision support system

We concentrate on the issue of utilizing artificial intelligence based computer systems as an aid to formulating and formalizing corporate planning problems. Our proposal involves cooperation between the analyst and expert system in order to find a suitable structure for the problem to be solved. The Al system is designed using logic programming. The study is an outgrowth of the experience gained in developing a strategic planning system with menu-driven simulation (heuristic, Monte Carlo), multiple criteria optimization and database query facilities for the concern management of Kansallis-Osake-Pankki (Finland).     

SATS: a microcomputer-based support for teaching structural analysis

This paper describes an educational software system for structural analysis. The system is intended to develop the students' intuitive skills to build effort diagrams for plane frames. It allows the students to draw the shear and moment diagrams for a given problem on the terminal screen, and then, to compare them with the correct ones. The instructor can generate an arbitrary number of new problems and store them on disk. During his session, the student may choose the problems he wishes to work on, according to his knowledge and interest. Moreover, the student can modify a problem statement to ponder the effect of those changes on the effort diagrams.     

Development of a microcomputer-based expert system for the analysis of manual materials handling tasks in industrial settings

This paper discusses the framework of a comprehensive knowledge-based expert system (M-LIFTAN) for analysis and design of manual materials handling tasks. The system, built using an expert system shell: ES / P ADVISOR written in Prolog 2, is implemented on a IBM AT® microcomputer. The knowledge base of M-LIFTAN allows the user to perform five different types of job analysis: (1) determination of maximum weights that can be handled manually by industrial workers for a variety of tasks, (2) determination of the NIOSH-based lifting recommendations, (3) prediction of maximum acceptable loads for lifting, (4) evaluation of the risk of overexertion injury while lifting loads under specified conditions, and (5) to seek advice for design/evaluation of complex manual handling tasks. An example of the consultation session illustrates the system's capabilities.     

Auditor evidence evaluation: expert systems as credible sources

Seventy-four experienced auditors from four Big-6 public accounting firms participated in a study of the effect of expert system use by subordinate auditors on superiors' decisions. Superiors were provided with information about a subordinate's decision and were told that the subordinate had or had not used an expert system. Superiors reported higher belief likelihoods and agreed more frequently with conclusions provided by subordinates who were expert system users, even when those conclusions were wrong. However, superiors' confidence in their own decisions was not affected by subordinate's use of an expert system.     

An expert decision support system for network routing: a case study

The paper presents a case study of the development of an expert decision support system which uses simple heuristic methods for fast determination of routes for simultaneous signals in a transmission network of limited capacity. It illustrates how heuristic solutions can be embodied in a model-based DSS and how the standard decision support literature, although intuitively appealing, provides little practical assistance in system construction or classification     

A microcomputer-based decision support system for the management of lumber mill production

Production management for a lumber mill includes the choice of saw patterns, as well as drying, sorting, grading and materials handling operations. The decision support system developed for an existing mill includes a linear programming (LP) model, data base software and a spreadsheet aid for detailed production scheduling. The LP model was structured to minimize total production cost subject to constraints on the available supply of raw material, the required output of timber, the available saw patterns and capacities on production facilities and materials handling operations. The LP solution is used by the spreadsheet support program to schedule product flow on a daily basis. The system was implemented on a microcomputer.     

Decision support system concepts in expert systems: An empirical study

This paper reports on a survey carried out on 67 ES to investigate whether they employ DSS concepts. The author examines several DSS frameworks and proposes a questionnaire model to conduct the survey. The survey data are analysed and the paper concludes that the three fundamental DSS issues: semi-structured task, support, and effectiveness are explicitly applied in ES. It shows also that although both DSS and ES have similar aims, they accomplish them in completely different ways. The differences are in the boundary of problem space and the way to tackle problems.     

Design of a microcomputer-based meetings system

This paper describes the design and implementation of a meetings system using a microcomputer. In this control system, the following achievements were made: counting and checking the voting in a very short time; establishing who is/is not present at the meeting; establishing whether/not the meeting is quorate; and controlling the debate by being able to call various members to speak.The meetings system provides most of the functions of a manual system but significantly reduces the time wastage — and hence the waste of money — by allowing the chairman and the members of the meeting to communicate with each other by way of electronic signals in a controlled manner and by relegating routine counting and listchecking tasks to a microcomputer.     

A microcomputer-based expert system prototype for helping the layperson find specific information on breast cancer questions

Medical expert systems have been around since the early 1970s. MYCIN, PUFF, CADUCEOUS and CASNET are examples of medical expert systems that have been built; however. their use, like most medical expert systems, is for the physician. There is a growing need for educating the public in certain areas of medicine. Laypersons want to be better informed. This paper focuses on a microcomputer-based expert system which is being developed to help the layperson be more informed on general and specific questions dealing with breast cancer.     

A case-based expert support system for due-date assignment in a wafer fabrication factory

Owing to the complexity of wafer fabrication, the traditional human approach to assigning due-date is imprecise and very prone to failure, especially when the shop status is dynamically changing. Therefore, assigning a due date to each order becomes a challenge to the production planning and scheduling staff. Since most production orders are similar to those previously manufactured, the case based reasoning (CBR) approach provides a suitable means for solving the due-date assignment problem. This research proposes a CBR approach that employs the k-nearest neighbors concept with dynamic feature weights and non-linear similarity functions. The test results show that the proposed approach can more accurately predict order due dates than other approaches.     

Design expert: An expert system application to clinical investigations

In recent years several expert systems have been developed for practical applications in applied statistical methodologies. Existing expert systems in statistics have explored several areas, e.g., the determination of appropriate statistical tests, regression analysis, and determination of the “best” experimental design for industrial screening experiments. The DESIGN EXPERT, a prototype expert system for the design of complex statistical experiments is presented here. It is intended for scientific investigators and statisticians who must design and analyze complex experiments, e.g., multi-level medical experiments with nested factors, repeated measures, and both fixed and random effects. This system is “expert” in the sense that it is able to (i) recognize specific types of complex experimental designs, based on the application of inference rules to nontechnical information supplied by the user; (ii) encode the obtained and inferred information in a flexible general-purpose internal representation, for use by other program modules; (iii) generate analysis of variance tables for the recognized design and an appropriate Biomedical Computer Programs runfile for data analysis, using the encoded information. DESIGN EXPERT can recognize randomized block designs, including lattice designs within embedded Latin Squares, crossover designs, split plots, nesting, repeated measures, and covariates. It is written in an experimental programming language developed specifically for research in Artificial Intelligence.     

Intelligent audit planning system for multiple auditors: IAPS

The auditor assignment planning process is regarded as a multi-agent multi-objective decision making problem that needs to balance between the “auditing firm's profit and audit risk” and the “individual auditor's preference”. The balance between the firm's profit to be optimized by a linear programming model and the audit risks checkable by a rule-based system is supported by adopting the Post-Model Analysis. The balanced solution from the firm's perspective is evaluated by the individual auditor's personal perspective. The Win-Win adjustments and a series of conflict resolution are assisted by an intelligent coordinating agent. A prototype IAPS (Intelligent Audit Planning System) that utilizes UNIK-LP, UNIK-PMA, and UNIK-AGENT could effectively support the auditor assignment process for audit engagements. This architecture would also be useful for support of other similar types of decision making processes.     

Decision support in fighter aircraft: from expert systems to cognitive modelling

This paper reviews two major programmes for support of pilot decision making in a fighter aircraft: the US Pilot's Associate and the French Copilote Electronique. In addressing the problem of decision support in a highly complex and time-pressurised environment, both programmes migrated from a traditional expert systems approach to one based on cognitive modelling. This, however, is where most commonality ends. The paper shows how the differences between the programmes can be explained in terms of their assumptions of what constitutes pilot expertise. These views explain the method for analysis of pilot activities, the model of the pilot, what phase of the pilot's problem solving the programmes attempt to support, and the support philosophy. The paper concludes with a discussion on computer-based decision support in complex, dynamic domains, and how cognitive modelling may contribute.     

Decision support in fighter aircraft: from expert systems to cognitive modelling

This paper reviews two major programmes for support of pilot decision making in a fighter aircraft: the US Pilot's Associate and the French Copilote Electronique. In addressing the problem of decision support in a highly complex and time-pressurised environment, both programmes migrated from a traditional expert systems approach to one based on cognitive modelling. This, however, is where most commonality ends. The paper shows how the differences between the programmes can be explained in terms of their assumptions of what constitutes pilot expertise. These views explain the method for analysis of pilot activities, the model of the pilot, what phase of the pilot's problem solving the programmes attempt to support, and the support philosophy. The paper concludes with a discussion on computer-based decision support in complex, dynamic domains, and how cognitive modelling may contribute.     

PERFEX: A cellular performance support expert

PERFEX (PERFormance EXpert) is an intelligent graphical software system that automates performance analysis and tuning of the cellular network. It combines artificial intelligence technologies with advanced graphics to assist performance engineers in analyzing cellular network performance data, validating network configuration, tuning system performance parameters, and carrying out special cellular engineering tasks. PERFEX is installed and in use in 25 GTE markets.     

Coupling interface of a microcomputer-based intelligent structural design system

An interactive interface has been created to couple a conventional structural analysis and design package to a knowledge-based system so as to form a microcomputer-based intelligent structural design system. Primarily, the interface comprises an automatic data generator and an interactive graphic editor. The data generator has been designed to automatically translate the symbolic output inferred by the knowledge-based system into numerical input for the structural analysis and design package. The interactive graphic editor allows the user to visually verify and/or modify the pre- and post-processed structural model. This paper presents an overview of the proposed intelligent structural design system, ISTRUDS, and describes the coupling interface, GENED.     

The design of a microcomputer-based net change MRP system

This paper describes the design and implementation of a Net Change Material Requirements Planning (MRP) System on an Apple II Plus microcomputer.MRP is identified as a flow control system. Reference is made to regenerative MRP and Net Change MRP and the distinction between the two systems is identified. An initial — Mark 1 — design of a regenerative MRP system is reviewed. The net change MRP package design is described in detail. The data base is outline with specifications of the Master Parts File, the Bill of Materials File and the Requirements File. The interrelationship between these files is presented and outline flowcharts of the major subprograms are provided. Some sample outputs from the system are discussed. Finally, these limitations of the system, together with ideas for future enhacements are presented.A complete listing of the program is available as an Appendix.     

Taking decisions in the expert intelligent system to support maintenance of a technical object on the basis information from an artificial neural network

In this paper, an intelligent operation system, which consists of an intelligent diagnostic subsystem (with a neural network) and an intelligent maintenance subsystem (with an expert system), was presented and discussed. The artificial neural network and the expert system, which use the information developed in the neural network, perform a special function in this system. The functional combination of the artificial neural network and the expert system together created a new solution in the form of an intelligent system, which was referred to as an intelligent maintenance system. This article also covers decision-making methods that are used in an expert maintenance system and whose purpose is an organization and control of the process of the prevention of technical objects. For this purpose, the method was described of taking decisions by an expert for complex parametric type hypotheses and for simple finished type hypotheses in the set of possible decisions’ hypotheses. A considerable part of this paper covers the presentation of the method to transform diagnostic information into the required form of maintenance information. For this purpose, an algorithm of the work of maintenance system was performed and descried. In the creation process of the maintenance knowledge base, the specialist knowledge of a human specialist was also used. Hence, a skilful and proper taking of decisions by an expert to create this set of information is essential. Two inference methods were characterized and described in this paper. The theoretical results obtained were verified in the examination of the influence of each of these decision-making inference methods on the final results of the process of the prevention treatment of an object.     

Managerial problem identifier (MPI): Integrating expert system and decision support technologies

In the past, managers have relied upon narrowly focused decision support systems (DSS) to facilitate the conventional decision process. Due to the human tendency to absorb only partial information, this technology has been underutilized. More contemporary theory advances the integration of Expert Systems (ES) with DSS to overcome the deficiencies found in conventional decision support systems. This paper presents a prototype Managerial Problem Identifier (MPI) that integrates decision support and expert systems. The interaction of financial accounting trends are analyzed by the expert system. The objective is to identify potential problems that might be responsive to early interaction.