By Topic

Intelligent Systems, 2006 3rd International IEEE Conference on

Date 4-6 Sept. 2006

Filter Results

Displaying Results 1 - 25 of 159
  • Web Intelligence, Business Intelligence and Decision Support Systems: A Challenge for Fuzzy Logic and Soft Computing

    Page(s): 3
    Save to Project icon | Request Permissions | PDF file iconPDF (926 KB)  
    Freely Available from IEEE
  • Fuzzy Methods for Intelligent Behavior Modeling

    Page(s): 4
    Save to Project icon | Request Permissions | PDF file iconPDF (297 KB)  
    Freely Available from IEEE
  • A New Frontier in Computation---Computation with Information Described in Natural Language

    Page(s): 5 - 6
    Save to Project icon | Request Permissions | PDF file iconPDF (1696 KB)  
    Freely Available from IEEE
  • T-detectors Maturation Algorithm with in-Match Range Model

    Page(s): 8 - 11
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (4099 KB) |  | HTML iconHTML  

    Negative selection algorithm is used to generate detector for change detection, anomaly detection. But it can not be adapted to the change of self data because the match threshold must be set at first. To solve the problem, I-TMA-GA and TMA-MRM inspired from the maturation of T-cells are proposed. But genetic algorithm is used to evolve the detector population with minimal selfmax. In this paper, to achieve the maximal coverage of nonselves, genetic algorithm is used to evolve the detector population with minimal match range with selfmax and selfmin. An augmented algorithm called T-detectors maturation algorithm based on min-match range model is proposed. The proposed algorithm is tested by simulation experiment for anomaly detection and compared with NSA, I-TMA-GA and TMA-MRM. The results show that the proposed algorithm is more effective than others View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Density maximisation classification in the lattice machine

    Page(s): 12 - 16
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (5645 KB) |  | HTML iconHTML  

    This paper reviews the lattice machine classification framework (H. Wang et al., 1999), (Hui Wang et al., 2000), (Hui Wang et al., 2004) and its classification methods, in particular the density maximisation method (Hui Wang et al., 2003). This paper also suggests a different way of estimating density, which is based on the contextual probability (H. Wang and W. Dubitzky, 2005). The lattice machine approximates data resulting in, as a model of data, a set of hypertuples that are equilabelled, supported and maximal. Such a model can be used for classification with the C2 method (Hui Wang et al., 2000) or the density maximisation method (Hui Wang et al., 2003). The density maximisation method uses the lattice machine model of data to classify new data with a view to maximising the density of the model. The density maximisation method uses a simple definition of density. In this paper we suggest using a different density estimation method, which is based on the contextual probability View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • LVOT: The Design of an Intelligent System for Building and Using Learning Virtual Objects

    Page(s): 17 - 22
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (7852 KB) |  | HTML iconHTML  

    This paper presents the design of an intelligent IMS-based architecture called learning virtual object tool (LVOT) to facilitate the creation and manipulation of objects in Urge-scale, cooperative elearning environments. The research work brings three contributions to knowledge: a) the analysis of a generic elearning environment (GeLEnv), b) the definition and use of LVO structures and, c) the design of the LVOT architecture. We apply one of our top-down analysis processes to describe the proposed GeLEnv, following three levels of abstraction. The paper summarises some of our explorations with learning objects and software architectures. We define three types of LVOs: basic, composite, and cooperative. Finally, we present the high and low level design of our LVOT platform View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Detecting Single and Multiple Faults Using Intelligent DSP and Agents

    Page(s): 23 - 29
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (7896 KB) |  | HTML iconHTML  

    In this paper intelligent agents and DSP techniques are integrated to detect single and multiple faults in electrical circuits. Agents are used to model the AC electrical circuit. A DSP engine is embedded into the agents to analyse the signals, i.e. the energy transfer between the physical components. An AC to DC rectifier circuit is chosen as test-bed for the proposed solutions View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Automating the Identification of Mechanical Systems' Technical State Using Case-Based Reasoning

    Page(s): 30 - 35
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (8004 KB) |  | HTML iconHTML  

    The paper considers application of the case-based reasoning paradigm for solving of the problem related to computer-aided identification of technical states for mechanical systems employed in petrochemistry. The results of investigation are: case models corresponding to the concept of "incident" (known from the practice of reaching reliability) and reflecting the properties and states of mechanical systems; an algorithm of case retrieval; the architecture and software for computer-aided identification of technical states for mechanical systems View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Applying Ant-based Multi-Agent Systems to Query Routing in Distributed Environments

    Page(s): 36 - 41
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (8559 KB) |  | HTML iconHTML  

    This paper presents SemAnt, a novel ant-based multi-agent system designed for distributed query routing. While the ant metaphor has been successfully applied to network routing both in wireless and fixed networks, little is yet known about its applicability to the task of query routing in distributed environments. We point out the similarities and dissimilarities between routing of data packets and routing of queries, and we present the design of SemAnt, which is based on the ant colony optimization meta-heuristic. For experimental evaluation, we deploy the algorithm in a peer-to-peer environment with a real-world application scenario and compare its performance against the well-known k-random walker approach. As we show, the benefits of SemAnt are that the routes for queries are optimized according to their popularity, and that the algorithm is highly suitable for volatile environments View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The Fusion Process of Goal Ontologies using Intelligent Agents in Distributed Systerns

    Page(s): 42 - 47
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (7213 KB) |  | HTML iconHTML  

    In the field of artificial intelligence, most of the distributed systems are described by services which can be composed to provide more complex ones. The potential to achieve dynamic composition of services has driven recent research efforts. To this end it is crucial to find solutions in order to automate this task. In the present paper, we propose a methodology which deals with these insufficiencies on two levels. The first level is the design. Based on teleological reasoning, each service is related to a goal which is represented by a conceptual model called an ontology. Services are described by a functional model which relies on a core reasoning process between interacting functional components of the complex system. The process is based on information flow (IF) approach, where the main idea is the fusion of goal ontologies. The second level is the implementation through multi agent systems (MAS). We propose an algorithm describing the mechanism of the dynamic fusion of services, in which the intelligent agents support the functional components of the complex system View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Differential Equations Systems versus Scale Free Networks in Sepsis Modeling

    Page(s): 48 - 51
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (5074 KB) |  | HTML iconHTML  

    The paper proposes a comparison between models that relieves the characteristics of the patient evolution in sepsis as the result of correct or corrupted information transfer as the cell level. Specifically, two different models for the cellular interactions are compared - one based on a three variables system of differential equations, the other on a cellular interaction scale free network. The advantages and limits of each model in understanding the structure of cellular signaling networks involved in sepsis phenomena are finally discussed View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Multitasking Driver Cognitive Behavior Modeling

    Page(s): 52 - 57
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (8342 KB) |  | HTML iconHTML  

    In order to process multitasking driver behavior effectively, an improved driver cognitive behavior modeling method of ACT-R is proposed in this paper. The manual module and visual module of ACT-R are concatenated directly to cope with human subconscious/unconscious behavior. A parallel processing method is proposed to mimic the parallel reactions style of a given cerebral area of human brain's reaction to the physical characteristics of the stimulus. Drive behavior assorting and risk level ranking method are applied to improve the model's executive efficiency. The results of the software simulation show that the improvements of the ACT-R cognitive architecture are efficient and flexible View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Fast Kernel for Calculating Structural Information Similarities

    Page(s): 59 - 64
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (7068 KB) |  | HTML iconHTML  

    Structural similarity computation plays a crucial role in many applications such as in searching similar documents, in comparing chemical compounds, in finding genetic similarities, etc. We propose in this paper to use structural information content (SIC) for measuring structural information, considering both the nodes and edges of trees. We utilize a binary encoding approach for assigning the weights of different layer nodes and determining if some tree is a subtree of another tree. By defining a fast kernel and recursively computing SICs, we evaluate the structural information similarities of data trees to pattern trees. In the paper, we present the algorithm for calculating SICs with computation complexity of O(n), and use simple examples to instantiate the performance of the proposed method View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Multivariate Microaggregation Based Genetic Algorithms

    Page(s): 65 - 70
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (7260 KB) |  | HTML iconHTML  

    Microaggregation is a clustering problem with cardinality constraints that originated in the area of statistical disclosure control for micro data. This article presents a method for multivariate microaggregation based on genetic algorithms (GA). The adaptations required to characterize the multivariate microaggregation problem are explained and justified. Extensive experimentation has been carried out with the aim of finding the best values for the most relevant parameters of the modified GA: the population size and the crossover and mutation rates. The experimental results demonstrate that our method finds the optimal solution to the problem in almost all experiments when working with small data sets. Thus, for small data sets the proposed method performs better than known polynomial heuristics and can be combined with these for larger data sets. Moreover, a sensitivity analysis of parameter values is reported which shows the influence of the parameters and their best values View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Towards the Practical Use of Qualitative Spatial Reasoning in Geographic Information Retrieval

    Page(s): 71 - 76
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (7200 KB) |  | HTML iconHTML  

    Geo-ontologies have a key role to play in the development of the geo-semantic Web, with regard to facilitating the search for geographical information and resources. They normally hold large amounts of geographic information and undergo a continuous process of revision and update to ensure their currency. Hence, means of ensuring their integrity are crucial and needed to allow them to serve their purpose. This paper proposes the use of qualitative spatial reasoning as a tool to support the development of a geo-ontology management system. Spatial integrity rules based on uniform and hybrid spatial reasoning are proposed for the automatic derivation of spatial relationships and for maintaining the spatial consistency of the geographic data. A framework for the representation of and reasoning over geo-ontologies is presented using the Web ontology language OWL and its associated reasoning tools. Spatial reasoning and integrity rules are represented using a spatial rule engine extension to the reasoning tools associated with OWL. To demonstrate the proposed approach, a case study showing a prototype geo-ontology and the implementation of the spatial reasoning engine is presented. This work is a step towards the realisation of a complete geo-ontology management system for the semantic Web View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Knowledge Engineering Approach to Concurrently Competng Cyclic Processes Control

    Page(s): 77 - 82
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (8053 KB) |  | HTML iconHTML  

    This paper addresses the problem of designing the steady-state behavior of a system composed of a set of repetitive processes competing for access to shared resources. Its objective is to provide a framework allowing to prototype a robust distributed control policy as a function of the characteristics of the component processes and dispatching rules involved. The considered problem resolution consists in finding a schedule with no process waiting for access to the shared resources and wherefore leading to controls not requiring resource conflict resolution. The problem is formulated as a task of prototyping of conditions sufficient for existence of a waiting-free n-process execution. The conditions prototyping is then examined within the framework of logic-algebraic method. The illustrative example of the approach proposed is provided View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Relative Qualification in Database Flexible Queries

    Page(s): 83 - 88
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (6296 KB) |  | HTML iconHTML  

    The simplest vague selection criterion in database queries is often expressed by a gradual property, or in other words, a certain qualification required to the targeted objects. Complex criteria often combine two or more simple and independent criteria, through an aggregation operation that means a multi-qualification of the searched objects. But there are also cases when in a complex criterion, one of the qualification is applicable in the context created from another attribute values, that means relative qualification. The relative qualification to another gradual property and the relative qualification to another crisp attribute are presented in the paper. In order to complete a real database querying problem, adequate procedures to dynamical defining linguistic values on database attributes are also proposed View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Query Model with Relevance Feedback for Image Database Retrieval

    Page(s): 89 - 94
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (7705 KB) |  | HTML iconHTML  

    Most of the solutions proposed in image database applications are limited to a specific application domain. Generic models attempt to ease the development of applications to researchers. In this paper, to overcome the difficulties faced by application-specific systems, we present a general purpose image management model, oriented to fill the gap between systems and users. To the retrieval process the most important issue is to have a query model that efficiently represents the image nature integrated with traditional data and a feedback mechanism to model the user's information needs. This work develops a query language to deal with the fuzzy nature of images. The query language, I-OQL, based on the ODMG standard, also is able to define high level concepts and to integrate different levels of abstraction. We also propose a general-purpose relevance feedback mechanism oriented to fill the gap between systems and users, expressing user subjectivity in the retrieval process. Experiment results are presented to explore and validate the query refinement process View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Extending the Resource-Constrained Project Scheduling Problem for Disruption Management

    Page(s): 95 - 102
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (11592 KB) |  | HTML iconHTML  

    This paper describes how the resource-constrained project scheduling problem (RCPSP) can be used as a basis for comprehensive disruption management, concerned with both rescheduling as well as potential structural process modifications. It is illustrated, how the RCPSP can be extended by the possibility to represent alternative activities and how the respective constructs can be used to describe various forms of typical interventions. Moreover, an approach for schedule optimization and the resolution of the generalized problem is presented, based on the combination of well-established methodologies and specific evolutionary operators. In an illustrative example it is finally shown how the proposed framework can be applied for the development of real-time decision support systems in the domain of airport ground process management View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Inductive Learning of Dispute Scenarios for Online Resolution of Customer Complaints

    Page(s): 103 - 108
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (8883 KB) |  | HTML iconHTML  

    We focus on online resolution of customer complaints. An efficient way to assist customers and companies is to reuse previous experience with similar agents. A formal representation of customer complaints and a machine learning technique for handling scenarios of interaction between conflicting human agents are proposed. It is shown that analysing the structure of communicative actions without context information is frequently sufficient to advise on complaint resolution strategies. Therefore, being domain-independent, the proposed machine learning technique is a good complement to a wide range of customer response management applications where formal treatment of inter-human interactions is required View full abstract»

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

    Page(s): 109 - 114
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (8896 KB) |  | HTML iconHTML  

    Conceptual modeling is viewed as a promising means to represent contextual knowledge, which may be enriched with semantics. Such modeling is capable of describing situations context, as well as, reasoning about it. Moreover, situational reasoning is attained taking into consideration similarity-based approaches. This paper proposes approximate reasoning about situations similarity using ontological modeling, description logics representation, and fuzzy logic inference rules View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Ad-Hoc Networking with OWL-S and CSP

    Page(s): 115 - 120
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (7137 KB) |  | HTML iconHTML  

    In order to achieve a ubiquitous ad-hoc environment suitable for any kind and number of compute devices, information concerning device usability must be stored and manipulated. Take, for example the home where a large number of devices - heating, cooking, lighting, entertainment, security all cooperate to provide a suitable environment for a home resident. This paper proposes a representation of home devices as OWL-S (Web service ontology) services, capable of being implemented by means of the formal algebra CSP (communication sequential process). Because of the ontological nature of OWL-S and the possibility of translating CSP equations to lightweight implementations, this proposal allows a rich semantic description of services capable of being hosted by a wide range of devices, including such ones with low computational resources. The paper describes the procedure of developing a service in OWL-S, its translation to CSP and its implementation in occam, an efficient CSP-based language View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Learning Concepts, Taxonomic and Nontaxonomic Relations from texts

    Page(s): 121 - 124
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (5841 KB) |  | HTML iconHTML  

    This paper discusses the knowledge extraction process in an ontology learning system called Hasti. It exploits an automatic, hybrid, symbolic approach to acquire conceptual knowledge and construct flexible and dynamic ontologies from scratch. This approach starts from a small kernel and learns concepts, taxonomic and non-taxonomic relations and axioms from natural language texts. The focus of this paper is on extraction of concepts and conceptual (taxonomic and non-taxonomic) relations using linguistic and template-driven methods. In this paper, the author will first present a brief overview on ontology learning systems and then describing the life cycle for the ontology learning and building process in Haiti, the knowledge extraction process will be discussed in more details. At last the author will present some experimental results of implementation and testing the proposed model View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Method for Solving Multiple Criteria Decision Making (MCDM) Problems and Decision Support System

    Page(s): 126 - 129
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (4912 KB) |  | HTML iconHTML  

    A visual multiple criteria approach is presented with displacing limitations as well, as the features of the applied software system of MADMML, which is implementing it. That system has been applied in the field of material science to determine the technological modes providing the preset requirements to the values examined. It is investigated that non-dominated (effective) decisions are determined by applying various filters of the system View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Case-Based Decision Support for Intelligent Patient Knowledge Management

    Page(s): 130 - 135
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (8851 KB) |  | HTML iconHTML  

    The majority of healthcare workers in hospitals continue to record, access and update important patient information using paper charts. Disparate patient data (clinical information, laboratory results and medical imagery) is entered by different caregivers and stored at different locations around the hospital. This is a cumbersome, time consuming process that can result in critical medical errors such as documents being mislaid or prescriptions being misinterpreted due to illegible handwriting. Hospitals everywhere are moving to integrate health data sources using electronic health record (EHR) systems as well as taking advantage of the flexibility and speed of wireless computing to improve the quality and reduce the cost of healthcare. We are developing a mobile application that allows doctors to efficiently access accurate real-time patient information at the point-of-care. The system can assist caregivers in automatically searching through very large repositories of previous patient cases as increasingly large hospital databases are making manual searches of such information unfeasible. The system performs computational prognosis by providing decision support for pre-screening of medical diagnosis. A presenting patient's symptoms can be input to a portable device and the application can quickly retrieve the most similar profiles with known diagnoses from large databases which can be used to compare treatments, diagnosis, test results and other information View full abstract»

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