Abstract: This paper describes an effort to model students' changing knowledge state during skill acquisition. Students in this research are learning to write short programs with the ACT Programming Tutor (APT). APT is constructed around a production rule cognitive model of programming knowledge, called theideal student model. This model allows the tutor to solve exercises along with the student and provide assistance as necessary. As the student works, the tutor also maintains an estimate of the probability that the student has learned each of the rules in the ideal model, in a process calledknowledge tracing. The tutor presents an individualized sequence of exercises to the student based on these probability estimates until the student has ‘mastered’ each rule. The programming tutor, cognitive model and learning and performance assumptions are described. A series of studies is reviewed that examine the empirical validity of knowledge tracing and has led to modifications in the process. Currently the model is quite successful in predicting test performance. Further modifications in the modeling process are discussed that may improve performance levels.

Abstract: Machine learning is the study of computational methods for improving performance by mechanizing the acquisition of knowledge from experience. Expert performance requires much domain-specific knowledge, and knowledge engineering has produced hundreds of AI expert systems that are now used regularly in industry. Machine learning aims to provide increasing levels of automation in the knowledge engineering process, replacing much time-consuming human activity with automatic techniques that improve accuracy or efficiency by discovering and exploiting regularities in training data. The ultimate test of machine learning is its ability to produce systems that are used regularly in industry, education, and elsewhere.

Abstract: Providing explanations for recommended actions is deemed one of the most important capabilities of expert systems (ES). There is little empirical evidence, however, that explanation facilities indeed influence user confidence in, and acceptance of, ES-based decisions and recommendations. This paper investigates the impact of ES explanations on changes in user beliefs toward ES-generated conclusions. Grounded on a theoretical model of argument, three alternative types of ES explanations A trace, justification, and strategy A were provided in a simulated diagnostic expert system performing auditing tasks. Twenty practicing auditors evaluated the outputs of the system in a laboratory setting. The results indicate that explanation facilities can make ES-generated advice more acceptable to users and that justification is the most effective type of explanation to bring about changes in user attitudes toward the system. These findings are expected to be generalizable to application domains that exhibit similar characteristics to those of auditing: domains in which decision making tends to be judgmental and yet highly consequential, and the correctness or validity of such decisions cannot be readily verified.

Abstract: Foreword L.A. Zadeh. Preface. 1. Overview of Intelligent Systems. 2. Research in Hybrid Intelligent Systems. 3. Expert Systems and Neural Networks.4. Industrial Experience: The Use of Hybrid Systems in the Power Industry. 5. Expert Networks. 6. Fuzzy Logic and Expert Systems. 7. Fuzzy Systems and Neural Networks. 8. Genetic Algorithms and Neural Networks. 9. Applications Using Hybrid Neural Networks with Fuzzy Logic and Genetic Algorithms. 10. Genetic Algorithms and Fuzzy Systems. 11. Adaptive Control of an Exothermic Chemical Reaction System Using Fuzzy Logic and Genetic Algorithms. 12. Genetic Algorithms and Expert Systems. 13. Hybrid Systems with Case-Based Reasoning. 14. Summary and the Future of Hybrid Intelligent Systems. References. Index.

Abstract: Publisher Summary This chapter discusses a knowledge representation, called a Bayesian network, that allows one to learn uncertain relationships in a domain by combining expert domain knowledge and statistical data. A Bayesian network is a graphical representation of uncertain knowledge that most people find easy to construct directly from domain knowledge. In addition, the representation has formal probabilistic semantics, making it suitable for statistical manipulation. Over the past decade, the Bayesian network has become a popular representation for encoding uncertain expert knowledge in expert systems. More recently, researchers have developed methods for learning Bayesian networks from a combination of expert knowledge and data. The techniques that have been developed are new and still evolving, but they have been shown to be remarkably effective in some domains. Learning using Bayesian networks is similar to that using neural networks. The process employing Bayesian networks, however, has two important advantages: (1) one can easily encode expert knowledge in a Bayesian network, and use this knowledge to increase the efficiency and accuracy of learning; and (2) the nodes and arcs in learned Bayesian networks often correspond to recognizable distinctions and causal relationships.

Abstract: In this paper, a hybrid model for short-term load forecast that integrates artificial neural networks and fuzzy expert systems is presented. The forecasted load is obtained by passing through two steps. In the first procedure, the artificial neural networks are trained with the load patterns corresponding to the forecasting hour, and the provisional forecasted load is obtained by the trained artificial neural networks. In the second procedure, the fuzzy expert systems modify the provisional forecasted load considering the possibility of load variation due to changes in temperature and the load behavior of holiday. In the test case of 1994 for implementation in the short term load forecasting expert system of Korea Electric Power Corporation (KEPCO), the proposed hybrid model provided good forecasting accuracy of the mean absolute percentage errors below 1.3%. The comparison results with exponential smoothing method showed the efficiency and accuracy of the hybrid model. >

Abstract: Artificial intelligence has been claimed to yield revolutionary advances in manufacturing. While most of the survey papers about artificial intelligence in manufacturing have been focused on knowledge-based expert systems, fewer attentions have been paid to neural networks. However, neural networks are able to learn, adapt to changes, and can mimic human thought processes with little human interventions. They could be of great help for the present computer-integrated manufacturing and the future intelligent manufacturing systems. This paper presents a state-of-the-art survey of neural network applications in manufacturing. The objective of this paper is to update information about the applications of neural networks in manufacturing, which will provide some guidelines and references for the research and implementation.

Abstract: RECONNAISANCE OF THE DOMAIN. Cluster Analysis: Why, What, How, When. Methods in Clustering Data. Examples and Discussion. Framing of Cluster Analysis Studies. Fuzzy Clustering: A Branch in Fuzzy Logic. RECONSIDERATION OF THE TASK. Indetermination and Uncertainty in Cluster Analysis. The Need and Relevance of Computer-assisted Reasoning in Cluster Analysis. COMPUTER-ASSISTED DECISION SUPPORT IN CLUSTER ANALYSIS. Knowledge-based Expert Systems: An Introduction. Rule Base Developments for Cluster Analysis. Case Study: Analysis of Delphind Sonar Sound Signals.

Abstract: 1. The Need For ObjectTechnology The Adaptable Business The Productive Developer The Satisfied User OT as the Oly Trinity 2. Inter-Operation, Reuse And Migration Inter-Operation of Object-Oriented Systems with Conventional IT Data Management Strategies D> Practical Problems with Migration to Object Technology Reusing Existing Software Components and Packages Combining Relational and Object-Oriented Databases Wrappers for Expert Systems and Blackboard Systems Using Object-Oriented Analysis as a Springboard 3. Building Graphical User Interfaces The Need for GUIs GUI Tools and Languages Designing the HCI GUI Standards Multi-media Systems, Virtual Reality and Optical Storage Case Studies 4. Distributed Systems, Databases And Object Management Modeling Distributed Systems The Client/Server Model Distributed Databases and Full-Content Retrieval Collaborative Work, Work Flow Automation and Graphics Network and Architectural Issues Object Request Brokers and Distributed Objects Case Studies Difficulties in Implementing Distributed and Client/Server Systems Case Studies 5. Building Expert Systems Fundamentals of Expert Systems Knowledge Representation Inference in Knowledge Based Systems Fuzzy Rules and Fuzzy Objects Frames and Objects Script Theory Blackboard Architectures Fuzzy and Neural Systems Implementation in an Expert Systems Environment Part II Migration Using SOMA 6. Object Modeling Basic Philosophy What is an Object-Oriented Analysis Method? The OMG and Abstract Object Models The Models of Software Engineering Objects Layers Finding Objects Structures Responsibilities Rules and Rulesets State Model Notation D>Fuzzy Extensions Deliverables 7. Requirements Capture And Analysis Object-Oriented Analysis Methods The Requirements Capture Process Context Modeling and the Environment Model Task Analysis: Task-Scripts, Subscripts, Component Scripts and Side-Scripts Identifying Objects Building the Object Model Refining the Task-Scripts to Identify Responsibilities Creating Class Cards and Walking Through the System Objects with Complex States Setting Priorities and Running Object-Oriented RAD Workshops 8. Strategic Modeling And Business Process Re-Engineering Object-Oriented Enterprise Modeling The Zachman Framework Modeling and Re-Engineering the Business Business Policy and Fuzzy Models Deliverables 9. Life-Cycle What Must an Object-Oriented Model Do? Life-Cycle Models RADs, Time Boxes and Evolutionary Development The SOMA Process Model General Project Management Tasks Roles, Skills and Responsibilities Hacking as a Structured Activity 10. Metrices, Estimation And Testing Metrics, Measures and Models Estimation Techniques Metrics for Object-Oriented systems Analysis The SOMA Metrics Testing Techniques Quality Measurement 11. Coordination And Reuse Component Management and Reuse Class Libraries and Library Control The Process Environment and Rools Designing for Reuse Repositories and CASE Tools Cross-Project Coordination 12. Moving To Physical Design And Implementation Converting Rules to Assertions Specification as Implementation and the Benefits of Prototyping The Shift of the Breakpoint (Continuum of Not?) Modeling Systems Dynamics Use of Effect Correspondence Diagrams and Other Matrix Techniques Physical Design Implementation in an Object-Oriented Language Implementation in a Conventional Language Integration of Class Libraries Code Generation Formal Methods and Logic Deliverables 13. Case Studies SOMA in SOMA Migrating a Large Software Product Building a Trading System Building a Graphical user Interface A Process Model for Migration Standards

Abstract: Expert systems (ES) were among the earliest branches of artificial intelligence (AI) to be commercialized. But how successful have they actually been? Many well-publicized applications have proven to be pure hype, numerous AI vendors have failed or been completely reorganized, major companies have reduced or eliminated their commitment to expert systems, and even Wall Street has become disillusioned -- a predicted $4 billion market proving to be smaller by an order of magnitude. Yet, in spite of these setbacks, there are many companies who remain enthusiastic proponents of the technology, and continue to develop important ES applications.The paper describes an investigation exploring how the first wave of commercial expert systems, built during the early and mid-1980s, fared over time. An important subset of these systems, identified in a catalog of commercial applications compiled in 1987, was located through a telephone survey, and detailed information on each systems was gathered. The data collected show that most of these systems fell into disuse or were abandoned during a five-year period from 1987 to 1992, while about a third continued to thrive. Quantitative and qualitative analysis of the data further suggested that the short-lived nature of many systems was not attributable to failure to meet technical performance or economic objectives. Instead, managerial issues such as lack of system acceptance by users, inability to retain developers, problems in transitioning from development to maintenance, and shifts in organizational priorities, appeared to be the most significant factors resulting in long term systems disuse.

Abstract: This paper presents a systematic study of various monitoring methods suitable,for automated monitoring of manufacturing processes. In general, monitoring is composed of two phases: learning and classification. In the learning phase, the key issue is to establish the relationship between monitoring indices (selected signature, features) and the process conditions. Based on this relationship and the current sensor signals, the process condition is then estimated in the classification phase. The monitoring methods discussed in this paper include pattern recognition, fuzzy systems, decision trees, expert systems and neural networks. A brief review of signal processing techniques commonly used in monitoring, such as statistical analysis, spectral analysis, system modeling, bi-spectral analysis and lime-,frequency distribution, is also included

Abstract: We present a critical discussion of research into the nature of design expertise, in particular evaluating claims that opportunism is a major influence on the behaviour of expert designers. We argue that the notion of opportunism has been under-constrained, and as a consequence the existence of opportunism in expert design has been exaggerated. Much of what has been described as opportunistic design behaviour appears to reflect a mix of breadth-first and depth-first modes of solution development. Whilst acknowledging that opportunities can arise in the design process (e.g. serendipitous solution discovery), such events might equally confirm structured behaviour as cause unstructured behaviour. We argue that the default mode for truly expert designers is typically a top-clown and breadth-first approach, since longer-term considerations of cost-effectiveness are more important for expert designers than short-term considerations of cognitive cost. However, there are situations (e.g. when faced with a highly unfamiliar design task) where it is cost-effective for experts to pursue a depth-first mode of solution development. The implications of our analysis for the development of methods and tools to support the design process are also discussed.

Abstract: This is a textbook for undergraduate and postgraduate students on machine learning, expert systems, and artificial intelligence courses. The text may also serve as a reference book for researchers in machine learning, knowledge based systems, genetic algorithms, and neural networks.

Abstract: A comprehensive list of ten major expert systems (ES) related factors likely to affect users' jobs has been defined, including problem importance, problem difficulty, developer skill, domain expert quality, user characteristics, user satisfaction, shell quality, user involvement, management support, and system usage. Impact on the job has been defined in terms of eleven items dealing with changes in job importance, amount of work, accuracy requirements, skills needed, job appeal, feed-back about performance, freedom in how to do the job, opportunity for advancement, job security, relation with peers, and job satisfaction. Data were collected on sixtynine expert systems developed through IBM's Corporate Manufacturing Expert Systems Project Center in San Jose, California. The results show that the major variables having the most impact on users' jobs are problem importance, problem difficulty, domain expert quality, user satisfaction with the ES, shell quality, and user involvement in ES development. Based on the results, recommendations are made for corporate and ES development managers to increase the likelihood that ES will have a desirable impact on users' jobs.

Abstract: During the past decade, object-oriented technology has found its way into programming languages, user interfaces, databases, operating systems, expert systems, etc. Products labeled as object-oriented database systems have been in the market for several years, and vendors of relational database systems are now declaring that they will extend their products with object-oriented capabilities. A few vendors are now offering database systems that combine relational and object-oriented capabilities in one database system. Despite these activities, there are still many myths and much confusion about object-oriented database systems, relational systems extended with object-oriented capabilities, and even the necessities of such systems among users, trade journals, and even vendors. The objective of lhis paper is to review the promises of object-oriented database systems, examine the reality, and how their promises may be fulfilled through unification with the relational technology.

Abstract: Computer security can be divided into two distinct areas, preventive security and the detection of security violations. Of the two, a greater degree of research and emphasis has been applied to prevention, while detection has been relatively overlooked. This is a costly oversight as preventive measures are never infallible. To date the detection of intruder violation on computer systems is a field heavily dominated by expert systems. However, the major drawbacks attributed to these systems including their heavy demand on system resources and their poor handling of the dynamic nature of user behaviour, have made their use infeasible. In practice, the effectiveness of intruder detection is heavily reliant upon the skills of the presiding system administrators and their knowledge of the behaviour of their users. The present study approaches the problem from a pattern recognition point of view, where a neural network is used to capture user behaviour patterns. It proposes that neural networks are not only capable of outperforming its heavier expert systems counterparts but in many ways better suits the demands and dynamic nature of the problem. In exploiting the strengths of neural networks in recognition, classification and generalisation this research illustrates the effectiveness of the neural network contribution to the application of intruder detection.

Abstract: Case-based reasoning is a technique recently developed to alleviate limitations of the rule-based expert systems. Instead of relying solely on rules, a case-based system maintains old cases in a case base. When a new problem is encountered, the system retrieves similar cases from the case base and constructs a solution to the new problem based on existing solutions. A key issue in case-based reasoning is how to index and retrieve similar cases. In this paper, we present a new approach that integrates fuzzy set concepts into the case indexing and retrieval process. This approach has a few advantages over existing methods. First, it allows numerical features to be converted into fuzzy terms to simplify the matching process. Second, it allows cases in different domains to be comparable. Finally, it allows greater flexibility in the retrieval of candidate cases.

Abstract: An expert system, such as could be used for service of a complicated physical device such as a printer or copier, exploits a knowledge base which is written in a markup language format such as SGML. The knowledge base comprises text which, if desired, can be printed out on paper to yield a traditional service manual. In addition to the typical formatting markup language tags surrounding the text of the knowledge base, hierarchical tags are provided in the electronic version of the knowledge base, to define a set of decision trees which can be accessed and navigated by an expert system. A diagnostic advisor can access specific elements of the knowledge base as needed to synthesize optimized diagnosis and repair procedures depending on an entry given by a tech rep servicing a machine. This arrangement thus supports both a printed service manual and a viewer that provides expert diagnostic advice.

Abstract: In this paper, we describe an expert consulting system for a dispatcher working in a courier service company. The system integrates interactive-graphic features and a learning module to support the dispatcher in his(her) task, and to suggest appropriate decisions when new requests come in. An experiment with a professional dispatcher is also reported.

Abstract: Documents an approach to sea ice classification through a combination of methods, both algorithmic and heuristic. The resulting system is a comprehensive technique, which uses dynamic local thresholding as a classification basis and then supplements that initial classification using heuristic geophysical knowledge organized in expert systems. The dynamic local thresholding method allows separation of the ice into thickness classes based on local intensity distributions. Because it utilizes the data within each image, it can adapt to varying ice thickness intensities to regional and seasonal changes and is not subject to limitations caused by using predefined parameters. >

Abstract: Automated knowledge acquisition is an important research issue in machine learning. Several methods of inductive learning, such as ID3 family and AQ family, have been applied to discover meaningful knowledge from large databases and their usefulness is assured in several aspects. However, since their methods are of a deterministic nature and the reliability of acquired knowledge is not evaluated statistically, these methods are ineffective when applied to domains essentially probabilistic in nature, such as medical domains. Extending concepts of rough set theory to a probabilistic domain, we introduce a new approach to knowledge acquisition, which induces probabilistic rules based on rough set theory (PRIMEROSE) and develop a program that extracts rules for an expert system from a clinical database, using this method. The results show that the derived rules almost correspond to those of the medical experts.

Abstract: Invited Papers: Ellsberg Paradox Intuition and Choquet Expected Utility (A Chateauneuf) Fuzzy Logic as Logic (P Hajek) Mathematical Foundations of Evidence Theory (J Kohlas) Semantics for Uncertain Inference Based on Statistical Knowledge (HE Kyburg) Prospects and Problems in Applying the Fundamental Theorem of Prevision as an Expert System: An Example of Learning about Parole Decisions (F Lad, I Coope) Coherent Prevision as a Linear Functional without an Underlying Measure Space: The Purely Arithmetic Structure of Logical Relations among Conditional Quantities (F Lad) Revision Rules for Convex Sets of Probabilities (S Moral, N Wilson) Contributed Papers: Generalized Concept of Atoms for Conditional Events (A Capotorti) Checking the Coherence of Conditional Probabilities in Expert Systems: Remarks and Algorithms (G Di Biase, A Maturo) A Hyperstructure of Conditional Events for Artificial Intelligence (S Doria, A Maturo) Possibilistic Logic and Plausible Inference (D Dubois, H Prade) Probability Logic as a Fuzzy Logic (G Gerla) Algorithms for Precise and Imprecise Conditional Probability Assessments (A Gilio) A Valuationbased Architecture for Assumptionbased Reasoning (R Haenni) 6 additional articles Index

Abstract: The reactive power source planning problem has a significant influence on secure and economic operation in electric power systems. To achieve both goals, system maximum security and minimum cost in operation, reactive power planning is posed as a multiobjective optimisation problem in terms of mathematical language. In the paper, the authors present an effective algorithm based on hybrid expert system simulated annealing (ESSA) to circumvent the complicated planning problem. A more practical problem formulation with multiobjectives and constraints is presented. Then, ESSA is introduced to search the global optimal solution considering both quality and speed at the same time. Simulation cases are used to evaluate the proposed algorithm.