By Topic

Proceedings Ninth IEEE International Conference on Tools with Artificial Intelligence

3-8 Nov. 1997

Filter Results

Displaying Results 1 - 25 of 80
  • Proceedings Ninth IEEE International Conference on Tools with Artificial Intelligence

    Publication Year: 1997
    Request permission for commercial reuse | PDF file iconPDF (401 KB)
    Freely Available from IEEE
  • W-ACE: a logic language for intelligent Internet programming

    Publication Year: 1997, Page(s):2 - 10
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1188 KB)

    The development of the World Wide Web (WWW) has been considerably delayed due to the excessive complexity of developing advanced and intelligent applications for the Internet. An average application may require the use of different languages, an in-depth understanding of various communication protocols and low-level communication mechanisms, etc. We propose a logic programming system, called W-ACE... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • IGLUE: an instance-based learning system over lattice theory

    Publication Year: 1997, Page(s):75 - 76
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (200 KB)

    Concept learning is one of the most studied areas in machine learning. A lot of work in this domain deals with decision trees. In this paper, we are concerned with a different kind of technique based on Galois lattices or concept lattices. We present a new semilattice based system, IGLUE, that uses the entropy function with a tap-down approach to select concepts during the lattice construction. Th... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Using fuzzy logic in ITS-course generation

    Publication Year: 1997, Page(s):190 - 193
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (366 KB)

    Shows how fuzzy logic has been used in the course building process. This process is based on the curriculum modeling approach that we have proposed, and exploits several knowledge sources, such as target-public knowledge and training requirements. By using these parameters, a fuzzy algorithm generates a course which is adapted to the given target public that can produce the required knowledge. The... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Author index

    Publication Year: 1997, Page(s):585 - 587
    Request permission for commercial reuse | PDF file iconPDF (132 KB)
    Freely Available from IEEE
  • Tools and experiments for hybrid neuro-symbolic processing

    Publication Year: 1997, Page(s):338 - 345
    Cited by:  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (736 KB)

    Symbolic and connectionist tools are widely used in the artificial intelligence (AI) domain. Both approaches report weaknesses to address the full range of capabilities required by this domain, and are often combined to overcome some limitations, but no extensive efforts have been done to give a wider view of the problem. More precisely, many ad hoc hybrid models were built from symbolic and conne... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • CSL. I. Modelling general N-ary, logical CSPs

    Publication Year: 1997, Page(s):414 - 421
    Cited by:  Papers (1)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (756 KB)

    Examines and details the motivations and design of a constraint specification language (CSL) for user-defined constraints. Many approaches to constraint programming are based on, as well as extended from, the logic programming paradigm. Some of the better-known constraint logic programming languages and systems are CLP, PROLOG III and CHIP. In these languages, unification in conventional logic pro... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Object-oriented constraint programming environment NeMo+ and its applications

    Publication Year: 1997, Page(s):296 - 303
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (736 KB)

    A constraint programming environment NeMo+, which is implemented on a base of a so-called subdefinite models approach is presented. Subdefinite models are a variety of constraint programming techniques. NeMo+ includes a high-level object-oriented declarative language for specification of data types and constraints. The method of subdefinite models is briefly reviewed in the first part of the paper... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A metalevel architecture for knowledge-based neural network design

    Publication Year: 1997, Page(s):331 - 337
    Cited by:  Patents (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (652 KB)

    In this paper, the term knowledge-based neural network (NN) design is used to refer to all efforts at exploiting prior knowledge in neural network configuration and training. A variety of techniques have been proposed for this purpose; SCANDAL provides a workbench for evaluating and integrating these techniques. After a quick overview of three main approaches to NN design, we describe SCANDALS mul... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A scalable distributed heterogeneous associative logic programming system

    Publication Year: 1997, Page(s):37 - 44
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (736 KB)

    This paper describes a distributed implementation of a scalable heterogeneous associative logic programming model, and describes an abstract instruction set for the distributed version of the model. Associative computation exploits data parallel computation. The implementation uses PVM for architecture independence, and uses object oriented programming for modularity and portability. Performance r... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Knowledge discovery in scheme approximation

    Publication Year: 1997, Page(s):568 - 573
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (620 KB)

    A scheme in databases can be considered as a knowledge description in database instances. To design schemes of databases is a knowledge acquisition technique. One of the deficiencies in database design is that there are no unique solutions. In addition, we can not avoid an evolution of the schemes because of the database paradigm. It is useful to employ AI methodologies, such as machine learning o... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Feature-based representation and indexing of axisymmetric parts in machining process planning using case-based reasoning

    Publication Year: 1997, Page(s):406 - 413
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (924 KB)

    A framework for a process planning system for the machining of axisymmetric parts using case-based reasoning is proposed. It is composed of four major modules: retriever, modifier, simulator and repairer. This paper focuses on the representation, indexing and retrieving of process planning cases. A feature-based representation for parts and processes is presented. An effective similarity metric is... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An object-oriented approach to visual databases

    Publication Year: 1997, Page(s):288 - 295
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (644 KB)

    As the demand for virtual reality systems increases, a new approach is needed to meet the following requirements: a world consists of a large number of objects; a camera is allowed to move and a world should be displayed in near real-time depending on the position of the camera as well as the angle of its lens; and minimum effort should be needed when objects are moving. We satisfy these requireme... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A fuzzy neural network approach to classification based on proximity characteristics of patterns

    Publication Year: 1997, Page(s):323 - 330
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (748 KB)

    A neural network classifier is presented, which is based on geometrical fuzzy sets. Starting from the construction of the Voronoi diagram of the training patterns, an aggregation of Voronoi regions is performed leading to the identification of larger regions belonging exclusively to one of the pattern classes. The resulting scheme is a constructive algorithm that defines fuzzy clusters of patterns... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A new hybrid neural-genetic methodology for improving learning

    Publication Year: 1997, Page(s):32 - 36
    Cited by:  Papers (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (388 KB)

    A new hybrid neural-generic methodology is presented that exploits the optimization advantages of genetic algorithms for the purpose of accelerating neural network training. The choice of fitness function is addressed and experimental findings are shown where neural network training is improved through the proposed approach. The results suggest that genetic algorithms can be a powerful tool for im... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Web mining: information and pattern discovery on the World Wide Web

    Publication Year: 1997, Page(s):558 - 567
    Cited by:  Papers (255)  |  Patents (33)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1000 KB)

    Application of data mining techniques to the World Wide Web, referred to as Web mining, has been the focus of several recent research projects and papers. However, there is no established vocabulary, leading to confusion when comparing research efforts. The term Web mining has been used in two distinct ways. The first, called Web content mining in this paper, is the process of information discover... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Towards individualized information navigation tools that adapt to user domain expertise

    Publication Year: 1997, Page(s):484 - 485
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (192 KB)

    The navigation of information spaces can be accelerated by restructuring the ways in which the information space is presented to the user. Individuals with little expertise in the browsed subject benefit less from speedy access of material when fast access comes at the expense of the information being moved out of its original context and thereby rendered incoherent. To ensure that users with vary... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Automatic generation of portable parallel natural language parsers

    Publication Year: 1997, Page(s):174 - 177
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (388 KB)

    Since natural language parsing is a computationally intensive task, the parallel parsing of natural language seems a promising choice. This paper describes both the Eu-PAGE (Eurotra PArser GEnerator) meta-compiler for the Eurotra formalism, which is a tool that automatically generates parallel natural language parsers, and the Dialogos parser, which is a parallel parser for the Greek language gene... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A generic tool for distributed AI with matching as message passing

    Publication Year: 1997, Page(s):11 - 18
    Cited by:  Papers (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (796 KB)

    The paper concentrates on the problem of integrating genetic programming, neural networks, autonomous agents with some symbolic AI techniques. For this purpose, it introduces and employs the S-calculus, which is a general model of computation with a quantitative aspect (cost) allowing naturally to express optimization and modification in dynamic parallel AI systems. The papers presents basic opera... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Pruning fuzzy ARTMAP using the minimum description length principle in learning from clinical databases

    Publication Year: 1997, Page(s):396 - 403
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (580 KB)

    The fuzzy ARTMAP is one of the families of neural network architectures based on ART (adaptive resonance theory) in which supervised learning can be carried out. However, it usually tends to create more categories than are actually needed. This often causes the so-called overfitting problem, where the performance of the fuzzy ARTMAP networks in the test set does not increase monotonically with add... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Dimensionality reduction of unsupervised data

    Publication Year: 1997, Page(s):532 - 539
    Cited by:  Papers (37)  |  Patents (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (580 KB)

    Dimensionality reduction is an important problem for efficient handling of large databases. Many feature selection methods exist for supervised data having class information. Little work has been done for dimensionality reduction of unsupervised data in which class information is not available. Principal component analysis (PCA) is often used. However, PCA creates new features. It is difficult to ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A new methodology for optimizing evasive maneuvers under uncertainty in the extended two-dimensional pursuer/evader problem

    Publication Year: 1997, Page(s):278 - 285
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (612 KB)

    Traditional analytic or control-theoretic solutions to the problem of optimizing evasive maneuvers in the extended two-dimensional pursuer/evader problem require the evader to execute specific sequences of maneuvers at precise pursuer/evader distances. These solutions depend upon several pursuer-specific characteristics, and fail to effectively account for uncertainty about the state of the pursue... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Data visualization in the DB-Discover system

    Publication Year: 1997, Page(s):474 - 477
    Cited by:  Papers (1)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (508 KB)

    The DB-Discover system is a research software tool for knowledge discovery from databases. Utilizing an efficient attribute oriented induction algorithm based upon the climbing tree and dropping condition methods, called multi attribute generalization, it generates many possible summaries of data from a database. We present the design of the data visualization capabilities of DB-Discover and descr... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Time dependent optimization with a folding genetic algorithm

    Publication Year: 1997, Page(s):125 - 132
    Cited by:  Papers (6)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (752 KB)

    Time-dependent optimization has revealed to be a promising gap for the entire genetic algorithms community since it has numerous applications. This paper extends previous work (Collard et al., 1996) related to the use of meta-genes in the so-called dual genetic algorithms (DGAs). A more generic framework, involving a variable number of genes, is introduced. Folding genetic algorithms are thus prop... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Combining multiple representations in a spatial reasoning system

    Publication Year: 1997, Page(s):314 - 322
    Cited by:  Papers (36)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1168 KB)

    We examine a variety of representations for storing and reasoning about spatial information and distinguish between quantitative representations grounded in numerical coordinate systems and qualitative representations, based on a high-level conceptual vocabulary for the description of spatial situations. We suggest that qualitative languages, can add powerful functionality to spatial information s... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.