Поиск по всему репозиторию:

    • 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

    • 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

    • 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

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

      Bezobrazov, Sergei (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

    • 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

    • 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

    • 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

    • 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

    • Image Representation Based Hybrid Intelligent Diagnosis Approach for Computer Aided Diagnosis (CAD) Systems 

      Chohra, Amine; Kanaoui, Nadia; Madani, Kurosh (BrSTU, 2006)
      Computer Aided Diagnosis (CAD) is one of the most interesting and most difficult dilemma dealing in one hand with expert (human) knowledge consideration. On the other hand, fault diagnosis is a complex and fuzzy cognitive process and soft computing approaches as modular neural networks and fuzzy logic, ...

      2023-11-24

    • Neural Networks for Chaotic Signal Processing: Application to the Electroencephalogram Analysis for Epilepsy Detection 

      Golovko, Vladimir Adamovich; Bezobrazova, Svetlana Valeryevna (BrSTU, 2006)
      Many techniques were used in order to detect and to predict epileptic seizures on the basis of electroencephalograms. One of the approaches for the prediction of epileptic seizures is the use the chaos theory, namely determination largest Lyapunov's exponent or correlation dimension of scalp EEG ...

      2023-11-27

    • Resampling-down Mesh based Discriminant Filter Synthesis for Face Recognition 

      Samokhval, V. A. (BrSTU, 2006)
      Presented paper addresses face recognition algorithm by means o f synthetic discriminant filters synthesized in pseudo 3-D mesh domain. The objective of the research is to construct facial descriptor in the form of linear filter, which should produce high and low outputs for intra- and inter-class ...

      2023-11-24

    • On Application of the Ternary Matrix Cover Technique for Minimization of Boolean Functions 

      Pottosin, Yu. V.; Shestakov, E. A. (BrSTU, 2006)
      To solve the task of recognizing features of objects used in expert systems the Boolean function approach can be attracted. In particular, the relation between the features can be given as a disjunctive normal form (DNF) of the Boolean function whose arguments correspond to the features, and the rise ...

      2023-11-27

    • Neural Network Techniques for Intrusion Detection 

      Golovko, Vladimir; Vaitsekhovich, Leanid (BrSTU, 2006)
      This paper presents the neural network approaches for building of intrusion detection system (IDS). Existing intrusion detection approaches have same limitations, namely low detection time and recognition accuracy. In order to overcome these limitations we propose several neural network systems for ...

      2023-11-29

    • Matching on Graphs 

      Shut, Vasily Nikolaevich; Svirsky, V. M.; Solomiyuk, K. S.; Gryazev, E. V. (BrSTU, 2006)
      This work is devoted to development of new algorithm of the decision of a matter about matching. In the result the algorithm of search maximal matching in graphs has been developed and realized, the estimation of its complexity, and comparison with existing algorithms have been made. Its characteristics, ...

      2023-11-27

    • Information-Based Algorithmic Design 

      Hiromoto, Robert E.; Manic, Milos (BrSTU, 2006)
      An information-based design principle is presented that provides a framework for the design of both parallel and sequential algorithms. In this presentation, the notion of information (data) organization and canonical separation are examined and used in the design of an iterative line method for pattern ...

      2023-11-29

    • On the Inspection of Classification Results in the Fuzzy Clustering Method Based on the Allotment Concept 

      Viattchenin, Dmitri A. (BrSTU, 2006)
      Viattchenin, Dmitri A. On the Inspection of Classification Results in the Fuzzy Clustering. Method Based on the Allotment Concept / Dmitri A. Viattchenin // International Conference on Neural Networks and Artificial Intelligence : proceedings, Brest, 31 May – 2 June, 2006 / Edited: V. Golovko [et al.]. ...

      2023-11-23

    • International Conference on Neural Networks and Artificial Intelligence 

      Golovko, Vladimir Adamovich; Akira, Imada; Sadikhov, Rauf Khosrovovich; Dunets, Andrey Petrovich (BrSTU, 2006)
      This book collected the papers of the 4th International Conference on Neural Networks and Artificial Intelligence. They are arranged in following streams: Cyberspace Security and Defense, Neural Robotics, Neural Diagnosis, Neural Prediction, Pattern Recognition, Image Processing, Pattern Classification. ...

      2023-11-23