Multiple Expert Systems Research Articles

Automatic classification of clustered microcalcifications by a multiple expert system

Mammography is a not invasive diagnostic technique widely used for early cancer detection in women breast. A significant visual clue of the disease is the presence of clusters of microcalcifications. The automatic recognition of malignant clusters of microcalcifications, which could be very helpful for diagnostic purposes, is a very difficult task because of the small size of the microcalcifications and of the poor quality of the mammographic images. In this paper we propose a novel approach for classifying clusters of microcalcifications, based on a Multiple Expert System; such system aggregates several experts, some of which are devoted to classify the single microcalcifications while others are aimed to classify the cluster considered as a whole. The final output results from the suitable combination of the two groups of experts. The tests performed on a standard database of 40 mammographic images have confirmed the effectiveness of the approach.

Lithofacies identification using multiple adaptive resonance theory neural networks and group decision expert system

Lithofacies identification supplies qualitative information about rocks. Lithofacies represent rock textures and are important components of hydrocarbon reservoir description. Traditional techniques of lithofacies identification from core data are costly and different geologists may provide different interpretations. In this paper, we present a low-cost intelligent system consisting of three adaptive resonance theory neural networks and a rule-based expert system to consistently and objectively identify lithofacies from well-log data. The input data are altered into different forms representing different perspectives of observation of lithofacies. Each form of input is processed by a different adaptive resonance theory neural network. Among these three adaptive resonance theory neural networks, one neural network processes the raw continuous data, another processes categorical data, and the third processes fuzzy-set data. Outputs from these three networks are then combined by the expert system using fuzzy inference to determine to which facies the input data should be assigned. Rules are prioritized to emphasize the importance of firing order. This new approach combines the learning ability of neural networks, the adaptability of fuzzy logic, and the expertise of geologists to infer facies of the rocks. This approach is applied to the Appleton Field, an oil field located in Escambia County, Alabama. The hybrid intelligence system predicts lithofacies identity from log data with 87.6% accuracy. This prediction is more accurate than those of single adaptive resonance theory networks, 79.3%, 68.0% and 66.0%, using raw, fuzzy-set, and categorical data, respectively, and by an error-backpropagation neural network, 57.3%.

Progress in materials for EML: review and preview

Materials developments in electromagnetic launcher technology are reviewed based on "open-literature" publications. One database analysis shows that materials topics are covered in 71 of 650 railgun papers published in the last decade. Several themes are evident in the electromagnetic launch (EML) literature, and those related to EM launcher technology are emphasized. In the new materials section, a preview is given of auxetic polymers and engineered carbon nanotubes. The first steps in the application of expert systems for screening and selecting high performance materials to be used in the design of these new flexible electrical machines are outlined. Increased knowledge in the materials and other intersecting technology areas may be rapidly incorporated, integrated and evaluated in a "virtual EM launcher platform". This proposed platform represents the interplay of multiple expert systems still being developed.

Refining the behavior of multiple expert systems: a concept and empirical results

Expert System Refinement (ESR) is introduced as a means to automatically refine the performance of one or more expert systems. The ESR concept is based on Holland’s learning classifier systems and a method for integrating multiple expert systems. Through users’ feedback about the usefulness/correctness of the integrated expert system’s recommendations, ESR enables behaviors of both individual expert systems as well as the integrated system to improve over time. The ESR concept is tested on a German Credit Database. This empirical evidence suggests that the ESR concept can be usefully applied in automating the process of expert system refinement and multiple expert systems integration. © 1998 John Wiley & Sons, Ltd.

Refining the behavior of multiple expert systems: a concept and empirical results

Refining the behavior of multiple expert systems: a concept and empirical results

Real time monitoring and analysis via the medical information bus, Part I.

Because of the complexity of monitored data in modern intensive care units (ICUs), and the risk of information being overlooked if medical staff have to pay attention to a multiplicity of monitoring apparatuses and alarm signals, the data for each patient may well be best presented on a single bedside screen after digestion by expert system techniques. Such central units should be able to deal with data from any monitoring apparatus, not just a predefined set. Furthermore, relay of the information from each bed to a central control station (one per ICU) is desirable for the purposes of permanent storage and for in-depth analysis. The paper describes a comprehensive system for ICU monitoring management and patient data analysis that integrates multiple expert systems and computers. The basic difficulties in applying expert system techniques to monitoring are overcome with the shell OPS/83, which allows calls to sequential C routines and allows time-driven reasoning through appropriate design of the inference engine and rules. Flexibility as regards connectable monitoring apparatus is afforded by basing data acquisition mainly, though not exclusively, on the IEEE Medical Information Bus.

A Rule-based Extension to the C++ Language

In rule-based systems, sets of rules are applied to known information to generate new, consequential information. The majority of the large number of existing systems1 has been produced with the objective of ease of use, enforcing an English-like syntax in the rules and hiding the control methods from the developer. The method adopted in the current work aims to provide rule-based facilities while maintaining the flexibility and implementation efficiency of a conventional language. This is achieved by extending the features of C++ to permit the development of rule-based systems whose control is decided by the developer. The design can be tailored to the application unrestricted by the normal constraints of the rule-based system, and a framework is made available for the development of multiple expert systems for use in blackboard system applications. This paper describes the approach adopted in the current work, the operation of the system and describes two example implementations. © 1997 John Wiley & Sons, Ltd.

A machine learning method for multi-expert decision support

When a decision maker has access to multiple expert systems, each embodying a different expert perspective on analyzing and reasoning about the same kind of decision problem, an important consideration is which to use at what times. We address this issue with a method based on competition among the distinct expert systems (and their respective rules). We begin by reviewing prior research concerned with the coordination of multiple sources of expertise in support of decision making, pointing out potential weaknesses of the proposed methods. Next, we introduce a new coordination method based on the competitive paradigm that has been applied in machine learning. This method involves adjustments to the strengths of expert systems and to their constituent rules based on their performances. A nine-step process for adjusting strengths is described. Advantages and limitations of this new method for expert system coordination are discussed. We outline an approach to testing the coordination method and report on preliminary testing of the performance of a system employing our method versus the performance of individual experts.

An expert system for voltage control of a large-scale power system

A decentralized expert system for voltage control of a large scale power system is proposed in this paper. The expert system is useful in dealing with modern large scale interconnected power systems which are characterized by complex and large computational burdens. The expert system consists of multiple local expert systems. Each local expert system is concerned with a part of the global system. The local expert systems work in parallel to perform their jobs: checking the existence of the violation and finding the most suitable control action. The sensitivity tree technique is adopted in finding the controller. The area of the system treated by a local expert system depends on the place of the violation and the place of the controller. The expert system makes use of the necessary system information and, at the same time, has the advantages of decentralized approaches, such as small computing time and small computer memory. This makes the expert system suitable for on-line applications. The expert system was tested, and encouraging results were obtained.

Embedding neural nets and expert systems in diagnostic microbiology laboratories

Describes a project for developing a reliable computer vision system that analyzes bacterial growths in real time on inexpensive personal computers, and an expert advising system that adds treatment recommendations to laboratory reports. The system embeds a neural network and multiple expert systems in the normal workflow of a clinical microbiology laboratory. Such laboratories receive specimens from patients with suspected bacterial infections, identify the organisms, determine which antibiotics will kill the bacteria or prevent growth, and convey the results to the treating physician, who can use the findings as a basis for treatment. Clearly this information is critical, since in the more extreme cases, lives are at stake. >

130 The research on multiple expert systems integrated decision support systems for solving complex problems

130 The research on multiple expert systems integrated decision support systems for solving complex problems

Integrating design tools for total building evaluation

To advance the use of expert systems and simulation tools, in fact to make them acceptable and usable to practitioners, a new approach is required in the development of an expert system and simulation tool environment. In this paper we detail the work currently taking place in New Zealand on the development of such an integrated environment for the use of multiple simulation tools and expert systems in the design process and for the analysis and refinement of the design as it progresses to a more concrete form.

A blackboard approach to modeling expertise in corporate settlement decisions*

Abstract: The SKADE system models expertise in corporate settlement decisions using the blackboard approach. The full model has four knowledge sources: General Counsel, Attorney, Manager and Insurance Adjuster. The combined expertise from each of these is required to make the settlement decision. A control component in the model coordinates the activities of the various knowledge sources. Based on the latest data entries on the blackboard, the control selects and executes the next knowledge source. The blackboard model reproduces the experts' opportunistic reasoning processes by the interaction between the various knowledge sources. The results of analyses of a hypothetical case through a series of experiments with the SKADE system indicate that the blackboard is an appropriate model for development of multiple cooperative expert systems in the settlement decision domain. Compared to straight rule‐based models, this blackboard provides more efficient problem solving. The initial success with the blackboard model suggests that further work needs to be done to see whether more complex models can be built to incorporate a broader range of determinants of settlement decisions.

The Research on Multiple Expert Systems Integrated Decision Support Systems for Solving Complex Problems

There has been an increasing interest in integrating decision support systems (DSS) and expert systems (ES) to provide decision makers a more accessible, productive and domain-independent information and computing environment. In this paper, we propose the multiple expert systems integrated decision support system (MESIDSS), present its basic framework and its management system of multiple ESs, and discuss emphatically the following aspects: combining opinions from multiple ESs, problem-based model integrating, and inconsistency processing among multiple ESs. Finally, application examples, a summary and some ideas for the future are presented.

A multiple domain expert system for beef cattle farmers

This paper describes the development of an expert system designed to advise on management strategies for beef cattle farmers who wish to improve their production systems. This task requires an integration of knowledge from a number of overlapping domains including cattle breeding, pasture improvement and pasture quality. We describe our approach to the problem of providing advice from more than one domain of expertise. We propose that by developing separate modules for each domain, using consistent terminology in all modules, and identifying where communication with another module is required, it is possible to develop an integrated multiple domain expert system.

Computerized conferencing for knowledge acquisition from multiple experts

Abstract The increasing complecity of many expert system application areas calls for the integration of the knowledge of multiple experts. The use of multiple experts introduces some interesting new problems during the process of knowledge acquisition. The problems are further complicated when the experts are geographically dispersed or unavailable for face-to-face interactions. This article discusses the motivations for acquiring the knowledge of multiple experts, the problems related to knowledge acquisition, new issues that arise whens multiple experts interact, solutions that can be brought to bear in building multiple expert systems (particularly when experts are geographically dispersed), and new tools for knowledge engineers to use when dealing with multiple experts.

Nursing Education Application of a Computerized Nursing Expert System

Nurse educators are required to be knowledgeable about a wide variety of complex health care problems in order to provide quality education. At the same time, they are given a multitude of other responsibilities such as participating in scholarly activity, advising students, maintaining an active role in nursing practice, and performing community service. These educators must find innovative ways to present current lectures while at the same time meeting their other obligations. The use of Creighton Online Multiple Modular Expert System (COMMES), a computerized decision support consultant, was evaluated as a technique for faculty use in developing and organizing new lecture content. The study found that COMMES was beneficial as a systematic prompt for lecture content, as a tool for organizing content, and as a means to verify completeness of lecture material.

A knowledge-based decision support architecture for advanced traffic management

Fundamental to the operation of most currently envisioned Intelligent Vehicle-Roadway System (IVRS) projects are advanced systems for surveillance, control and management of integrated freeway and arterial networks. A major concern in the development of such Smart Roads, and the focus of this paper, is the provision of decision support for traffic management center personnel, particularly for addressing nonrecurring congestion in large or complex networks. Decision support for control room staff is necessary to effectively detect, verify and develop response strategies for traffic incidents. The purpose of this paper is to suggest a novel artificial intelligence-based solution approach to the problem of providing operator decision support in integrated freeway and arterial traffic management systems, as part of a more general IVRS. A conceptual design is presented that is based on multiple real-time knowledge-based expert systems (KBES) integrated by a distributed blackboard problem-solving architecture. The paper expands on the notions of artificial intelligence and Smart Roads, and in particular the role, characteristics and requirements of KBES for real-time decision support. The overall concept of a decision support architecture is discussed and the blackboard approach is defined. A conceptual design for the proposed distributed blackboard architecture is presented, and discussed in terms of the component KBES functions at an areawide level, as well as the subnetwork or individual traffic control center level.

Interactive learning: a multiexpert paradigm for acquiring new knowledge

In this paper a paradigm for knowledge acquisition is presented. The paradigm, referred to as Multiexpert Knowledge System (MKS), is based on the philosophy that many decision problems which are candidate expert system applications do not rely on just a single expert for advice but utilize the expertise of many, sometimes conflicting, knowledge sources. Because of the potential for conflict between sources, the contemporary approach to building multiple expert or multiexpert knowledge systems has been to eliminate conflict prior to building the knowledge base. The MKS paradigm accommodates multiple, potentially conflicting experts and uses their expertise in the formulation of new knowledge (rules). These new rules are tested using sequential analysis and organized into a knowledge base by means of an entropy reduction program. Together the MKS paradigm, sequential analysis and entropy reduction are components in the design of an 'interactive' learning expert system which behaves as a 'virtual' expert learning and unlearning new knowledge.

Ontological versus knowledge engineering

The author first discusses the difference between a knowledge base (KB) and a database (DB), which seems to hinge on the 'gray box' verses 'black box' nature of the entries. He then discusses the need for a huge KB to break today's bottleneck in intelligent systems, i.e. their brittleness when confronted by unforeseen problems. That same brittleness-the representation trap-is what prevents multiple expert systems from cooperating or even sharing rules. The author then considers the central question of the present work: How is the task of building a huge KB different from that of building n small KBs? It is shown that this leads into the realm of ontological engineering, and it is found that there is no single, elegant 'use-neutral' solution to the problem, at least not at present, but that a kind of variegated 'tool-box' approach might succeed.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>