Showing papers in "IEEE Intelligent Systems in 1996"

Data mining and knowledge discovery: making sense out of data

Abstract: Current computing and storage technology is rapidly outstripping society's ability to make meaningful use of the torrent of available data. Without a concerted effort to develop knowledge discovery techniques, organizations stand to forfeit much of the value from the data they currently collect and store.

Distributed intelligent agents

Abstract: In Retsina, the authors have developed a distributed collection of software agents that cooperate asynchronously to perform goal-directed information retrieval and integration for supporting a variety of decision-making tasks. Examples for everyday organizational decision making and financial portfolio management demonstrate its effectiveness.

Rapidly adapting machine vision for automated vehicle steering

Abstract: The Ralph vision system helps automobile drivers steer, by sampling an image, assessing the road curvature, and determining the lateral offset of the vehicle relative to the lane center. Ralph has performed well under extensive tests, including a coast-to-coast, 2,850-mile drive.

Agent-based engineering, the Web, and intelligence

Abstract: Web based agents show great potential for design and engineering applications. To integrate engineering agents into the Web, researchers must resolve the conflict between HTTP's client server protocol and the peer to peer protocol required by agents. The author surveys the types and definitions of agents, eventually focusing on those useful for engineering, and on how they can be integrated with the World Wide Web. Because it is simply silly to discuss software agents without distinguishing them from other types of software, the author ventures to offer a definition. It will be iconoclastic and perhaps applicable only to a certain type of engineering agent. But it will be useful in identifying some technical implementation issues.

Neural network control of robot manipulators

Abstract: The author describes neural network controllers for robot manipulators in a variety of applications, including position control, force control, parallel-link mechanisms, and digital neural network control. These "model-free" controllers offer a powerful and robust alternative to adaptive control.

Neural networks for computer virus recognition

Abstract: We have developed a neural network for generic detection of a particular class of computer viruses-the so called boot sector viruses that infect the boot sector of a floppy disk or a hard drive. This is an important and relatively tractable subproblem of generic virus detection. Only about 5% of all known viruses are boot sector viruses, yet they account for nearly 90% of all virus incidents. We have successfully deployed our neural network as a commercial product, distributing it to millions of PC users worldwide as part of the IBM AntiVirus software package. We faced several challenges in taking our neural network from a research idea to a commercial product. These included designing an appropriate input representation scheme; dealing with the scarcity of available training data; finding an appropriate trade off point between false positives and false negatives to conform to user expectations; and making the software conform to strict constraints on memory and speed of computation needed to run on PCs. The article discusses our methods for handling these challenges.

Reality check for data mining

Abstract: Data-mining tools let business managers make profitable use of the massive quantities of information their companies collect. This article looks at two particularly useful data-mining applications.

Using Archon to develop real-world DAI applications. 1

Abstract: Archon provides a software framework that assists interaction between the subcomponents of a distributed AI application, and a design methodology that helps structure these interactions. The Archon project has been applied to several real world industrial applications. Two of these applications, electricity transportation management and particle accelerator control, have run online in the organizations for which they were developed-Iberdrola, a Spanish electric utility, and the European Laboratory for Particle Physics (CERN). Archon's problem solving entities are called agents; they can control their own problem solving and interact with other community members. The interactions typically involve agents cooperating and communicating with one another to enhance their individual problem solving and to better solve the overall application problem. Each agent consists of an Archon layer and an application program (known as an intelligent system).

Al models for business process reengineering

Abstract: Most models fail to capture the rationale behind processes, making business reengineering less effective. The authors describe their I* framework, which views organizations as collections of actors with strategic interests, and interdependencies involving goals, tasks, and resources. The authors discuss the ConGolog framework, which supports reasoning about the dynamics of processes under incomplete knowledge.

Constructing Bayesian networks to predict uncollectible telecommunications accounts

Abstract: The complexities of building models that can predict whether a customer account or transaction is collectible are greater than most current learning systems can handle. The authors describe software that builds Bayesian network models for such predictions. They also examine how varying model parameters and hence model structure can affect predictive accuracy.

Expert systems: a view of the field

Abstract: Reports of the decline of expert systems are greatly exaggerated. Survey results indicate impressive growth, as researchers develop systems to tackle difficult but commercially rewarding problems.

Hierarchical distributed genetic algorithms: a fuzzy logic controller design application

Abstract: Unlike conventional genetic algorithms, HDGAs use a multiresolutional search scheme and change structure to achieve a goal. In this application, an HDGA investigates various configurations dynamically to find the optimal design of a fuzzy logic controller for a complex, unmanned, space-based plant.

Developing case-based reasoning for structural design

Abstract: Case-based systems enable users to retrieve previously known designs from memory and adapt them to fit the current design problem. The four case-based design systems described in the paper illustrate how various implementations achieve design assistance or design automation objectives.

Expert systems as knowledge servers

Abstract: Wide-area networks and the Internet-based World Wide Web allow developers to provide intelligent knowledge servers. Expert systems running on servers can support a large group of users who communicate with the system over the network. In this approach, user interfaces based on Web protocols provide access to the knowledge servers. Users do not need special hardware or software to consult these services with appropriate Web browsers.

Data mining and forecasting in large-scale telecommunication networks

Abstract: Large-scale telecommunication networks process millions of transactions daily. The authors present an approach for warehousing data about faulty networks and for mining it to find trends. Applying this approach to AT&T's worldwide network, the authors have identified several patterns, which AT&T can use to improve network reliability.

Visualization support for data mining

Abstract: WinViz uses parallel coordinates, a computational geometry method, to let users visually formulate queries and analyze results. When integrated with machine-learning algorithms, WinViz provides a powerful tool for data mining.

Stock selection using rule induction

Abstract: High-quality financial databases have existed for many years, but human analysts can only scratch the surface of the wealth of knowledge buried in this data. Using the rule-induction technology in the Recon data-mining system, an investment strategy based purely on the learned rules can generate significant profits.

Conceptual, collaborative building design through shared graphics

Abstract: The Interdisciplinary Communication Medium computer environment integrates a shared graphic modeling environment with network-based services to accommodate many perspectives in an architecture/engineering/construction team.

Scalable discovery of informative structural concepts using domain knowledge

Abstract: The subdue system evaluates the benefits of using domain knowledge to guide the discovery of repetitive, functional substructures in large structural databases. Results show that domain-specific knowledge improves the search for such substructures and enables greater data compression.

A profile of the Australian Artificial Intelligence Institute [World Impact]

Abstract: architectures. To make the theory of BDI agents more practical, we need the notion of plans supplied in advance, rather than generated by the agent. For such agents, deliberation relates to selecting a plan. Plan execution consists of the hierarchical expansion of these plans, guided by a means-end analysis. Augmented with plans, we can provide an abstract architecture of BDI agents and relate it to implemented systems such as dMARS. Team-oriented systems. By extending the notion of single agents, we have investigated multiple agents working as a team and the associated theory of mutual beliefs, joint goals, and joint intentions. As a natural extension of plans, we have joint plans that act as recipes or coordination protocols for multiple agents. This is elaborated in our research on planned team a~t ivi ty .~ Reactive plan recognition. An agent’s recognition of the mental state (beliefs, desires, plans, and intentions) of other agents is an important part of intelligent activity. Doing this with limited resources and with a continuously changing environment is a challenge. We have extended the philosophy of using plans to this task, and call the approach reactive plan recognition. We provide algorithms for reactive plan recognition and embed them in the framework of agent-based reasoning. This results in a model for mental-state recognition with integrated reactive plan execution and recognition. This approach has been applied in an air-combat model to enable pilots to infer their opponents’ mental state and choose their tactics accordingly. Agent-oriented methodology. Extensive work with end users initiated a research program to enable software analysts and engineers, rather than researchers, to design, implement, and maintain BDI systems. We developed an agent-oriented methodology and modeling technique for systems of agents based on object-oriented models. By expanding existing techniques, we can produce an approach that those familiar with the obejct-oriented paradigm can easily learn and ~nderstand.~ Agent-oriented languages. We developed an agent-oriented language, Agentspeak, that captures the essential features of BDI agents. It can be viewed as a simplified, textual language of an agent-based system such as dMARS. Agentspeak is a programming language based on a restricted first-order language with events and actions. Unlike our other work, the agent’s beliefs, desires, and intentions are not explicitly represented. This shift in perspective from an external viewpoint is likely to have a better chance of unifying theory and practice. Experimentation. The AA11 performs experiments on constrained and welldefined domains to investigate how commitment to goals contributes to effective behavior. We also compare different strategies for reacting to change. The results demonstrate the feasibility of developing systems that empirically measure agent performance. The combination of c o m t ment with intelligent reactive replanning results in optimal behaviors.

Applying AI to structural safety monitoring and evaluation

Abstract: Four decision-support systems: Mistral, Damsafe, Kaleidos, and Igor provide powerful AI-based tools for evaluating structural data. The paper considers how safety managers, engineers, and authorities are using the systems to handle safety problems in structures.

Knowledge-based assistance for finite-element modeling

Abstract: The authors propose a knowledge-based framework for assisting users in setting up, interpreting, and hierarchically refining finite-element models in a structural engineering domain. The central mechanism for providing modeling assistance is the explicit representation and incremental activation and refraction of modeling assumptions that operate on functional descriptions.

A framework for the development of multiagent architectures

Abstract: A high-performance software system provides the necessary facilities to experiment with various multiagent-coordination choices at different abstraction levels. The authors discuss these abstractions and empirically evaluate their usefulness for the construction of distributed systems.

A constraint-based high school scheduling system

Abstract: Constructing annual class schedules for a typical Japanese high school consumes hundreds of hours. The Windows-based SchoolMagic scheduling system uses an arc-consistency algorithm to generate high-quality initial assignments, which it then refines with a hill-climbing algorithm to reduce scheduling time 50-fold.

Intelligent executive information systems

Abstract: There have been substantial changes in the technology available to support executive decision making. Perhaps the most visible change has been the rapid development of the Internet and the World Wide Web. In addition, this network infrastructure has facilitated and promoted the growth of enabling technologies, such as databases and artificial intelligence. These changes in technology have led to a change in the basic nature of executive information systems. Accordingly, the purpose of the article is to extend the structure of EISs to account for this wide range of recent technological changes.

Artificial neural networks for the presetting of a steel temper mill

Abstract: Studies about presetting temper mills have traditionally used mathematical tools. But artificial neural networks can help solve the problem of modeling complex functions in high-dimensional spaces. On-line implementation of an ANN at a temper mill plant has led to a hybrid model that mixes symbolic and connectionist modules.

The digital library as a community of information agents

Abstract: sound decisions. Again, decision-theoretic agents will be able to apply economic and game-theoretic models for dealing with multiagent interactions. These tools include various mechanisms such as auctions, bidding schemes, and negotiation strategies. Finally, there will be the need and opportunity to conduct system-level analyses of the multiple agents, investigating the roles of system-wide constraints on behavior, whether these are imposed by the library administration (“artificial social laws”) or arrived at dynamically through gradual adaptation (“artificial social conventions”). In short, digital libraries offer an interesting intellectual playground, and within it, the notion of information agents presents an exciting new challenge. We believe that AI has the right set of tools to tackle this challenge, with contributions from multiple areas, including knowledge representation, reasoning about uncertainty, and multiagent systems. However, the new challenge will stretch and test these tools in novel ways, which will benefit the community as a whole.

Planning cordless business communication systems

Abstract: The Popular tool uses constraint-based programming to optimize the placement of base stations for local wireless communication.

Scheduling high-grade steelmaking

Abstract: This expert system for scheduling high-grade steel production cuts engineering planning time, allows for greater what-if experimentation, and improves quality control. The complexity of production-cycle scheduling problems had defeated earlier, purely conventional software approaches.

Intelligent Agents: Where AI Meets Information Technology [Guest Editorial]

Abstract: The articles in this special issue discuss intelligent agents, with an emphasis on the relationship between artificial intelligence and information technology (as discussed in the accompanying article). As guest editor, I wanted to include an overview and technical material, speculation and implementation, controversial claims and evaluated techniques, as well as research articles and articles of interest to application developers. Although no finite number of articles could actually do all this, I'm very happy to have collected the material included here. There are four main articles, as well as a collection of short pieces by young scientists, making the content of this issue quite diverse and covering a wide spectrum of the work in this field.In the first article, Charles Petrie writes about agents and their relevance to engineering applications. He also discusses many issues in terms of what agents are and presents the important issue of differing views about the communication between agents?peer-to-peer versus client/server. This article includes numerous Web pointers and can serve as an excellent starting place for those interested in learning more about agents using the World Wide Web.The next article, by David King and Dan O'Leary, focuses on executive information systems. These authors point out that the combination of AI and information technology leads to a new way of looking at information systems for corporate use, and new approaches to accessing information external to the corporation's own data resources. This article also includes many Web pointers, which we hope you will enjoy exploring.The third article, by Katia Sycara, Keith Decker, Anandeep Pannu, Mike Williamson, and Dajun Zeng, presents examples of the use of distributed intelligent agents for helping users to retrieve, filter, and fuse information relevant to their tasks. The authors show how such agents are helping in a variety of applications. This article dramatically demonstrates why agent-based computing has become such an important idea in recent years.The final feature article, by Moises Lejter and Thomas Dean, focuses on agent-related research, particularly in the area of multiagent architectures. This technical article concentrates on developing and evaluating a framework that addresses a number of issues in understanding multiagent systems. While some might argue that this article is more fitting to Artificial Intelligence or other such journals, I felt it was important to have an article that reflected on some of the exciting research issues in the agents field. I'm grateful to Moises and Tom for letting us publish it here.Last, but definitely not least, is a special section for this issue. In an effort to display some of the excitement in the agents field, I asked several young scientists who are doing the leading work in the field to write short pieces speculating on some of the exciting new directions for agents technology. The short pieces by Jim Firby, Ken Haase, Hiroaki Kitano, Jose Ambite and Craig Knoblock, Lynn Stein, Lee Spector, and Pattie Maes indicate many of the new directions being taken by some of the best and brightest of AI's up and coming generation.