Поиск по всему репозиторию:

ПросмотрМатериалы конференций и семинаров по издательству "BrSTU"

Отображаемые элементы 1-20 из 54

    • A Framework for Parallel Processing of Image Dataflow in Industrial Applications 

      Otwagin, Aleksej; Doudkin, Alexander (BrSTU, 2006)
      Basic algorithms and processing technologies of integrated circuit layout images are considered. The images represented as a set of frames can regard as a dataflow and the processing are perfectly suited for parallel implementation. Framework architecture for designing parallel systems of image dataflow ...

      2023-11-24

    • A Fuzzy-CMAC Based Hybrid Intuitive Approach for Biped Robot’s Adaptive Dynamic Walking 

      Sabourin, Christophe; Kurosh Madani; Bruneau, Olivier (BrSTU, 2006)
      In this paper, we have proposed a new neural network based hybrid intuitive approach for biped robot's adaptive walking. Our approach takes advantage on the one hand from a Fuzzy-CMAC based stage and on the other hand from high level intuitive control strategy involving only the regulation of the ...

      2023-11-28

    • A Modification of the FCM-CV-algorithm and Its Application for Radar Portraits Classification 

      Sadowska, Krystyna; Sharamet, Andrei (BrSTU, 2006)
      Sadowska, K. A Modification of the FCM-CV-algorithm and Its Application for Radar Portraits Classification / K. Sadowska A. Sharamet // International Conference on Neural Networks and Artificial Intelligence : proceedings, Brest, 31 May – 2 June, 2006 / Edited: V. Golovko [et al.]. – Brest : BSTU, ...

      2023-11-23

    • A Neural Network Based Speech Recognition System For Isolated Tamil Words 

      Bharath, B.; DeepaIakshmi, V.; Nelson, I. (BrSTU, 2006)
      Speech recognition is always looked upon as a fascinating field in human computer interaction. It is one of the fundamental steps towards understanding human cognition and their behavior. White most of the literature on speech recognition is based on Hidden Markov Models (HMM). This paper presents a ...

      2023-11-24

    • A Steganographic Method Using Learning Vector Quantization 

      Gorbashkо, Larisa; Golovko, Vladimir (BrSTU, 2006)
      The new technique for embedding image data is presented. The message is subjects to vector quantizer by neural network. The modified data is inserted into the coiner in the wavelet transform domain. The vector quantization enables to increase the capacity of embedded data. The experimental results ...

      2023-11-29

    • A weighting function approach for neural network nonlinear time series analysis of satellite remote sensing of rainstorms 

      Lisheng Xu; Jilie Ding; Xiaobo Deng (BrSTU, 2006)
      One of frequently used neural networks, i.e., a radial-based function network (RBFN) with Gaussian activation functions is employed to study the nonlinear time series by carrying out the characterization experiments for a GMS- 5 satellite 11 µm IR observations of rainstorm process. The proposed ...

      2023-11-27

    • Algorithm for calculating the mutual correlation function for a video surveillance system 

      Sadykhov, Rauf Khosrovovich; Lamovsky, D. V. (BrSTU, 2006)
      This paper describes a new algorithm to calculate cross-correlation function. We combined box filtering technique for calculation of cross correlation coefficients with parallel processing using MMX/SSE technology of modem general purpose processors. We have used this algorithm for real time optical ...

      2023-11-27

    • An Approach to Interplanetary Shocks Prediction Using Single ACE/EPAM Channel Data 

      Turchcnko, Volodymyr; Demchuk, Viktor; Sachenko, Anatoly; Veremeyenko, Yuri (BrSTU, 2006)
      An approach to prediction of the arrival time of interplanetary shocks using neural networks based on the data gathered from single EPAM (Electron, Proton and Alpha Monitor) channel o f NASA's ACE (Advanced Composition Explorer) spacecraft is proposed in this paper. A short description of ACE spacecraft ...

      2023-11-24

    • An Approach to Solving Face Detection Task 

      Krasnoproshin, Viktor Vladimirovich; Koblov, E. V. (BrSTU, 2006)
      In this paper a pattern-recognition based approach to solving face detection task is proposed. All main steps are revealed and algorithms for their solution are built. It is shown that these algorithms in the aggregate effectively solve the face detection task. The conditions when the exact solution ...

      2023-11-24

    • An Artificial Neural Network Based Approach to Mass Biometry Dilemma Taking advantage from IBM ZISC-036 Neuro-Processor Based Massively Parallel Implementation 

      Kurosh Madani; Abdennasser Chebira; Damien Langlois (BrSTU, 2006)
      Over the recent past years, new public security tendency to fit up public areas with biometric devices has emerged new requirements in biometric recognition dealing with what we call here "mass biometry". Ifthe main goal in "individual biometry" is to authenticate and/or identify an undesired individual ...

      2023-11-28

    • Analysis of approaches to design voice conversion systems 

      Thai Trung Kien (BrSTU, 2006)
      Analysis of approaches to design voice conversion systems is proposed in this paper. Base on analysis we give principles of voice conversion system, speech modes will be used to represent parameters of speech signal and acoustic characteristics will influence the quality of system. Moreover, we compare ...

      2023-11-27

    • Applying Natural Computation to Real World Business – Selected Highlights from Cercia 

      Frayn, Colin M. (BrSTU, 2006)
      Bringing cutting-edge natural computation research into industry is a challenging task, with numerous obstacles to overcome. In this paper I describe a few selected projects that we have developed at the Centre of Excellence for Research in Computational Intelligence and Applications (Cercia) and I ...

      2023-11-29

    • Artificial Immune Systems for Information Security: Comparative Analysis of Negative and Positive Selections 

      Безобразов, Сергей Валерьевич (BrSTU, 2006)
      The artificial immune system is a new, perspective system for protection of computer systems from viruses. Training and selection of detectors is necessary in artificial immune system, as it prevents break-in of unnecessary detectors. This paper presents comparative analysis of two methods detectors ...

      2023-11-29

    • Artificial Intelligence and Neural Networks The Legacy of Alan Turing and John von Neumann 

      Muehlenbein, Heinz (BrSTU, 2006)
      The work of Alan Turing and John von Neumann on machine intelligence and artificial automata is reviewed. Turing's proposal to create a child machine with the ability to Ieam is discussed. Von Neumann's had doubts that with teacher based learning it will be possible to create artificial intelligence. ...

      2023-11-29

    • Can neural networks holistically reprogram themselves through their own observation? 

      Mariage, Jean-Jacques (BrSTU, 2006)
      Neural networks (NNs) are inspired -at least metaphorically -from biological solutions nature selected by evolution. On one hand, learning algorithms' efficacy has been widely demonstrated experimentally, even if the mathematical proof of their convergence is not always very easy to establish (SOM). ...

      2023-11-23

    • Classification of handwritten signatures based on boundary tracing 

      Adamski, Marcin; Saeed, KhaIid (BrSTU, 2006)
      The paper presents a system for offline classification of handwritten signatures. The algorithm is based on boundary tracing technique for extracting characteristic features. Outer and inner boundaries are treated separately. The upper and lower parts of the boundaries are extracted to form two sequences ...

      2023-11-23

    • Comparative Analysis of Neural Networks and Statistical Approaches to Remote Sensing Image Classification 

      Kussul, Nataliya; Skakun, Serhiy; Kussul, OIga (BrSTU, 2006)
      This paper examines different approaches to remote sensing images classification. Included in the study are statistical approach, namely Gaussian maximum likelihood classifier, and two different neural networks paradigms: multilayer pcreeptron trained with EDBD algorithm, and ARTMAP neural network. ...

      2023-11-24

    • Computer Network Security Approach Based on Multi-Agent Dynamic Recognition 

      Vaitsekhovich, Leanid (BrSTU, 2015)
      Vaitsekhovich, L. Computer Network Security Approach Based on Multi-Agent Dynamic Recognition / L. Vaitsekhovich // Modern problems of mathematics and computer engineering : a collection of materials of the IX Republican scientific conference of young scientists and students, Brest, November 19–21, ...

      2020-01-15

    • Computer-aided technique for defect and project rules inspection on PCB layout image 

      Doudkin, Alexander; Inyutin, Alexander (BrSTU, 2006)
      A technique o f PCB layout optical inspection based on image comparison and mathematical morphology methods is proposed. The unique feature of the technique is that the inspection is performed at different stages of image processing. The presence of all layout elements is checked up, then positions ...

      2023-11-28

    • Directional Derivatives of Value Functions in Parametric Nonlinear Programming 

      Leschov, Alexey; Minchenko, Leonid (BrSTU, 2015)
      Leschov, A. Directional Derivatives of Value Functions in Parametric Nonlinear Programming / A. Leschov, L. Minchenko // Modern problems of mathematics and computer engineering: a collection of materials of the IX Republican scientific conference of young scientists and students, Brest, November 19–21, ...

      2020-01-10