Search

Now showing items 1-10 of 10

    • Application of algorithms for searching motion in the frame for the detection of vehicles 

      Анфилец, Сергей Викторович; Касьяник, Валерий Викторович; Шуть, Василий Николаевич (BSUIR, 2011)
      In the paper discusses methods for detecting moving objects in the video stream. It is proposed combined algorithm applied to the detection of vehicles. The results of testing under real conditions revealed a fairly high percentage of detection in order to be able to apply it in the detectors of transport.

      2023-11-20

    • Behavior Patterns of adaptive Multi-Joined Robot learned by Multi-Agent Influence Reinforcement Learning 

      Kabysh, Anton; Golovko, Vladimir; Mikhniayeu, Andrei; Rubanau, Uladzimir; Lipnikas, Arunas (BSUIR, 2011)
      This paper describes behavior patterns produced by Multi-Joined Robot learned via Influence Reinforcement learning. This learning technique used for distributed, adaptive and self-organizing control in multi-agent system. This technique is quite simple and uses agent’s influences to estimate learning ...

      2023-10-23

    • Computing of Lyapunov Exponents Techniques Using Neural Networks 

      Golovko, Vladimir; Savitsky, Yury (BSUIR, 2003)
      The authors examine neural network techniques for computing of Lyapunov spectrum using observations from unknown dynamical system. Such an approach is based on applying of multilayer perceptron (MLP) for forecasting the next state of dynamical system from the previous one. It allows for evaluating the ...

      2023-11-17

    • Dynamic windows scaling in Unix-like systems interface 

      Diomin, Vladimir; Kostiuk, Dmitriy; Nikoniuk, Alexander (BSUIR, 2011)
      The models of a scaled down window and of a window with variable scale are presented, as far as their practical implementation for Unix-like systems as the Compiz window manager extension modules. An implementation specific is provided for the X Window System environment. Changes in the original window ...

      2023-11-20

    • Neural Network Model for Transient Ischemic Attacks Diagnostics 

      Golovko, Vladimir; Apanel, Elena; Mastykin, Alexander; Vaitsekhovich, Henadzi; Evstigneev, Victor (BSUIR, 2011)
      In this paper the neural network model for transient ischemic attacks recognition have been addressed. The proposed approach is based on integration of the NPCA neural network and multilayer perceptron. The dataset from clinic have been used for experiments performing. Combining two different neural ...

      2023-11-20

    • Neural Networks for Chaotic Time Series Forecasting 

      Golovko, Vladimir; Savitsky, Yury (BSUIR, 2001)
      This paper examines neural network in order to predict behavior o f chaotic systems. The prediction is performed both on the level o f emergent structures and on the level o f individual data points. The network is tested using the Henon and Lorenz chaotic time series. The results o f experiments and ...

      2023-11-16

    • Some Aspects of Chaotic Time Series Analysis 

      Golovko, Vladimir; Savitsky, Yury; Maniakov, Nikolaj; Rubanov, Vladimir (BSUIR, 2001)
      We address two aspects in chaotic time series analysis, namely the definition of embedding parameters and the largest Lyapunov exponent. It is necessary for performing state space reconstruction and identification of chaotic behavior. For the first aspect, we examine the mutual information for ...

      2023-11-16

    • Some Methods of Adaptive Multilayer Neural Network Training 

      Maniakov, Nikolaj; Makhnist, Leonid; Rubanov, Vladimir (BSUIR, 2003)
      Is proposed two new techniques for multilayer neural networks training. Its basic concept is based on the gradient descent method. For every methodic are showed formulas for calculation of the adaptive training steps. Matrix algorithmizations for all of these techniques are very helpful in its program ...

      2023-11-16

    • Training of the recurrent neural networks for prediction 

      Savitsky, Jury; Golovko, Vladimir (BSUIR, 1999)
      In this paper the technique of creation of effective methods of training recurrent neural network for prediction problems are discussed. The various functions of activation of neural units are considered. The adaptive algorithms of training of neural networks with varied functions of activation of ...

      2023-11-15

    • Генерация слов смежных классов кода Хэмминга 

      Махнист, Леонид Петрович (BSUIR, 1999)
      Предложен алгоритм формирования слов фиксированного веса смежных классов кода Хэмминга

      2023-11-15