Advanced Search

ISSN1001-3806 CN51-1125/TN Map

Volume 33 Issue 4
Aug.  2009
Article Contents
Turn off MathJax

Citation:

Application study on neural network and genetic algorithm in the interpretation of correlation peak

  • Corresponding author: SHAO Jun, sj_opt@163.com
  • Received Date: 2008-06-12
    Accepted Date: 2008-08-27
  • In order to identify correlation peak better in the research of target recognition technology based on coherent optics,combining the genetic algorithm(GA)and the artificial neural network(ANN),based on GA and back propagation(BP)neural network,a correlation peak identification system was built with GA optimizing the initial weights and thresholds of the ANN.The optimized identification system could not only avoid the tendency of local minimum and slow convergence speed in ANN training,but also overcome the shortage of local precise searching capacity in GA.It realizes the superiority complementation between the both the methods,and is helpful to solve the problem of recognizing correlation peak.The testing results show that the improved method makes full use of the advantages of GA and BP algorithm,and gets much better interpretation effect.
  • 加载中
  • [1]

    PELCKMANS K,SUYKENS J A K,de MOOR B.Building sparse representations and structure determination on LS-SVM substrates[J].Neurocomputing,2005,64(3):137-159.
    [2]

    YANG Q D,LI J Zh.Design the weight and threshold of artificial neu-ral network based on the genetic algorithm[J].Journal of TianjinUniversity,2003,36(3):782-786(in Chinese).
    [3]

    XIA G F,ZHAO B J,HAN Y Q.Chaotic weak signal detection in the long range laser rangefinders using neural network[J].Laser Technology,2006,30(5):449-451(in Chinese).
    [4]

    KERMANI B G.Using neural network and genetic algorithm to en-hance performance in an electronic nose[J].IEEE Transactions on Biomedical Engineering,1999,46(4):429-439.
    [5]

    LUO B L,WANG Ch Ch,DU J L.Study on laser beam combination by binary phase grating[J].Laser Technology,2006,30(4):381-389(in Chinese).
    [6]

    MU K J,ZHOU X J,REN G R,et al.Reconstruction of parameters of fiber gratings from time-delay characteristics using the genetic algorithm[J].Chinese Journal of Lasers,2007,34(5):687-693(in Chinese).
    [7]

    van ROOI A J F,JAIN J L C,JOHNSON R P.Neural network training using genetic algorithms[M].Singapore:World Scientific Publishing Co Pte Ltd,1996:136-147.
    [8]

    XU D P,ZHOU J Zh,GUO H F,Quality prediction of laser cladding layer based on improved neural network[J].Laser Technology,2007,31(5):511-514(in Chinese).
    [9]

    Fecit.Neural network theroy and MATLAB 7 application[M].Beijing:Publishing House of Electronic Industry,2005:89-115(in Chinese).
    [10]

    XIE T,CHEN H W.Evolutionary algorithms for multi-objective optimization and decision-making problems[J].Engineering Science,2002,4(2):59-67(in Chinese).
  • 加载中
通讯作者: 陈斌, bchen63@163.com
  • 1. 

    沈阳化工大学材料科学与工程学院 沈阳 110142

  1. 本站搜索
  2. 百度学术搜索
  3. 万方数据库搜索
  4. CNKI搜索

Article views(4233) PDF downloads(181) Cited by()

Proportional views

Application study on neural network and genetic algorithm in the interpretation of correlation peak

    Corresponding author: SHAO Jun, sj_opt@163.com
  • 1. Department of Optical and Electronic Engineering, Ordnance Engineering College, Shijiazhuang 050003, China

Abstract: In order to identify correlation peak better in the research of target recognition technology based on coherent optics,combining the genetic algorithm(GA)and the artificial neural network(ANN),based on GA and back propagation(BP)neural network,a correlation peak identification system was built with GA optimizing the initial weights and thresholds of the ANN.The optimized identification system could not only avoid the tendency of local minimum and slow convergence speed in ANN training,but also overcome the shortage of local precise searching capacity in GA.It realizes the superiority complementation between the both the methods,and is helpful to solve the problem of recognizing correlation peak.The testing results show that the improved method makes full use of the advantages of GA and BP algorithm,and gets much better interpretation effect.

Reference (10)

Catalog

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return