a borítólapra  Súgó epa Copyright 
Acta polytechnica HungaricaVolume 4, Issue No. 1 (2007.)


Tematikus cím:Special Issue on Computational Intelligence, and Applied Machine Intelligence and Informatics - Guest Editors: Imre J. Rudas and Peter Sincák
  • Annamária R. Várkonyi-Kóczy ,
    András Rövid ,
    Szilveszter Balogh ,
    Takeshi Hashimoto ,
    Yoshifumi Shimodaira :

    Abstract: High dynamic range of illumination may cause serious distortions and other problems in viewing and further processing of digital images. In this paper a new tone reproduction preprocessing algorithm is introduced which may help in developing hardly or non-viewable features and content of the images. The method is based on the synthetization of multiple exposure images from which the dense part, i.e. regions having the maximum level of detail are included in the output image. The resulted high quality HDR image makes easier the information extraction and effectively supports the further processing of the image.

    Keywords: high dynamic range images, image reproduction, image processing

  • László Horváth :

    Abstract: This paper is concerned with the evaluation of effects of modeled object changes at development of product in virtual space. Modeling of engineering objects such as elements and structures of products, results of analyses and tests, processes for production, and customer services has reached the level where sophisticated descriptions and modeling procedures serve lifecycle management of product information (PLM). However, effective utilization of highly associative product models is impossible in current modeling because techniques are not available for tracking and evaluation of high number of associative relationships in large product model. The author analyzed the above problem and considered inappropriate organization of product information as its main cause. In order to gain a solution in current modeling systems, a new method is proposed in this paper for change management. In this method, joint modeling of design objectives and human intent is applied for shape-centered products. As background information for the proposed modeling, paper discusses research results in change management for product development in modeling environments. Following this, integrated modeling of closely related engineering objects is proposed as extension to current industrial PLM systems. Next, design objective driven product change management is detailed. Finally, virtual space is outlined as a possible advanced application of the proposed change management with the capability of representation of human intent.

    Keywords: product modeling, virtual space, change management, behavior-based modeling

  • András Róka ,
    Ádám Csapó ,
    Barna Reskó ,
    Péter Baranyi :

    Abstract: Traditional edge-detection algorithms in image processing typically convolute a filter operator and the input image, and then map overlapping input image regions to output signals. Convolution also serves as a basis in biologically inspired (Sobel, Laplace, Canny) algorithms. Recent results in cognitive retinal research have shown that ganglion cell receptive fields cover the mammalian retina in a mosaic arrangement, with insignificant amounts of overlap in the central fovea. This means that the biological relevance of traditional and widely adapted edge-detection algorithms with convolutionbased overlapping operator architectures has been disproved. However, using traditional filters with non-overlapping operator architectures leads to considerable losses in contour information. This paper introduces a novel, tremor-based retina model and edge-detection algorithm that reconciles these differences between the physiology of the retina and the overlapping architectures used by today's widely adapted algorithms. The algorithm takes into consideration data convergence, as well as the dynamic properties of the retina, by incorporating a model of involuntary eye tremors and the impulse responses of ganglion cells. Based on the evaluation of the model, two hypotheses are formulated on the highly debated role of involuntary eye tremors: 1) The role of involuntary eye tremors has information theoretical implications 2) From an information processing point of view, the functional role of involuntary eye-movements extends to more than just the maintenance of action potentials. Involuntary eye-movements may be responsible for the compensation of information losses caused by a non-overlapping receptive field architecture. In support of these hypotheses, the article provides a detailed analysis of the model's biological relevance, along with numerical simulations and a hardware implementation.

    Keywords: Image contour detection, Non-Overlapping receptive field, Artificial involuntary eye-movements

  • Gyula Hermann :
    Geometric Error Correction in Coordinate Measurement47-62en [208.92 kB - PDF]EPA-02461-00009-0040

    Abstract: Software compensation of geometric errors in coordinate measuring is hot subject because it results the decrease of manufacturing costs. The paper gives a summary of the results and achievements of earlier works on the subject. In order to improve these results a method is adapted to capture simultaneously the new coordinate frames in order use exact transformation values at discrete points of the measuring volume. The interpolation techniques used have the draw back that they could not maintain the orthogonality of the rotational part of the transformation matrices. The paper gives a technique based quaternions which avoid this problem and leads to better results.

  • Ján Vascák :

    Abstract: A number of various approaches for robot navigation have been designed. However, practical realizations strike on some serious problems like imprecision of measured data, absence of complete knowledge about environment as well as computational complexity and resulting real-time bottlenecks. Each of proposed solutions has some of mentioned drawbacks. Therefore one of possible solutions seems to be in combining several means of computational intelligence. In this paper a combination of harmonic potential fields, neural networks and fuzzy controllers is presented. Also some simulation experiments are done and evaluated.

    Keywords: harmonic potential fields, neural networks, fuzzy controller

  • József Tick :
    P-Graph-based Workflow Modelling75-88en [228.89 kB - PDF]EPA-02461-00009-0060

    Abstract: Workflow modelling has been successfully introduced and implemented in several application fields. Therefore, its significance has increased dramatically. Several work flow modelling techniques have been published so far, out of which quite a number are widespread applications. For instance the Petri-Net-based modelling has become popular partly due to its graphical design and partly due to its correct mathematical background. The workflow modelling based on Unified Modelling Language is important because of its practical usage. This paper introduces and examines the workflow modelling technique based on the Process-graph as a possible new solution next to the already existing modelling techniques.

    Keywords: workflow management, workflow modelling, P-graphs

  • Gergely Mezei ,
    Tihamér Levendovszky ,
    Hassan Charaf :
    Formalizing the Evaluation of OCL Constraints89-110en [131.48 kB - PDF]EPA-02461-00009-0070

    Abstract: Domain-specific modeling has growing importance in many fields of software enginering, such as modeling control flows of data processing, or in man-machine systems. Customizable language dictionary and customizable notations of the model elements offered by domain-specific technologies make software systems easier to create and maintain. However, visual model definitions have a tendency to be incomplete, or imprecise; the definitions can be extended by textual constraints attached to the model items. Textual constraints can eliminate the incompleteness stemming from the limitations of the structural definition as well. The Object Constraint Language (OCL) is one of the most popular constraint languages in the field of UML and Domain Specific Modeling Languages. OCL is a flexible, yet formal language with a mathematical background. Existing formalisms of OCL does not describe dynamic behavior of constraints. Our research aims at creating an OCL optimization solution and prove its correctness formally. However, the shortcomings of the existing formalism has led us to create a new formalism. The paper presents OCLASM, a new formalism for OCL, which can describe both the semantics and the dynamical behavior of the language constructs, thus, it is capable of describing proofs of optimization algortihms. OCLASM is based on the Abstract State Machines technique.

    Keywords: OCL, optimization, constraints, Abstract State Machines

  • Marek Paralic :

    Abstract: In this paper the current research activities of the Distributed team at the Department of Computer and Informatics, FEI, TU in Košice are described. Our focus is to propose and verify new methods and tools, which could contribute to the design and implementation of integrated, pervasive and collaborative services. Pervasive computing is an important research area whose challenges require a thorough rethinking and revision of conventional software design ideas. In reality, there is little consensus and very little basic understanding of the underlying issues and their interactions to produce useful solutions. Our research activities aim to perform the research necessary to contribute to this understanding.

    Keywords: service-oriented computing, agent technology, pervasive computing, semantic web services

  • Kornélia Ambrus-Somogyi :
    Deterioration-based Maintenance Management Algorithm119-126en [59.35 kB - PDF]EPA-02461-00009-0090

    Abstract: The Road Management Systems (and the PMS) usually do not take into consideration the future traffic change. The maintenance and rehabilitation actions and the development of the road network structure and the changing traffic structure modify the amount of the traffic on the road section. The deterioration process depends on mostly the volume of the traffic. That is why it is important to take into consideration the change of the traffic volume during the planning time horizon. In the lecture some techniques are shown which handle this problem: in multiperiod, long time model at each planning period the traffic volume change is take into consideration. In ranking models the problem could be handled and solved. In the case of one period Markov stabile model there is nothing to do. In the multiperiod model the problem could be solved also.

  • Jolana Sebestyénová :
    Case-based Reasoning in Agent-based Decision Support System127-138en [215.33 kB - PDF]EPA-02461-00009-0100

    Abstract: The paper describes decision support system for modeling, control, and simulation of continuous, as well as discrete event systems. Models, control methods, and tools are in database specified by their attributes. Each attribute’s weight is initially estimated according to importance and classification power of a given feature. Automatic learning of attributes weights uses the answers of the users after simulation provided by the system to increase the quality of case-based reasoning. The proposed learning algorithm guarantees convergence of the attributes weights to relatively steady values yielding to Case-based reasoning of best quality. If simulation of a new case was successful from the point of view of the user, the new case is added to case base.

    Keywords: decision support system, case-based reasoning, case-based learning, learning of weights