Showing papers on "Applications of artificial intelligence published in 1992"

An architecture for real-time distributed scheduling

Abstract: Industrial managers, engineers, and technologists have many expectations from artificial intelligence and its application to knowledge-based systems. Although the past decade has witnessed a number of innovative applications of AI in manufacturing, the field is still in its infancy and holds even greater promise for the future. The AAAI Press book Artificial Intelligence Applications in Manufacturing, (from which the following article was selected) presents a number of articles that relate to the enhancement of planning and decision making capabilities in today's automated production environments.

TOPAZ: A Tool Kit for the Construction of Application-Specific Transaction Managers

Abstract: ‘Advanced database applications’, such as CAD/CAM, CASE, large AI applications or image and voice processing, place demands on transaction management which differ substantially from those in traditional database applications. In particular, there is a need to support ‘enriched’ data models, ‘synergistic’ cooperative work, and application- or user-supported consistency. Unfortunately, the demands are not only sophisticated but also diversified, which means that different application areas might even place contradictory demands on transaction management. This paper deals with these problems and offers a solution by introducing a flexible and adaptable tool kit approach for transaction management. This tool kit enables a database implementor or applications designer to assemble application-specific transaction managers. Each such transaction manager is meant to provide a number of individualized, application-specific transaction types. To be able to emulate each kind of application environment the nesting of transaction is supported. In particular, different transaction types can be executed in any order within such a hierarchy. Particular emphasis is placed on a flexible and comprehensive support of cooperative work.

What your computer really needs to know, you learned in kindergarten

Abstract: Research in distributed AI has led to computational techniques for providing AI systems with rudimentary social skills This paper gives a brief survey of distributed AI, describing the work that strives for social skills that a person might acquire in kindergarten, and highlighting important unresolved problems facing the field

Concept Support as a Method for Programming Neural Networks with Symbolic Knowledge

Abstract: Neural networks are usually seen as obtaining all their knowledge through training on the basis of examples. In many AI applications appropriate for neural networks, however, symbolic knowledge does exist which describes a large number of cases relatively well, or at least contributes to partial solutions. From a practical point of view it appears to be a waste of resources to give up this knowledge altogether by training a network from scratch. This paper introduces a method for inserting symbolic knowledge into a neural network-called “concept support.” This method is non-intrusive in that it does not rely on immediately setting any internal variable, such as weights. Instead, knowledge is inserted through pre-training on concepts or rules believed to be essential for the task. Thus the knowledge actually accessible for the neural network remains distributed or -as it is called-subsymbolic. Results from a test application are reported which show considerable improvements in generalization.

Artificial Intelligence Methods and Applications

Abstract: An introduction to artificial intelligence, N.G. Bourbakis fundamental methods for horn logic and AI applications, E. Kounalis and P. Marquis applications of genetic algorithms to permutation problems, F. Petry and B. Buckles extracting procedural knowledge from software systems using inductive learning in the PM system, R. Reynolds and E. Zannoni resource oriented parallel planning, S. Lee and K. Chung advanced parsing technology for knowledge based shells, J. Kipps analysis and synthesis of intelligent systems, W. Arden document analysis and recognition, S.N. Srihari et al signal understanding - an AI approach to modulation and classification, J.E. Whelchel et al and others.

Belief Revision: Conditionals and knowledge-base update

Abstract: Knowledge update has been a matter of concern to two quite separate traditions: one in philosophical logic, and another in artificial intelligence. In this paper we draw on both traditions to develop a theory of update, based on conditional logic, for a kind of knowledge base that has proven to be of interest in artificial intelligence. After motivating and formulating the logic on which our theory is based, we will prove some basic results and show how our logic can be used to describe update in an environment in which knowledge bases can be treated as truth-value assignments in four-valued logic. In keeping with Nuel Belnap's terminology in Belnap (1977a) and Belnap (1977b), we will refer to such truth-value assignments as set-ups or as four-valued set-ups . Paraconsistency, primeness, and atomistic update For the moment we will not say exactly what a four-valued set-up is. Instead we will describe informally some conditions under which it would be natural to structure one's knowledge base as a four-valued set-up. One of these conditions has to do with the treatment of inconsistent input; a second has to do with the representation of disjunctive information; the third concerns what kinds of statements can be the content of an update. Inconsistent input A logical calculus is paraconsistent if it cannot be used to derive arbitrary conclusions from inconsistent premises. Belnap argues in general terms that paraconsistent reasoning is appropriate any context where an automated reasoner must operate without any guarantee that its input is consistent, and where nondegenerate performance is desirable even if inconsistency is present. Knowledge bases used in AI applications are cases of this sort.

Book review: Exploration and Innovation in Design: Towards a Computational Model By D. Navinchandra (Springer Verlag, 1991)

Abstract: Workers in many areas of practical interest have come to rely daily on mature AI applications. Using AI tools, doctors diagnose diseases, technicians maintain complicated equipment, lenders qualify borrowers, and plant managers schedule and control manufacturing facilities. One domain that has not seen much practical support from AI is conceptual design. We think of design as more "creative" than other intellectual tasks, and that very label suggests, that we have fewer explicit models for what happens in design, and thus a weaker base on which to build applications. N's book brings together a number of AI techniques, some with original twists, into a cogent and lucid model for how machines can help with some types of design.

Applications of artificial intelligence in engineering VII

Abstract: Papers presented at the Seventh International Conference on Applications of Artificial Intelligence in Engineering, held at the University of Waterloo, Canada, July 1992.

Inside two commercially available statistical expert systems

Abstract: A decade of research into the applications of artificial intelligence in statistics has finally resulted in the appearance of commercially available statistical expert systems. This paper takes a closer look at two of these systems, which are now commercially available on microcomputers, and shows what knowledge they actually contain and how they operate. It is concluded that although the technology and concepts that drive these systems could still benefit from further improvement, the real challenge lies in defining and constructing the statistical knowledge and strategy that should be incorporated and in presenting the results to the user's full advantage.

Artificial Intelligence Applications in Power Systems

Abstract: Modem power systems become more and more complex and electrical networks become highly interconnected as the demands of electricity grow due to thie progress of society. There is a need for modem power systems to generate and to supply high quality electric energy to customers with very high degree of security. To achieve this requirement, in the last three decades, power engineers Pave employed computers to assist them to analyse, to plan and to operate power systems.

Neural networks: a new dimension in expert systems applications

Abstract: Despite significant advances in expert systems, efforts to build truly intelligent systems that approach reasoning and sensory ability of humans have not been rewarding. A new AI approach, neural networks, utilizes brain-like processing to emulate human learning. This approach will be the focus of commercial applications of AI in the 90s. This article will discuss major features of neural networks and address the impact of this approach on expert systems, as well as implications for research in this area.

Applied Artificial Intelligence: A SourceBook

Abstract: From the Publisher: The practical applications of artificial intelligence have grown considerably in the last decade. It is now possible to identify the problems best solved through AI and to forge some cost-effective solutions. This book documents the latest advances in knowledge-based systems design and development. It also places the information in context, offering an historical perspective on the rise of artificial intelligence. In a single reference, you'll find comprehensive descriptions of current applications of artificial intelligence. The book covers how to represent knowledge; use conventional programming languages to program knowledge-based systems; deal with uncertainty and ambiguity in knowledge processing; apply AI to manufacturing, law, airline scheduling, and national defense; relate AI to other fields and disciplines, and understand the contribution that neural networks might make.

AI research and applications in Digital's service organization

Abstract: The Digital Services Research Group and its predecessor groups and offshoots in Digital Equipment Corporation have been mobilizing leading-edge AI research to bear on real-life problems that face the corporation and its customers. The general strategy of the group is to explore emerging techniques relevant to service and support needs through developing rapid prototypes, deploying these prototypes, and incorporating feedback from users. With over 32 major projects undertaken during the past decade, we have worked on broad spectrum of problems and explored a variety of advanced AI techniques. This article describes the current AI activities in five areas: (1) enterprise advisory systems, (2) natural language processing and textual information retrieval, (3) largescale knowledge base management and access, (4) software configuration management, and (5) intrusion detection. We also list some future research directions.

On the implementation issues of a parallel expert system

Abstract: Recent progress in computing hardware technology has resulted in advances in the development of parallel computer systems. This new generation of computers offers advanced architectures and technologies for many AI applications. A new subfield of AI, called Distributed Artificial Intelligence, has emerged which is concerned with the co-operation solution of problems by a decentralized and loosely coupled collection of intelligent agents. In the paper, a parallel expert system called HOPES (Hierarchically Organized Parallel Expert System), is introduced. The system structure and multiblackboard architecture are presented and discussed. The focus of the paper will be on the implementation issues of the HOPES system. Although the so-called second generation expert systems technology has been around for some time, relatively little research effort has been put on implementing such systems. Thus, a major purpose of the paper is to provide general guidelines for implementations of parallel knowledge-based systems. The authors are concerned with two categories of hardware structures. First, multiprocessor system with common memory. Second, multiprocessor system without common memory. This paper will reveal some very important implementation problems and discuss key issues which are believed to be essential for implementing parallel/distributed knowledge-based systems.

The Artificial Intelligence Applications to Learning Programme

Abstract: The Artificial Intelligence Applications to Learning Programme has been funded since 1987 by what is now known as the Training, Enterprise and Education Directorate (TEED). The Programme aimed to explore and accelerate the use of AI technologies in learning, in both the educational and industrial sectors. The ten demonstrator projects were evaluated for their impact on industry and on further and higher education, while the project was in progress and later during its dissemination phase. The most useful outcomes of evaluation emerged during the latter phase, when the innovations had had an opportunity to become established and brought to market. There were issues related to technology-drive and the need to find problems for which the solution existed through group collaboration. One profitable line of development was to use AI to enrich training systems. An ideal training system must feel “good” to the client, should go beyond existing adaptive training systems, offer a high rate of training, be cost effective, have visual appeal, give sophisticated feedback, should fit closely with the user's current practice, and should have a shele life of more than 3 years.

Expressing relational and temporal knowledge in visual probabilistic networks

Abstract: Bayesian networks have been used extensively in diagnostic tasks such as medicine, where they represent the dependency relations between a set of symptoms and a set of diseases. A criticism of this type of knowledge representation is that it is. restricted to this kind of task, and that it cannot cope with the knowledge required in other artificial intelligence applications. For example, in computer vision, we require the ability to model complex knowledge, including temporal and relational factors. In this paper we extend Bayesian networks to model relational and temporal knowledge for high-level vision. These extended networks have a simple structure which permits us to propagate probability efficiently. We have applied them to the domain of endoscopy, illustrating how the general modelling principles can be used in specific cases.

Database and artificial intelligence integration: a challenge to academia

Abstract: Database (DB) and Artificial Intelligence (AI) courses have been long-standing offerings in computer science curriculums. Due to the present-day need for "intelligent" databases and "knowledge-base" management systems, the technologies of database and artificial intelligence are increasingly being integrated in research. Academia can give recognition to this important movement toward integration. An approach to teaching database and artificial intelligence concepts emphasizing their capabilities, limitations, and the need for integrating their technologies is proposed. An introduction gives a brief history of past and current practices. Reasons why the current routine should be modified are discussed. State-of-the-art information concerning current research in this area is presented, and finally, a course outline is suggested.

Artificial Intelligence and Large Scale Scientific Experiments

Abstract: As ever larger scientific endeavors are made, it becomes even more crucial that they be designed, performed, and analyzed very carefully. Artificial intelligence (AI) techniques are seen as a methodology for automating some of the tasks involved in large scale scientific experimentation. Scientific experimentation, in turn, is seen as a methodology for improving the capabilities of AI through the special demands it makes. This paper discusses how large scale scientific experimentation can be helped by AI and vice-versa. Large Scale Scientific Experiments Scientific experimentation has challenges that no other domain has to offer. It differs in large part by its exploratory nature which means that the theories and tools used to test the theory must be state of the art and so are not as reliable as traditional methods, such as those used in industrial applications. This is exemplified by the fact that an experiment is usually only performed one time, as opposed to an industrial application that are often performed many times. This means that expertise in an experiment is constantly evolving and puts extra demands on the management of it. Also, a scientific result demands quantitative verification to a level that exceeds most other domains. As scientific experiments become more and more complex they also become much more costly and it becomes imperative that the experiments be carefully designed to insure they will be able to meet their goals. High Energy Physics (HEP) is the biggest of "Big Science" endeavors and paradigmatic of large scale experimental science. As such, HEP can serve as a testbed for applications of intelligent computation technology to scientific experimentation. (In this paper, intelligent computation will refer to AI methods such as expert systems or learning programs.) At the same time, the special demands of scientific experimentation allow AI researchers a chance to improve their methodologies to handle more of the scenarios presented by experiments. Specifically, AI has a role in large experimental settings as a means of automating, at least to some extent, the design and data analysis of an experiment. In the design phase, AI can be used to verify the design of an experiment more thoroughly and quickly than can be done by scientists directly. The efforts of the scientists can then be focussed on the more abstract characteristics of the experiment while a program handles the computational details. This gives the scientist more time to conceptualize the experiment as well as spend time on other aspects of the experiment. In the data analysis phase, AI can be used to explore many more possible analyses of the data so that the most effective one can be found. AI has something to learn from experimental science as well. The Scientific Method has not been codified and any part of it that can be will improve the ability to do science.

A survey on the parallel distributed processing of production systems

Abstract: The importance of production systems in artificial intelligence (AI) has been repeatedly demonstrated by a large number of expert systems. As the number and size of expert systems grow, there has however been an emerging obstacle in such AI applications: the large processing time. The need for faster execution of production systems has spurred research in both the software and hardware domains, including connectionist architectures. This paper surveys various aspects of parallel distributed processing of production systems. Approaches taken to date to solve the problems associated with production systems are classified here into three levels: the algorithmic level, the parallel implementation level, and the connectionist level. Several pattern matchers and multiple rule firing principles are presented to demonstrate the algorithm level improvement. Several parallel implementation efforts are surveyed along with experimental results on real machines or with simulators. The presentation of three different types of connectionist production systems (local, distributed, and hierarchical representation) completes this survey. Finally, we explore some potential avenues towards the implementation of a true asynchronous parallel production system.

Artificial intelligence applications to communication network design with bulk facilities

Abstract: This paper presents a heuristic sytem for a special problem in communication network design with bulk facilities, called the TI problem.We apply AI to this problem. The knowledge acquired from an expert team is represented procedurally. Our work shows the promise of applying AI methodologies in solving network optimization problems.

Designing artificial intelligence applications in law: A systemic view

Abstract: Artificial intelligence applications development in law has historically focused on formal legal reasoning. Most of the systems are rule-based and none has yet become a fully functional prototype or commercially viable. The attempts to build large-scale systems without examining the intrinsic systemic nature of the legal process has resulted in limited operational success. The legal function, another area of legal activity, has emerged rapidly offering potential for artificial intelligence-based applications. This paper discusses the systemic differences between legal reasoning and legal function and suggests that different design methodologies be used in the two domains. Legal reasoning requires a holistic approach such as the blackboard model incorporating the properties of softness, openness, complexity, flexibility, and generality of legal systems, while traditional rule-based approaches are sufficient for legal function applications.

The Master of Science in Artificial Intelligence Program at the University of Georgia

Abstract: The interdisciplinary Master of Science program in Artificial Intelligence at the University of Georgia is intended to prepare students for careers as developers of artificial intelligence applications or for further graduate work in artificial intelligence or related areas. The program includes foundational courses in computer science, linguistics, logic, philosophy, and psychology as well as specialized courses in artificial intelligence programming languages and techniques. Seminars emphasize knowledge-based systems, natural language understanding, and logic programming. Students are admitted to the program with degrees in many areas including business, computer science, education, linguistics, philosophy, and psychology. A liberal undergraduate education with some previous experience in computing is desirable. It normally takes two years to complete all prerequisites, all required courses, and the thesis.

Computers in Artificial Intelligence Education

Abstract: SUMMARY Both the origin and development of artificial intelligence (AI) are connected with the origin and development of computers. Computers play a very important role in engineering education. AI influences such disciplines like CAD, CASE, CAE, and others. The specific experience concerning AI education at a technical university has been gathered in this paper. There is stressed need of good balance between theoretical background and individual training with computers as well as importance of personal experience in solving practical AI.