Abstract: From the Publisher: The text provides an introduction to expert systems, neural nets, genetic algorithms, smart systems and artificial life and shows how they are likely to transform geographical enquiry. An integral disk provides examples and exercises for the readers to try themselves, which is a major methodological milestone in geography. The authors provide an easy to understand basic introduction to AI relevant to Geography.

Abstract: Part 1 The cognitive perspective: cognitive and developmental factors in expert performance, K.A. Ericsson and N. Charness some concrete advantages of abstraction - how experts' representations facilitate reasoning, C.M. Zeitz cognitive models of directional inference in expert medical reasoning, V.L. Patel and M.F. Ramoni experience and expertise - the role of memory in planning for opportunities, C.M. Seifert et al issues of expert flexibility in contexts characterized by complexity and change, P.J. Feltovich et al. Part 2 Expertise in context: cognitive conceptions of expertise, R.J. Sternberg metaphors for expertise - how knowledge engineers picture human expertise, M. LaFrance a look at expertise from a social perspective, E.W. Stein expertise in dynamic, physical task domains, V.L. Shalin et al expertise in context - personally constructed, socially selected and reality-relevant?, N.M. Agnew et al. Part 3 Socially situated expertise: the conceptual nature of knowledge, situations and activity, W.J. Clancey RAT-Tale - sociology's contribution to understanding human and machine cognition, H.M. Collins. Part 4 Expert systems in context: model-based expert systems and the explanation of expertise, N. Shadbolt and K. O'Hara a study of solution quality in human expert and knowledge-based system reasoning, C.C. Hayes abduction and abstraction in diagnosis - a schema-based account, C.R. Stern and G.F. Luger integrating skill and knowledge in expert agents, H. Hexmoor and S.C. Shapiro toward automated expert reasoning and expert-novice communication, M. Miller and D. Perlis the tuning effect - the nature of trust in expert systems advice, F.J. Lerch et al interpreting generic structures - expert systems, expertise and context, K. O'Hara and N. Shadbolt. Part 5 Pushing the envelope: an argument for the uncomputability of infinitary mathematical expertise, S. Bringsjord expertise and context in uncertain inference, H.E. Kyburg negative expertise, M. Minsky context, cognition and the future of intelligent infostructures, A.T. Rappaport. Part 6 Recapitulation and synthesis: a general conceptual framework for conceiving of expertise and expert systems, R.R. Hoffman et al.

Abstract: Power system generation expansion planning is a challenging problem due to the large-scale, long-term, nonlinear and discrete nature of generation unit size. Since the computation revolution, several emerging techniques have been proposed to solve large scale optimization problems. Many of these techniques have been reported as used in generation expansion planning. This paper describes these emerging optimization techniques (including expert systems, fuzzy logic, neural networks, analytic hierarchy process, network flow, decomposition method, simulated annealing and genetic algorithms) and their potential usage in solving the challenging generation expansion planning in future competitive environments in the power industry. This paper provides useful information and resources for future generation expansion planning.

Abstract: Cooperation is often presented as one of the key concepts which differentiates multi-agent systems from other related disciplines such as distributed computing, object-oriented systems, and expert systems. However, it is a concept whose precise usage in agent-based systems is at best unclear and at worst highly inconsistent. Given the centrality of the issue, and the different ideological viewpoints on the subject, this was a lively panel which dealt with the following main issues.

Abstract: The paper discusses a framework that uses machine learning and other automatic-learning methods to assess power-system security. The framework exploits simulation models in parallel to screen diverse simulation scenarios of a system, yielding a large database. Using data mining techniques, the framework extracts synthetic information about the simulated system's main features from this database.

Abstract: A machine learning approach to automated building of knowledge bases for image analysis expert systems incorporating GIS data is presented. The method uses an inductive learning algorithm to generate production rules from training data. With this method, building a knowledge base for a rule-based expert system is easier than using the conventional knowledge acquisition approach. The knowledge base built by this method was used by an expert system to pe$orm a wetland classification of Par Pond on the Savannah River Site, South Carolina using SPOT multispectral imagery and GIs data. To evaluate the peqformance of the resultant knowledge base, the classification result was compared to classifications with two conventional methods. The accuracy assessment and the analysis of the resultant production rules suggest that the knowledge base built by the machine learning method was of good quality for image analysis with GIS data.

Abstract: Ishibuchi, Fuzzy Neural Networks and their Applications. Chak, Feng, and Palaniswami, Implementation of Fuzzy Systems. Aiello, Burattini, and Tamburrini, Neural Networks and Rule-Based Systems. Fletcher andHinde, Construction of Rule Based Intelligent Systems. Pal and Mitra, Expert Systems in Soft Computing Paradigm. Watanabe and Tzafestas, Mean-Value-Based Functional Reasoning Techniques in the Development of Fuzzy-Neural Network Control Systems. Chen and Teng, Fuzzy Neural Network Systems in Model Reference Control Systems. Juditsky, Zhang, Delyon, Glorennec, and Benveniste, Wavelets in Identification.

Abstract: From the Publisher: Information technology has provided numerous options to individuals, governments, and corporations around the world. These options demand that choices be made, and such choices often involve ethical decisions. Users must decide, for example, whether certain data should be made available on the Internet, whether the information contained in various databases should be sold to third parties, and whether software developers should be held responsible for social and economic problems that result from their programs. This book provides a rigorous but accessible discussion of some of the major ethical issues concerning computers and information technology. The text gives particular attention to widespread issues concerning intellectual property rights, censorship, and privacy, along with less frequently raised topics, such as ethical worries about image manipulation, virtual reality, and the moral status of "intelligent" machines and expert systems.

Abstract: Usually, expert systems use numbers to describe the experts' degree of belief in their statements In practice, however, it is difficult to assign an exact numerical value to the expert's degree of belief At best, we can get an interval of possible values This fact leads to the use of interval-valued degree of belief When intervals are used to describe degrees of belief, then computations with intervals must be used to process them In this paper, we describe applications of such interval computations to expert systems and to intelligent control

Abstract: An automated custom power supply design system uses an expert system containing a set of rules, including manufacturing limitations to limit design choices and ensure feasibility and manufacturability of the design. A design interface collects specifications from a user. A complement of power components for satisfying the electrical specifications is defined and mechanical specifications for each component are provided by the system for use in creating the mechanical design. After the mechanical design is established a thermal analysis is performed and the completed design is returned to a host computer. After an order is received, a computer integrated manufacturing system generates all of the specifications required to manufacture the components for the system and the system.

Abstract: In order to analyze the performance of photovoltaic (PV) systems, we have developed a real-time expert system based on a central microcomputer used as a microserver and can be easily consulted from different automatic stations. The developed system is able to ensure the monitoring, supervision, and control of PV systems installed over a wide area, on one hand, and to create a general PV systems database, on the other. This paper presents a design of a universal data acquisition system with available components and which is easily accessible through a server. The hardware and software configuration of the expert system are described. Performance of this system are also presented when applied on PV systems.

Abstract: Artificial intelligence has recently been investigated and applied with success to the solution of some long-standing power system problems where conventional methods experience difficulty Tutorials previously published in the Power Engineering Journal have introduced expert systems and artificial neural network applications in power systems This series of three tutorials gives practising power engineers an overview and general appreciation of the basic concepts of fuzzy logic and an insight into how this technique can be applied to solve complex power system problems The first tutorial gives a general introduction to fuzzy logic

Abstract: Knowledge acquisition and representation has been characterised as the major bottleneck in the development of expert systems (Barr & Geigenbaum, 1982), especially in problem domains of high complexity. Financial analysis is one of the most complicated practical problems, where the expert systems technology is highly applicable, mainly because of its symbolic reasoning and its explanation capabilities. The aim of this paper is to present a complete methodology for knowledge acquisition and representation for expert systems development in the field of financial analysis. This methodology has been implemented in the development of the FINEVA multicriteria knowledge-based decision support system for the assessment of corporate performance and viability. The application of this methodology in the development of the FINEVA system is presented.

Abstract: A system for matching individuals, products and service providers is trained to react as if an expert was assisting the user, in real-time, to make purchases or design personal development programs or marketing programs. The system allows the user to obtain recommendations from experts based on individual preferences, personal profiles, and desires and goals of individuals. The system creates a database of information about the individuals in order to provide a customized response based on an individual's objectives. The computer system is configured with five primary components: input device (84), processor (93), database (96), expert system (92) and display (81). The computer-driven system creates, accesses, and processes data from databases related to products, services, providers, and the like. Boolean, fuzzy, rule-based, and knowledge-based logic, expert systems, expert interaction and/or expert intervention are used to achieve results.

Abstract: This paper presents an extended survey of the application of knowledge-based decision support systems (KBDSSs) in financial management. KBDSSs originated from the combination of decision support systems with expert system (ES) technology. Thus, initially, the implementation of both decision support systems and ESs in several fields of financial management is discussed. The existing problems and limitations of these two approaches are outlined, and the new methodological framework based on the use of KBDSSs and its application in financial management are presented.

Abstract: The paper demonstrates a novel component oriented fuzzy expert system (COFES) developed in PROLOG for power system fault diagnosis. This 'expert system' assesses faults on power systems using intelligent techniques that can take account of bad/missed SCADA data. Incorrect operation of protective relays and/or circuit breakers during single as well as multiple faults and corresponding uncertain incoming information render proper fault diagnosis a very involved task. To handle these uncertainties and rank various fault hypotheses a fuzzy signal model based on fuzzy information theory has been developed. The model measures degree of correctness of received and nonreceived input data. The proposed method incorporates fuzzy symbol classification through an enhanced knowledge-base which includes network model, predefined subnetworks, relaying schemes and fuzzy diagnostic rules. This expert system has been applied to a sample power system. The results obtained along with their evaluations are completely reported.

Abstract: A method for tutoring a trainee in a simulator comprises the steps of defining an expert system simulating an activity, and using the expert system to provide instructional feedback to the trainee. The step of defining an expert system comprises constructing a decision support system so as to define a human factors engineering module, programming a plurality of training scenarios, and establishing automated performance measures. The method for tutoring of the present invention eliminates the need to have an expert trainer available and the consequent expense associated therewith.

Abstract: Since the early to mid 1980s, much of the effort in power systems analysis has turned away from the methodology of formal mathematical modelling which came from the fields of operations research, control theory and numerical analysis to the less rigorous techniques of artificial intelligence (AI) Today, the main AI techniques found in power systems applications are those utilising the logic and knowledge representations of expert systems, fuzzy systems, artificial neural networks (ANN) and, more recently, evolutionary computing These techniques are outlined in this paper and the power system applications indicated

Abstract: This paper presents an expert system for diagnosis of power system fault allocation in real time (SIDUF-TR). The system uses information on the tripped relays and circuit breakers to identify the most probable faulted element of the power system, serving as a decision making support for energy control center dispatchers. First, the expert system structure is presented, including a description of the inference method used to determine the most probable failures places. Then the architecture for real-time operation of SIDUF-TR in a control center is described. Finally, the result of the application of the system to a real disturbance is presented. I. INTRODUC~ON In cases of power system disturbances, control centers dispatchers must use their judgement and experience to determine the possible faulted elements as the first step in the restoration procedures. When a breaker or its associated relays fail to operate, the fault is removed by backup protection. In such cases, the outage area is very large and it is difficult for the dispatchers to estimate the fault location. Moreover, multiple faults may eventually take place, with many breakers being tripped within a short time. In these circumstances, so many alarm messages pour into the dispatch center that it is impossible for the dispatchers to analyze the situation satisfactorily and to ensure that the most appropriate actions be taken. Therefore, it is important to develop some means of providing accurate fault analysis to assist dispatchers in these situations. This may be achieved by using an expert system, embedded in the existing energy management system (3,8). Development of expert systems for fault diagnosis of power systems has received growing attention in the last years (6,8). Some of the previously reported systems for fault diagnosis use the monitoring information-based approach (1,8). A tree structure or a tabular form are used to organize monitoring information from tripped relays and circuit breakers and its relationship to fault location. Other fault diagnosis systems use the model-

Abstract: Rule-based representation techniques have become popular for storage and manipulation of domain knowledge in expert systems. It is important that systems using such a representation are verified for accuracy before implementation. In recent years, graphical techniques have been found to provide a good framework for the detection of errors that may appear in a rule base. The authors present a graphical representation scheme that: 1) captures complex dependencies across clauses in a rule base in a compact yet intuitively clear manner and 2) is easily automated to detect structural errors in a rigorous fashion. Their technique uses a directed hypergraph to accurately detect the different types of structural errors that appear in a rule base. The technique allows rules to be represented in a manner that clearly identifies complex dependencies across compound clauses. Subsequently, the verification procedure can detect errors in an accurate fashion by using simple operations on the adjacency matrix of the directed hypergraph. The technique is shown to have a computational complexity that is comparable to that of other graphical techniques. The graphical representation coupled with the associated matrix operations illustrate how directed hypergraphs are a very appropriate representation technique for the verification task.