The Experts below are selected from a list of 25563 Experts worldwide ranked by ideXlab platform

Wang Zhi-quan - One of the best experts on this subject based on the ideXlab platform.

  • Study of Internet Traffic Data Flow Forecast of RBF Neutral Network Based on Chaos Theory
    Computer Engineering, 2006
    Co-Authors: Wang Zhi-quan
    Abstract:

    Chaotic characteristics of the Internet traffic data flows is studied on the theory of the phase space reconstruction,and some parameters such as correlative dimension and Lyapunov exponent are computed,the Internet traffic chaos phenomena lying in Internet traffic data flows are demonstrated.A radial basic function(RBF) Neutral Network model is constructed to forecast the Internet traffic data flows.The simulation results show that the forecast method of the RBF Neutral Network compared with the forecast method of back propagation(BP) Neutral Network has faster learning capacity and higher accuracy of forecast.

Liu Cong - One of the best experts on this subject based on the ideXlab platform.

  • Prediction of capacity of aeronautic battery based on wavelet Neutral Network
    Chinese Journal of Power Sources, 2011
    Co-Authors: Liu Yong-zhi, Liu Cong
    Abstract:

    In order to predict the residual capacity of aeronautic battery effectively,the WNN was used to build the wavelet Neutral Network models of internal resistance and SOC of battery.After training the wavelet Neutral Network model by experiment data,the wavelet Neutral Network for predicting internal resistance and SOC was obtained.Comparing the predicting results of wavelet Neutral Network with BP,the results show that the result of comparing the predicting results of the WNN with the BP shows that the wavelet Neutral Network with a higher precision is more suitable for the prediction of SOC than BP NN.

Du Mei-fan - One of the best experts on this subject based on the ideXlab platform.

Zheng Jia - One of the best experts on this subject based on the ideXlab platform.

  • Prediction of Mooring Load Based on Wavelet Neutral Network
    Computer Simulation, 2013
    Co-Authors: Zheng Jia
    Abstract:

    Research the accurate prediction of ship mooring load. Ship mooring load has strong randomness and complexity,and is a non-stationary time series. The paper put forward a mooring load prediction method based on wavelet Neutral Network. The model combines the characteristic of wavelet analysis with the advantage of Neutral Network. The wavelet basis function has been used as the transfer function of neural Network's hidden layer nodes. Then the wavelet Neutral Network forecasting model was built up to realize the forecasting calculation of mooring load data.The simulation results show that the wavelet Neutral Network algorithm attains high-precision forecast results. It can meet requirements of short-term early-warning of mooring load.

Sébastien Verel - One of the best experts on this subject based on the ideXlab platform.

  • The Road to VEGAS: Guiding the Search over Neutral Networks
    2011
    Co-Authors: Marie-eleonore Marmion, Clarisse Dhaenens, Laetitia Jourdan, Arnaud Liefooghe, Sébastien Verel
    Abstract:

    VEGAS (Varying Evolvability-Guided Adaptive Search) is a new methodology proposed to deal with the Neutrality property of some optimization problems. ts main feature is to consider the whole Neutral Network rather than an arbitrary solution. Moreover, VEGAS is designed to escape from plateaus based on the evolvability of solution and a multi-armed bandit. Experiments are conducted on NK-landscapes with Neutrality. Results show the importance of considering the whole Neutral Network and of guiding the search cleverly. The impact of the level of Neutrality and of the exploration-exploitation trade-off are deeply analyzed.

  • GECCO - The road to VEGAS: guiding the search over Neutral Networks
    Proceedings of the 13th annual conference on Genetic and evolutionary computation - GECCO '11, 2011
    Co-Authors: Marie-eleonore Marmion, Clarisse Dhaenens, Laetitia Jourdan, Arnaud Liefooghe, Sébastien Verel
    Abstract:

    VEGAS (Varying Evolvability-Guided Adaptive Search) is a new methodology proposed to deal with the Neutrality property that frequently appears on combinatorial optimization problems. Its main feature is to consider the whole evaluated solutions of a Neutral Network rather than the last accepted solution. Moreover, VEGAS is designed to escape from plateaus based on the evolvability of solutions, and on a multi-armed bandit by selecting the more promising solution from the Neutral Network. Experiments are conducted on NK-landscapes with Neutrality. Results show the importance of considering the whole identified solutions from the Neutral Network and of guiding the search explicitly. The impact of the level of Neutrality and of the exploration-exploitation trade-off are deeply analyzed.