By Topic

Proceedings Mexico-USA Collaboration in Intelligent Systems Technologies.

12-15 Nov. 1996

Filter Results

Displaying Results 1 - 25 of 55
  • Proceedings ISAI/IFIS 1996 Mexico - USA collaboration in intelligent systems technologies [front matter]

    Publication Year: 1996, Page(s):1 - 15
    IEEE is not the copyright holder of this material | PDF file iconPDF (618 KB)
    Freely Available from IEEE
  • Transferring artificial intelligence technology through a research center of excellence

    Publication Year: 1996, Page(s):30 - 35
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (545 KB)

    The Center of Excellence for Software and Systems Engineering (CECASE) at the University of Kansas was established by the State of Kansas as a vehicle for developing and transferring advanced technology to Kansas businesses. In this paper we describe three CECASE projects that used three different methods of successfully transferring advanced Artificial Intelligence (AI) technology to Kansas compa... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Knowledge discovery for dealing with the empty query problem in relational database systems

    Publication Year: 1996, Page(s):36 - 43
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (770 KB)

    An algorithm, CONEQ, is presented aimed at filtering out certain types of empty queries made to a relational database system. This algorithm employs the existing set of semantic integrity constraint rules for the database together with the current database state in a typical generate-and-test cycle aimed at creating a stronger set of semantic integrity rules that better reflect the particular data... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Using non-statistical induction based techniques for financial forecasting

    Publication Year: 1996, Page(s):44 - 51
    Cited by:  Papers (2)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (615 KB)

    In this paper, we used data consisting of attributes containing financial performance information on failed and non-failed banks. We developed and tested several models using three induction-based machine learning techniques (C4.5, a backpropagation neural network and SX-WEB) and linear discriminant analysis. All models showed test set classification correctness under 74% when trained and tested w... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A fuzzy neural controller in marketting applications

    Publication Year: 1996, Page(s):52 - 59
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (618 KB)

    Customer satisfaction measurement is an important part of marketing research in any organizations since it is the key to the formulation of customer value strategies and to the continuously improving implementation of these strategies. In this article, we present an application of fuzzy neural network for customer satisfaction. The structure of the network can be interpreted in terms of a fuzzy co... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Maintaining a short term model of the users in a medical record management system

    Publication Year: 1996, Page(s):60 - 67
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (578 KB)

    A patient folder management system should be the active supporting tool to the creation of the physician's belief about the patient's state of health, i.e. it has to be capable of retrieving and proposing the most appropriate and useful information to the user. Our target is to propose a new philosophy for a patient folder management system, capable of tailoring the information to the user's belie... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A PVM implementation of the fishmarket multiagent system

    Publication Year: 1996, Page(s):68 - 76
    Cited by:  Papers (1)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (1314 KB)

    This is an implementation proposal for a Structured Negotiation Environmen tfor Heterogeneous Agents (SNE-H) based on the Fishnmarket model. Our aim in this implementation is to explore design issues that may be relevant for the construction of a network communication infrastructure for cooperating heterogeneous agents. Hence, the Fishmarket multiagent system has been built on top of PVM package a... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The trust relationship between users and intelligent support systems

    Publication Year: 1996, Page(s):77 - 84
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (793 KB)

    Concepts from social psychology, human factors, cognitive engineering, computer science, and industrial engineering are integrated to examine: the dynamics of trust between a user and an intelligent system; how trust impacts on the joint system performance; and how the interface impacts on trust. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Obstacle modeling in a set membership for navigation systems based in ultrasonic range sensors

    Publication Year: 1996, Page(s):85 - 92
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (560 KB)

    The periodic re-localization of a mobile robot is necessary in order to reduce the uncertainty about its position and orientation when it moves. These uncertainties are due, among others, to integration errors of its internal sensors, such as odometers, accelerometers, etc. So, the localization of external references can be used to update the actual position and orientation of the vehicle; to this... View full abstract»

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

    Publication Year: 1996, Page(s):93 - 99
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (570 KB)

    In this study a reactive navigation controller using fuzzy logic has been designed. The reactive controller deals with the uncertamty and ambiguity of the information the system (mobile robot) receives. The technique has been used on MOBIRO, an experimental mobile robot holding a set of five ultrasonic proximity sensors to extract the knowledge from its surroundings. The developed technique genera... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Fuzzy coloured petri nets in modelling flexible manufacturing systems

    Publication Year: 1996, Page(s):100 - 107
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (557 KB)

    Recently, Coloured Petri Nets (CPNs) have been widely used for modelling asynchronous discrete events exhibited in dynamic systems, while Fuzzy Petri Nets (FPNs) used for systems that involve approximate reasoning and uncertainty knowledge inference. In this paper, we propose a net-based structure, the so-called Fuzzy Coloured Petri Nets (FCPNs) to model both the dynamic behaviour and inexact prod... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Modeling in standards - requirements to represent a chemical distributor

    Publication Year: 1996, Page(s):108 - 116
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (703 KB)

    One of the most time-consuming phases of knowledge and model Wed systems development is related to the modeling of application domains. One approach to shortening this process is to reuse domain specific models during the life cycle of a product. A chemical distributor is used to demonstrai how standardized formalisms defined in ISO 10303 STEP) and lEC 1131 can be used when developing models for m... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A distributed system for integrated speech and image understanding

    Publication Year: 1996, Page(s):117 - 126
    Cited by:  Papers (5)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (704 KB)

    Most published work in the field of pattern analysis, in our opinion underestimates the importance of system architecture or system development. When building large distributed systems both become a prerequisite in order to achieve the overall goal - a complex system solving a demanding task. In our paper we present the approach we have taken and the first solutions we found for an architecture in... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A computational model of the mechanical design process

    Publication Year: 1996, Page(s):127 - 134
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (625 KB)

    Existing mechanical design computational models have two fundamental drawbacks: partialness and shallowness. They are partial in that only some aspects of the design process are represented, and they are shal low in that the "what" aspect of the design process is often modeled without attaching design rationale to it. This limits their use as a representational tool. This paper proposes a computat... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Integration of language kind image processing for assembly instruction manual understanding

    Publication Year: 1996, Page(s):135 - 140
    Cited by:  Papers (1)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (509 KB)

    Assembly Instruction Manuals usually consist of both explanation and illustration. An expart who has rich knowledge on mechanical assemblies is able to under stand illustration without reading explanation. It is, how ever, difficult for a novice to read an instruction manual without referring to both of them. People may probably read explanation and see illustration alternately. It is difficult to... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Image classification by neural networks for the quality control of watches

    Publication Year: 1996, Page(s):141 - 149
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (617 KB)

    A method is presented for the automatic time detection of watches, where the hands are classified by a neural network. In order to reduce the overall cost of data collection, strict limits were imposed on the data collection time. This constraint severely limits the available amount of images, and poses the challenge to solve the hand recognition problem with a minimum amount of training and test ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Selecting training instances for supervised classification

    Publication Year: 1996, Page(s):150 - 155
    Cited by:  Papers (1)  |  Patents (1)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (536 KB)

    Several experimental studies have tested the relative merits of various supervised machine learning models. Comparisons have been made along dimensions that include model complexity, prediction accuracy, training set size, and training time. Only limited work has been done to study the effect of training set exemplar typicality on model performance. We present experimental results obtained in test... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A self-adaptive genetic algorithm for function optimization

    Publication Year: 1996, Page(s):156 - 161
    Cited by:  Papers (1)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (458 KB)

    Genetic algorithms (GA's) have some control pa rameters such as the probability of bit mutation or the probability of crossover. These are nornially given a priori by the user (programmer) of the algorithm. There exists a wide variety of values for control parameters and it is difficult to find the best choice of these values in order to optimize the be haviour of a particular GA. We introduce a s... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Evolving neural induction regular language using combined evolutionary algorithms

    Publication Year: 1996, Page(s):162 - 169
    Cited by:  Papers (1)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (699 KB)

    This paper proposes a new algorithm called combined evolutionary algorithm (CEA) to train a neural network, and demonstrates its use in inducing thefinite state automata task. This algorithm evolves neural networks by incorporating the ideas of evolutionary programming(EP) and real coded genetic algorithms (RCGA) into evolution strategies (ESs). Simultaneously, we add the local competition into th... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The classification of symbolic concepts using the Alisa concept module

    Publication Year: 1996, Page(s):170 - 179
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (896 KB)

    The Adaptive Learning Image and Signal Analysis (ALISA) system was used to extract geometric information from images of printed text (alphabetic characters) for optical character recognition. Each pixel in a character image was classified by the ALISA Geometry Module as a constituent of a small universal (canonical) set of primitive geometry classes, creating a geometric class map that was spatial... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Neural-network-based fault detector for transmission line protecirion

    Publication Year: 1996, Page(s):180 - 185
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (471 KB)

    This paper describes a fault detector that uses artificial neural networks (ANN). It represents the Brst step toward the development of a neural distance relay for protecting transmission lines. We envisage the fault defection problem as a pattern classification process. Our suggested approach Is based on the fact that when a fault occurs, a change In the system Impedance takes place and, as a con... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Neural-network-based fault location estimator for transmission line protection

    Publication Year: 1996, Page(s):186 - 191
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (554 KB)

    A classical task in the protection of transmission lines against short circuits is the estimation of the electrical distance to the fault and its comparison against a given threshold to determine whether the line is faulted or not. This paper presents a novel neural network approach to this problem, as a step towards the design of a neural protective relay. Two different alternatives are proposed ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Data mining tools applied to high-voltage insulators

    Publication Year: 1996, Page(s):192 - 197
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (496 KB)

    The integration of four artificial intelligence tools that combine the ID3 algorithm and the case-based reasoning method of the nearest neighbor are proposed to solve the problem of characterizing the flashover on high-voltage insulators. The first tool uses data mining to build a classification or decision tree from historic data, the second, generates production rules, the third, operates the de... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Unsupervised cluster discovery: the peakfinder algorithm

    Publication Year: 1996, Page(s):198 - 208
    Cited by:  Patents (2)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (961 KB)

    The PeakFinder Algorithm is an unsupervised meAhod for discovering significant clustm (classes) in a noisy histogram whose underlying distribution estimates the probability density function of an n dimensional feature space for one symbolic category. The histogram is filtered using a suitable kernel function, whose strength (window size) is searched for the smallest value that yields the largest n... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Detection of traffic jams using alisa

    Publication Year: 1996, Page(s):209 - 214
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (556 KB)

    Based on collective learning systems theory, ALISA (Adaptive Learning Image and Signal Analysis) is an adaptive image classification engine that has been designed and tested at the Research Institute for Applied Knowledge Processing (FAW) in Ulm, Germany, at Robeit Hosch GmbH in Stuttgart, Germany, at the University of the Americas in Puebla, Mexico, and at 'Me George Washington University in Wash... View full abstract»

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