Proceedings 12th IEEE Internationals Conference on Tools with Artificial Intelligence. ICTAI 2000

15-15 Nov. 2000

Filter Results

Displaying Results 1 - 25 of 67
  • Proceedings 12th IEEE Internationals Conference On Tools With Artificial Intelligence

    Publication Year: 2000, Page(s):iii - ix
    Request permission for commercial reuse | |PDF file iconPDF (305 KB)
    Freely Available from IEEE
  • Proceedings 12th IEEE Internationals Conference on Tools with Artificial Intelligence. ICTAI 2000

    Publication Year: 2000
    Request permission for commercial reuse | |PDF file iconPDF (878 KB)
    Freely Available from IEEE
  • About the use of local consistency in solving CSPs

    Publication Year: 2000, Page(s):104 - 107
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (385 KB)

    Local consistency is often a suitable paradigm for solving constraint satisfaction problems. We show how search algorithms could be improved, thanks to a smart use of two filtering techniques (path consistency and singleton arc consistency). We propose a possible way to get benefits from using a partial form of path consistency (PC) during the search. We show how local treatment based on singleton... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Intelligent content-based retrieval

    Publication Year: 2000, Page(s):262 - 265
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (360 KB)

    This paper deals with the challenge of extending classical image retrieval by including visual rules. The visual rules are extracted automatically from classes of images. They contribute to making the retrieval process more accurate. The visual-rules extraction is based on symbolic representations of image descriptors. The symbolic representations are the results of color and texture clustering. View full abstract»

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

    Publication Year: 2000, Page(s):426 - 427
    Request permission for commercial reuse | |PDF file iconPDF (111 KB)
    Freely Available from IEEE
  • A distributed multimedia knowledge based environment for modeling over the Internet

    Publication Year: 2000, Page(s):140 - 146
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (572 KB)

    The paper describes a knowledge-based scalable multimedia environment for graph based modeling and the design of complex objects over the Internet. A complex object is modeled as a directed hierarchical graph with each sub-component abstracted as a node and the shared parameters between two components as an edge. The knowledge base archives and retrieves reusable components, and integrates multipl... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A synergistic model for interpreting human activities and events from video: a case study

    Publication Year: 2000, Page(s):132 - 139
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (668 KB)

    This paper describes a new approach for representing, recognizing and interpreting human activity from video. The approach presented (at the conceptual level) is a model based on the hierarchical synergy of three other models (the L-G graph, the SPN graph and a NN model). In particular, in our project human activity is strongly related with the ability of describing and interrelating events. Thus,... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Identifying causal structure in a biological neural network

    Publication Year: 2000, Page(s):126 - 129
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (344 KB)

    A simulator for the Burgess, Recce, and O'Keefe (1994) BRO model of rodent navigation was built. Initial experiments did not reproduce the navigation performance reported by BRO. To determine the cause of the discrepancy, we reconstructed and reanalyzed their model. We were able to verify their main claim that if phase-modulated place cells act as radial basis functions, then they computationally ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Function approximation based multi-agent reinforcement learning

    Publication Year: 2000, Page(s):36 - 39
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (308 KB)

    The paper presents two new multi-agent based domain independent coordination mechanisms for reinforcement learning. The first mechanism allows agents to learn coordination information from state transitions and the second one from the observed reward distribution. In this way, the latter mechanism tends to increase region-wide joint rewards. The selected experimented domain is Adversarial Food-Col... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Multi-resolution on compressed sets of clauses

    Publication Year: 2000, Page(s):2 - 10
    Cited by:  Papers (10)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (728 KB)

    The paper presents a system based on new operators for handling sets of propositional clauses represented by means of ZBDDs (zero-suppressed binary decision diagrams). The high compression power of such data structures allows efficient encodings of structured instances. A specialized operator for the distribution of sets of clauses is introduced and used for performing multi-resolution on clause s... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Efficient prediction of interconnect crosstalk using neural networks

    Publication Year: 2000, Page(s):122 - 125
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (320 KB)

    Interconnect crosstalk prediction has become increasingly important with deep submicron downscaling of ICs and wafer scale integration. Existing tools for management of the emi problem are computationally expensive and not very broad in application. The unique approach proposed involves the creation of parameterized models of primitive interconnect structures, wirecells, using modular artificial n... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Constrained genetic algorithms and their applications in nonlinear constrained optimization

    Publication Year: 2000, Page(s):286 - 293
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (620 KB)

    The paper presents a problem-independent framework that unifies various mechanisms for solving discrete constrained nonlinear programming (NLP) problems whose functions are not necessarily differentiable and continuous. The framework is based on the first-order necessary and sufficient conditions in the theory of discrete constrained optimization using Lagrange multipliers. It implements the searc... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A knowledge based system: an object case approach

    Publication Year: 2000, Page(s):190 - 193
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (364 KB)

    We propose an object based system to represent domain knowledge and to store it in libraries for reuse, following a case based paradigm. Our tool is generic enough to model any problem which requires a legal qualification. This kind of problem requires cooperation between several knowledge domains (e.g., medical practice and legal evaluation). The proposed case model captures the necessary expert'... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Building efficient partial plans using Markov decision processes

    Publication Year: 2000, Page(s):156 - 163
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (636 KB)

    Markov decision processes (MDP) have been widely used as a framework for planning under uncertainty. They allow to compute optimal sequences of actions in order to achieve a given goal, accounting for actuator uncertainties. But algorithms classically used to solve MDPs are intractable for problems requiring a large state space. Plans are computed considering the whole state space, without using a... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A visualization tool for interactive learning of large decision trees

    Publication Year: 2000, Page(s):28 - 35
    Cited by:  Papers (7)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (916 KB)

    Decision tree induction is certainly among the most applicable learning techniques due to its power and simplicity. However learning decision trees from large datasets, particularly in data mining, is quite different from learning from small or moderately sized datasets. When learning from large datasets, decision tree induction programs often produce very large trees. How to efficiently visualize... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Interpretation of self-organizing maps with fuzzy rules

    Publication Year: 2000, Page(s):304 - 311
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (688 KB)

    Exploration of large and high-dimensional data sets is one of the main problems in data analysis. Self-organizing maps (SOMs) can be used to map large data sets to a simpler; usually two-dimensional topological structure. This mapping is able to illustrate dependencies in the data in a very intuitive manner and allows fast location of clusters. However because of the black-box design of neural net... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Multi-objective retrieval of object pose from video

    Publication Year: 2000, Page(s):242 - 249
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (652 KB)

    Introduces a novel approach for rigid object pose estimation. The system rotates a reference frame of the object of interest until it reaches a view at which the rotated reference view and the unknown-pose view seem to be “similar”. A number of pose similarity measures were tested for different types of objects undergoing various amounts of rotation from the reference pose. We demonstr... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • DGPS/INS integration using neural network methodology

    Publication Year: 2000, Page(s):114 - 121
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (392 KB)

    This paper presents an INS/DGPS land vehicle navigation system using a neural network methodology. The network setup is developed based on a mathematical model to avoid excessive training. The proposed method uses a KF-based backpropagation training rule, which achieves the optimal training criterion. The North and East travel distances are used as desired targets to train the two decoupled neural... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Cognitively adequate modelling of spatial reference in human-robot interaction

    Publication Year: 2000, Page(s):222 - 228
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (744 KB)

    The question addressed in this paper is which types of spatial reference human users employ in their interaction with a robot and how a cognitively adequate model of these strategies can be implemented. Experiments in human-robot interaction were carried out which show how human users approach an artificial communication partner which was designed on the basis of empirical findings regarding spati... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Learning methods for online-process diagnosis

    Publication Year: 2000, Page(s):281 - 284
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (344 KB)

    Because of the very high workpiece costs in manufacturing processes, production errors should be detected online in order to avoid a series of defective workpieces. This article describes a qualitative evaluation method for time series that is applied to the diagnosis of a procedure for spraying car body parts. The determination of the parameters for the procedure is gained through learning data, ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Tools for intelligent decision support system development in the legal domain

    Publication Year: 2000, Page(s):186 - 189
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (324 KB)

    We describe tools that are particularly suited to the development of knowledge based systems in the domain of law. The first tool is a conceptual model that supports the categorization of legal tasks. Once categorized, tasks can be mapped onto to the most appropriate artificial reasoning model (if any) for computer based implementation. This scheme is based on theoretical and cultural perspectives... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Implementing an action language using a SAT solver

    Publication Year: 2000, Page(s):96 - 103
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (852 KB)

    In recent years, research on planning algorithms has made big progress. Recent approaches encode the plan search space into a data structure called the planning graph. To extract plans, a planning graph is transformed into the satisfiability problem (SAT), which is solved by a high-speed SAT solver. This kind of planning is called SAT planning. On the other hand, recent research on reasoning about... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Strategies for optimizing image processing by genetic and evolutionary computation

    Publication Year: 2000, Page(s):151 - 154
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (436 KB)

    We examine the results of previous attempts to apply genetic and evolutionary computation (GEC) to image processing. In many problems, the accuracy (quality) of solutions obtained by GEC-based methods is better than that obtained by others such as conventional methods, neural networks (NNs) and simulated annealing (SA). However, the computation time required is satisfactory in some problems, where... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Belief revision and possibilistic logic for adaptive information filtering agents

    Publication Year: 2000, Page(s):19 - 26
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (692 KB)

    Prototypes of adaptive information agents have been developed to alleviate the problem of information overload on the Internet. However, the explanatory power and the learning autonomy of these agents are weak. A logic based framework for the development of information agents is appealing since semantic relationships among information objects can be captured and reasoned about. This sheds light on... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A heuristic search based factoring tool

    Publication Year: 2000, Page(s):298 - 301
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (456 KB)

    Factoring is believed to be a difficult task. Although factoring is of interest in its own right, the security of RSA cryptography, among other cryptographic systems, is dependent on the difficulty of factoring the product of large primes. We show how to cast the problem of factoring integers as a state-based search to which the techniques of AI may be applied. Using small primes as operators, goa... View full abstract»

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