Showing papers on "Applications of artificial intelligence published in 1996"

Foundations of neural networks, fuzzy systems, and knowledge engineering

Abstract: From the Publisher: "Covering the latest issues and achievements, this well documented, precisely presented text is timely and suitable for graduate and upper undergraduate students in knowledge engineering, intelligent systems, AI, neural networks, fuzzy systems, and related areas. The author's goal is to explain the principles of neural networks and fuzzy systems and to demonstrate how they can be applied to building knowledge-based systems for problem solving. Especially useful are the comparisons between different techniques (AI rule-based methods, fuzzy methods, connectionist methods, hybrid systems) used to solve the same or similar problems." -- Anca Ralescu, Associate Professor of Computer Science, University of Cincinnati Neural networks and fuzzy systems are different approaches to introducing human-like reasoning into expert systems. This text is the first to combine the study of these two subjects, their basics and their use, along with symbolic AI methods to build comprehensive artificial intelligence systems. In a clear and accessible style, Kasabov describes rule- based and connectionist techniques and then their combinations, with fuzzy logic included, showing the application of the different techniques to a set of simple prototype problems, which makes comparisons possible. A particularly strong feature of the text is that it is filled with applications in engineering, business, and finance. AI problems that cover most of the application-oriented research in the field (pattern recognition, speech and image processing, classification, planning, optimization, prediction, control, decision making, and game simulations) are discussed and illustrated with concrete examples. Intended both as a text for advanced undergraduate and postgraduate students as well as a reference for researchers in the field of knowledge engineering, Foundations of Neural Networks, Fuzzy Systems, and Knowledge Engineering has chapters structured for various levels of teaching and includes original work by the author along with the classic material. Data sets for the examples in the book as well as an integrated software environment that can be used to solve the problems and do the exercises at the end of each chapter are available free through anonymous ftp.

Foundations of distributed artificial intelligence

Abstract: Partial table of contents: FORMULATIVE READINGS. Logical Foundations of Distributed Artificial Intelligence (E. Werner). Distributed Artificial Intelligence Testbeds (K. Decker). COOPERATION, COORDINATION, AND AGENCY. Coordination Techniques for Distributed Artificial Intelligence (N. Jennings). Negotiation Principles (H. Muller). Planning in Distributed Artificial Intelligence (E. Durfee). DAI FRAMEWORKS AND THEIR APPLICATIONS. IMAGINE: An Integrated Environment for Constructing Distributed Artificial Intelligence Systems (D. Steiner). AGenDA--A General Testbed for Distributed Artificial Intelligence Applications (K. Fischer, et al.). Agent Factory: An Environment for the Fabrication of Multiagent Systems (G. O'Hare). RELATED DISCIPLINES. Philosophy and Distributed Artificial Intelligence: The Case of Joint Intention (R. Tuomela). User Design Issues for Distributed Artificial Intelligence (L. Hall). Appendix. Index.

AI techniques in induction machines diagnosis including the speed ripple effect

Abstract: Various applications of artificial intelligence (AI) techniques (expert systems, neural networks, and fuzzy logic) presented in the literature prove that such technologies are well suited to cope with on-line diagnostic tasks for induction machines. The features of these techniques and the improvements that they introduce in the diagnostic process are recalled, showing that, in order to obtain an indication on the fault extent, faulty machine models are still essential. Moreover, by the models, that must trade off between simulation result effectiveness and simplicity, it is possible to overcome crucial points of the diagnosis. With reference to rotor electrical faults of induction machines, a new and simple procedure based on a model which includes the speed ripple effect is developed. This procedure leads to a new diagnostic index, independent of the machine operating condition and inertia value, that allows the implementation of the diagnostic system with a minimum configuration intelligence.

Introduction to sports biomechanics

Abstract: This article reviews developments in the use of Artificial Intelligence (AI) in sports biomechanics over the last decade It outlines possible uses of Expert Systems as diagnostic tools for evaluating faults in sports movements ('techniques') and presents some example knowledge rules for such an expert system It then compares the analysis of sports techniques, in which Expert Systems have found little place to date, with gait analysis, in which they are routinely used Consideration is then given to the use of Artificial Neural Networks (ANNs) in sports biomechanics, focusing on Kohonen self-organizing maps, which have been the most widely used in technique analysis, and multi-layer networks, which have been far more widely used in biomechanics in general Examples of the use of ANNs in sports biomechanics are presented for javelin and discus throwing, shot putting and football kicking I also present an example of the use of Evolutionary Computation in movement optimization in the soccer throw in, which predicted an optimal technique close to that in the coaching literature After briefly overviewing the use of AI in both sports science and biomechanics in general, the article concludes with some speculations about future uses of AI in sports biomechanics Key PointsExpert Systems remain almost unused in sports biomechanics, unlike in the similar discipline of gait analysisArtificial Neural Networks, particularly Kohonen Maps, have been used, although their full value remains unclearOther AI applications, including Evolutionary Computation, have received little attention

A Methodology for simplification and interpretation of backpropagation-based neural network models

Abstract: A new methodology for building inductive expert systems known as neural networks has emerged as one of the most promising applications of artificial intelligence in the 1990s. The primary advantages of a neural network approach for modeling expert decision processes are: (1) the ability of the network to learn from examples of experts' decisions that avoids the costly, time consuming, and error prone task of trying to directly extract knowledge of a problem domain from an expert and (2) the ability of the network to handle noisy, incomplete, and distorted data that are typically found in decision making under conditions of uncertainty. Unfortunately, a major limitation of neural network-based models has been the opacity of the inference process. Unlike conventional expert system decision support tools, decision makers are generally unable to understand the basis of neural network decisions. This problem often makes such systems undesirable for decision support applications. A new methodology is presented that allows the development of highly simplified backpropagation neural network models. This methodology simplifies netw variables that are not contributing to the networks ability to produce accurate predictions. Elimination of unnecessary input variables directly reduces the number of network parameters that must be estimated and consequently the complexity of the network structure. A primary benefit of this development methodology is that it is based on a variable importance measure that addresses the problem of producing an interpretation of a neural network's functioning. Decision makers may easily understand the resulting networks in terms of the proportional contribution each input variable is making in the production of accurate predictions. Furthermore, in actual application the accuracy of these simplified models should be comparable to or better than the more complex models developed with the standard approach. This new methodology is demonstrated by two classification problems based on sets of actual data.

The challenge of artificial intelligence

Abstract: Artificial intelligence (AI) is a relatively young discipline, yet it has already led to general-purpose problem-solving methods and novel applications. Ultimately, AI's goals of creating models and mechanisms of intelligent action can be realized only in the broader context of computer science. Creating mechanisms for sharing of knowledge, knowhow, and literacy is the challenge. The great Chinese philosopher Kuan-Tzu once said: "If you give a fish to a man, you will feed him for a day. If you give him a fishing rod, you will feed him for life." We can go one step further: If we can provide him with the knowledge and the know-how for making that fishing rod, we can feed the whole village. Therein lies the promise-and the challenge-of AI.

LispWeb: a specialized HTTP server for distributed AI applications

Abstract: We describe the design and the implementation of LispWeb , a specialized HTTP server, written in Common Lisp, able to deliver Distributed Artificial Intelligence ( DAI ) applications over the World Wide Web ( WWW ) In addition to implementing the standard HTTP protocol, the LispWeb server offers a library of high-level Lisp functions to dynamically generate HTML pages, a facility for creating Graphical User Interfaces on the WWW through dynamically generated image maps, and a server-to-server communication method ( STSP ) LispWeb is intended to act as the front-end of a network of intelligent agents that communicate with each other using an extension to the HTTP protocol The dynamic generation of HTML pages allows complex AI applications to be delivered to end-users without the need for specialized hardware and software support, and using a simple and homogeneous interface model

Intelligent Quality Systems

Abstract: This study discusses Quality Systems employing techniques from the field of Artificial Intelligence (AI). It focuses upon expert systems and neural networks, two of the most popular AI techniques. Expert Systems encapsulate human expertise for solving complex problems. Neural Networks are able to learn problem solving from examples. The authors illustrate applications of these techniques to the design and operation of effective quality systems. Readers with a background in quality engineering and manufacturing will be able to learn about the uses of expert systems and neural networks to achieve intelligent Statistical Process Control, monitor processes and detect incipient faults in them, design experiments and predict performance, inspect products and monitor and diagnose plants and processes. Readers with an AI background will find a wealth of ideas for practical problems on which to deploy and test their techniques.

Incremental algorithms for managing temporal constraints

Abstract: This paper addresses the problem of efficiently updating a network of temporal constraints when constraints are removed from or added to an existing network. Such processing tasks are important in many AI applications requiring a temporal reasoning module. First we analyze the relationship between shortest-paths algorithms for directed graphs and arc-consistency techniques. Then we focus on a subclass of STP for which we propose new fast incremental algorithms for consistency checking and for maintaining the feasible times of the temporal variables.

Planning in Dynamic Environments: The DIPART System

Abstract: Many current and potential AI applications are intended to operate in dynamic environments, including those with multiple agents. As a result, standard AI plan-generation technology must be augmented with mechanisms for managing changing information, for focusing attention when multiple events occur, and for coordinating with other planning processes. The DIPART testbed (Distributed, Interactive Planner’s Assistant for Real-tlme Transportation pIanning) was developed to serve as an experimental platform for analyzing a variety of such mechanisms. In this paper, we present an overview both of the DIPART system and of some of the methods for planning in dynamic environments that we have been investigating using DIPAI~T. Many of these methods derive from theoretical work in real-time AI and in related fields, such as real-tlme operating systems.

AI and navigation on the Internet and Intranet

Abstract: Recent research has focused on using AI to harness the World Wide Web. Although intelligent agents are one of the most visible uses of AI on the WWW, substantial hype surrounds such usage. Oren Etzioni and Daniel Weld (1995) analyze the fact, fiction, and forecast of intelligent agents on the WWW and distinguish between the hype and the reality. The analysis summarizes some of the work discussed and demonstrated at the Fall Symposium on AI Applications in Knowledge Navigation and Retrieval, sponsored by the American Association for Artificial Intelligence. In addition, the analysis investigates subsequent and related research in this rapidly changing field. Finally, I investigate some of the implications of these recent developments and isolate some gaps in the current research. I give particular attention to the impact of such systems on issues such as privacy and electronic commerce.

Relevance and insight in experimental studies

Abstract: As its name suggests, artificial intelligence is a science of the artificial. As with other conscious creations, there is a great temptation to assume that we can understand the behavior of AI systems entirely through formal analysis. However, the complexity of most AI constructs makes this impractical, forcing us to rely on the same experimental approach that has been so useful in the natural sciences. Many of the same issues and methods apply directly to AI systems, including the need to identify clearly one's dependent and independent variables, the importance of careful experimental design, and the need to average across random variables outside one's control. However, beyond these obvious features, a compelling experimental study of intelligent behavior must satisfy two additional criteria: it must have relevance and it must produce insight. I will illustrate these ideas with examples from machine learning, one of the most experimentally oriented subfields within artificial intelligence. Moreover, because AI researchers are often concerned with extending some existing method to improve its behavior, I will focus on this paradigm.

Artificial intelligence in bridge engineering

Abstract: The idea to use artificial intelligence (AI) in civil engineering is as old as AI itself. Since the 1950s, studies on AI applications in civil or bridge engineering have proliferated. Most of these studies have dealt with specialized isolated engineering subtasks. Few of the applications have been delivered to practitioners and were used to advance their work. This paper presents a model of the life-cycle flow of information in bridge engineering as an organizing framework for reviewing previous work on AI applications in bridge engineering. Several common patterns that emerge from the studies are summarized. A subsequent analysis of the status of the bridge stock in many countries suggests that a more integrated approach to AI applications may have a larger practical impact. Several practical areas that can benefit significantly from AI techniques are identified, and several studies are proposed including the AI technology needed and the methodology according to which these applications should be developed.

The Innovative Applications of Artificial Intelligence Conference: Past and Future

Abstract: This article is a reflection on the goals and focus of the Innovative Applications of Artificial Intelligence (IAAI) Conference. The author begins with an historical review of the conference. He then goes on to discuss the role of the IAAI conference, including an examination of the relationship between AI scientific research and the application of AI technology. He concludes with a presentation of the new vision for the IAAI conference.

Applications of artificial intelligence for quality control at hot strip mills

Abstract: The quality control in hot strip mills usually include thickness, width, shape, flatness, yield strength, tensile strength, ductility, etc.. This research takes the width control at the roughing mill of a hot strip mill as an example of Al applications for the quality control of the hot strip. The width control consists of the bar-to-bar width control for the mean width of bars, the in-bar width control for the width variation within bars and the head/tail width control for reducing the crop loss at the crop-shear in front of the finishing mills. Back-Propagation (BP) neural networks and Radial Basis Function (RBF) neural networks were applied to model and predict the bar-to-bar width and the in-bar width. The training and the testing of the neural networks are based on the data collected from the B H P Steel S P P D roughing mill. Bias and momentum are used in the learning process of B P networks for speeding up the learning process. Also Cauchy method is applied here to avoid the local minimum of the learning process. Moreover, polynomial regression models were developed for the comparison between the neural network models and the regression models. The comparison is also conducted for the performances between the B P networks and the R B F networks. The factor analysis both by B P networks and the regression models are used to show the most effective parameters for the width variation. The performance of the head & tail stroking system is dependent on the original head/tail width shape of the incoming bar and the trace of the edger roll for the stroking. The original shapes can be classified as a limited number of basic shapes. O n the other hand, the trace of the edger roll for the stroking can be represented by three parameters. Based on expert knowledge, B P neural networks are set up for representing the relationships between the basic shapes and the stroking parameters. Well trained networks can be used

Applications of Artificial Intelligence and Cognitive Science Techniques in Banking

Abstract: In this paper we propose to develop some cognitive science techniques which could be useful for several domains of banking. One of our main topics will be decision support systems and knowledge-based decision support systems. Thus we have to consider the knowledge acquisition stage which is known as the bottleneck in the construction of these systems. We will present a model for learning strategies established by a decision maker for a feature task of categorical judgment of objects described by several attributes. It has been improved for several domains and we will show an application to understand how individuals categorize savings plans. This knowledge will be useful for the bank consultant to be able to advise exactly what his/her clientele wants to have. To finish, some applications in the credit field, training systems, and portfolio management are briefly discussed.

Artificial intelligence in economics and management : an edited proceedings on the Fourth International Workshop : AIEM4, Tel-Aviv, Israel, January 8-10, 1996

Abstract: Foreword. Part I: Artificial Intelligence Techniques. Using Machine Learning, Neural Networks And Statistics to Predict Corporate Bankruptcy: A Comparative Study P.P.M. Pompe, A.J. Feelder. Prolog Business Objects in a Three-Tier Architecture D.G. Schwartz. The Effect of Training Data Set Size and the Complexity of the Separation Function on Neural Network Classification Capability: The Two-Group Case M. Leshno, Y. Spector. Imaginal Agents D.G. Schwartz, D. Te'eni. Part II: Financial Applications. Financial Product Representation and Development Using a Rule-Based System A. Lange, et al. Applications of Artificial Intelligence and Cognitive Science Techniques in Banking P. Lenca. Part III: Business Applications. AI-Supported Quality Function Deployment Y. Reich. Knowledge Reuse in Mass Customization of Knowledge-Intensive Services M. Benaroch. Harvest Optimization of Citrus Crop Using Genetic Algorithms N. Levin, J. Zahavi. `Corpus', An Approach to Capitalizing Company Knowledge M. Grundstein. Part IV: Economic Applications. Fuzzy Approach in Economic Modelling of Economics of Growth V. Deinichenko, et al. Computer Based Analysis of an Economy in Transition to Steady State Equilibrium K. Cichocki, T. Szapiro. A Multistrategy Conceptual Analysis of Economic Data K.A. Kaufman, R.S. Michalski. The Credible Modeling of Economic Agents with Limited Rationality B. Edmonds, S. Moss. Reasoning and A Programming Language for Simulating Economic and Business Processes with Artificially Intelligent Agents B. Edmonds, et al. Part V: Qualitative and Cognitive Research. Information Processing, Motivation and Decision Making L.M. Botelho, H. Coelho. A PracticalTool for Explanation of Quantitative Model Behavior R. Berndsen. Practical Application of Artificial Intelligence in Education and Training L. Dannhauser.

Applications of artificial intelligence in engineering XI

Abstract: Knowledge representation neural networks genetic algorithms constraint propagation integration of design and manufacturing concurrent engineering surveillance systems fault diagnosis multimedia and man/machine communication evaluation and selection modelling uncertainties evaluation. biomedical engineering civil engineering environmental engineering agriculture electronics. (Part contents).

Well-Behaved IDL Theories

Abstract: The field of nonmonotonic logic, sixteen years old now, is devoted to solve the problem of reasoning under incomplete knowledge, whose good understanding is essential to the construction of AI as a science and whose relevance reaches far beyond AI applications. During these years, many insights have been accumulated in the form of desirable properties the proposed formalisms should exhibit and of criticisms on the available solutions. This paper takes advantage on this experience to derive from them a sort of canon to be imposed to nonmonotonic formalisms. This canon is translated as a set of etiquette rules guiding knowledge representation into theories framed within the Inconsistent Default Logic, IDL. It is then established the important result that IDL produces a unique extension for a theory constructed according to these rules. This result calls forth IDL as an interesting alternative to credulous common sense reasoning formalization fulfilling many desired properties.

Robots in the AI Classroom: What Smart Machines Can Teach Smart Students

Abstract: The design and implementation of autonomous robots provides experience with engineering problems as well as with hard problems in artificial intelligence. Our aims in this article are fourfold: First, we describe how the use of robots complements traditional classroom lectures for the teaching of important concepts in a graduate‐level AI class. Second, we discuss the use of robots as a multimedia tool for capturing student interest and facilitating the self‐guided exploration of AI concepts. Third, we relate readings and robots in the curriculum and show how the robots aid understanding of philosophical issues in AI. Finally, we describe the robot kits and the organization of the class, present several completed projects by student teams, and report some of the feedback given by students who completed the course. We also analyze the successes and failures of the first two courses offered and describe the changes made for the recently completed second course.

Temporal reasoning methodologies used in AI applications for power system control centers

Abstract: The results already obtained with intelligent real time applications in power systems show that artificial intelligence techniques are adequate and useful for solving some problems for which traditional programming techniques are not able to provide good solutions On the other hand, the duration of this kind of project is still rather long and the total number of deployed systems all over the world is still very low This is due to the complex issues that real time applications for power systems must deal with, among which temporal reasoning plays a key role This paper presents the most important temporal reasoning requirements for real-time applications in power systems It also presents the methods used in some systems that have been developed to deal with temporal reasoning, with particular emphasis on SPARSE, an expert system for fault analysis and service restoration, developed for Portuguese Control Centers

Artificial Intelligence Applications in Aircraft Systems.

Abstract: : Air Operations Division at the DSTO Aeronautical and Maritime Research Laboratory is developing a capability in the use of Artificial Intelligence (A I), including knowledge based systems technology, in applications related to the operation and support of aircraft systems. A survey of the work program of Air Operations Division was undertaken to identify opportunities offered by advanced computing techniques for the solution of existing research problems. This document describes the findings of the survey. Some of the research opportunities identified have been pursued, and a brief description of progress is provided.

Chapter 8 Artificial intelligence in economics and finance: A state of the art — 1994: The real estate price and assets and liability analysis case

Abstract: Publisher Summary This chapter emphasizes specific contributions, advantages, and weaknesses of artificial intelligence (AI) techniques various purposes: (1) knowledge-based reasoning that applies heuristic knowledge to make policy search more robust, or to satisfy trading principles in a competitive economy, (2) machine learning to learn the behavior of economic agents, (3) decision rationalization in decision support systems, and case-based reasoning, and (4) integration of databases and knowledge bases via suitable knowledge representations. In the real world of economic analysis, AI approaches must be scalable and tunable to changing characteristics without having to change the underlying techniques or algorithms. In economic applications, better explanation-based interfaces are necessary between the user and the system. From the perspective of business, almost no AI research addresses economic competition theories, either with reference to game theory, or to disequilibrium theories. The strongest potential of some AI techniques lies in their data/information fusion capability, which is little explored. This holds especially for neural networks, case-based reasoning, and knowledge representation standards.