Title page for 89521066


[Back to Results | New Search]

Student Number 89521066
Author Cong-Xing Wang(王琮星)
Author's Email Address s9521066@cc.ncu.edu.tw
Statistics This thesis had been viewed 1884 times. Download 1533 times.
Department Electrical Engineering
Year 2001
Semester 2
Degree Master
Type of Document Master's Thesis
Language zh-TW.Big5 Chinese
Title 進化演算法應用在多層感知迴授等化
器上之效能分析
Date of Defense 2002-06-19
Page Count 71
Keyword
  • EA
  • Abstract 模擬類神經網路(Nerous network)的多層感知機(MLP)架構,其非線性的特性結構運用在調適性等化器(Adaptive Equalizer)上,可解決訊號空間的非線性問題。而訊號受符元干擾(ISI)和Noise的影響,等化器的運用是必要的。傳統式調適性等化器利用最小均方差演算法(Least Mean Square, LMS),而多層感知機的網路學習演算法則為倒傳遞演算法(Backpropagation algorithm, BP)。
      本篇論文將探討進化演算法(Evolution algorithms ,EAs),並將之應用在多層感知機(MLP)之後遞式判別回授等化器(Decision Feedback Equalizer, DFE)上。利用進化演算法全域搜尋(global search)的特性,使等化器的效能達到更理想的狀態。EA是模擬生物基因演進的運用法則,經由交配(crossover)、突變(mutate)、選擇(selection)等程序,找出等化器最佳係數解。此論文並針對各個程序步驟做深入探討,並分析各參數值(parameter)對效能(performance)的影響,更完整建構進化演算法(EA)的設定,使EA能在運用上有更佳的效能。
    Table of Content 目錄                          頁碼
    --------------------------------------------------------------
    摘要
    誌謝
    目錄......................................................I
    圖目、表目..............................................III
    第一章  緒論(introduction)..............................1
    1.1 前言.................................................1
    1.2 等化器(Equalizer)的運用..............................3
    1.3 調適性等化器(adaptive equalizer).....................6
    第二章  回授等化器(Decision Feedback Equalizer).........8
    2.1 類神經網路(Neural Network)...........................8
    2.2 多層感知器(Multilayer Perceptrons)..................11
    2.3 多層感知回授等化器(MLP decision feedback equalizer).14
    2.4 消除符元干擾(ISI)...................................18
    2.5 倒傳遞演算法(Backpropagation algorithm).............20
    第三章  進化演算法(Evolution Algorithm)................28
    3.1 進化演算法簡介......................................28
    3.2 染色體初始值........................................30
    3.3 交配(crossover).....................................31
    3.4 突變(mutation)......................................33
    3.5 評估(evaluation)....................................34
    3.6 選擇(selection).....................................35
    第四章  模擬與結果(Simulation and Results).............38
    4.1 收斂特性(convergence characteristics)...............39
    4.2 位元錯誤率(Bit error rate)..........................42
    4.3 決策區間(Decision Region) ..........................47
    4.4 適存函數(fitness)...................................52
    4.5 EA設定值的探討......................................55
    第五章  結論(Conclusion) ..............................67
    參考文獻(Reference) .....................................69
    Reference [1] S. Siu, G.J. Gibson, and C.F.N. Cowan, “Decision feedback equalizer using
       neural network structures and performance comparison with standard
       architecture”, IEE Proc. Part I, Communication, Speech, and Vision,
       Vol.137, NO.4, pp 221-225,August, 1990.
    [2] S. Siu, and C.F.N. Cowan, “Performance analysis of the norm back
       propagation algorithm for adaptive equalizer” IEE Proc.Part F, Vol. 140,
       No. 1, Febr. 1993.
    [3] S. Siu, C.H. Chang, and C.H. Wei, Transactions Briefs,“ Norm Back
       Propagation Algorithm For Adaptive Equalizer”, IEEE Transactions on  
       circuits and systems-II: Analog and digital sigital processing, vol.42,
       no.9, September 1995.
    [4] Y.H. Pao,“Adaptive Pattern Recognition and Neural Networks”,Case
       Western Reserve University.
    [5] P. Power, F. Sweeney, C.F.N. Cowan,“EA Crossover Schemes for a MLP
       Channel Equaliser”IEEE, 1999.
    [6] T. Bäck, H.P. Schwefel, “Am overview of evolutionary algorithms for
       parameter optimizarion”, University of Dortmund Department of Computer
       Science XI P.O Box 50 05 00 . D-4600 Dortmund 50 . Germany.
    [7] Simon Haykin, Communucation systems , 3rd edition , WILEY
    [8] Simon Haykin, Adaptive Filter Theory, 3rd edition , Prentice-Hall, Inc.
       1996
    [9] G.J. Gibson, S. Siu, C.F.N. Cowan, “The application of nonlinear
       structures to the reconstruction of binary signal”, IEEE Trans. On Signal
       Processing, Vol. 39, No. 8,pp.1877-1884, Aug, 1991.
    [10] G.J. Gibson, S. Siu, and C.F.N. Cowan, “Application of Multi-layer
       Perceptron as Adaptive Channel Equalizers”, Adaptive Systems in Control
       and Signal Processing 1989. Selected papers from the IFAC Symposium,
       Glasgow, U.K.,19-21 April 1989 (Oxford, U.K. : Pergamon)
    [10] G.J. Gibson, and C.F.N. Cowan, “On the decision regions of multiplayer
       perceptrons”, Proc. of the IEEE, vol. 78, pp. 258-262.
    [11] P. Power, F. Sweeney, C.F.N. Cowan, “ Non-linear Mlp Channel
       Equalisation” , Statistical Signal Processing (Ref. No. 1999/002), IEE 
       Colloquium on , 6 January 1999.
    [12] S. Qureshi, “Adaptive Equalisation”, Proceedings of the IEEE, Vol.73,
       No.9 pp.1349-1387,Sept.1985.
    [13] Bernard Sklar, DIGITAL COMMUNICATIONS Fundamental and Applications,
       Prentice-Hall, Inc. 1988
    [14] 傅心家, 神經網路導論, 第三波文化事業股份公司 。
    [15] 林繼洲, 函數連結與模糊適應等化器效能評估,
       元智大學電機工程研究所碩士論文, 1999.
    [16] 張吉良, 利用進化演算法在多層感知結構之判別回授等化器,
       中央大學電機工程研究所碩士論文, 2001.
    [17] 陳德, 模糊類神經網路結合進化演算法運用在基頻通道等化器上,
       中央大學電機工程研究所碩士論文, 2001.
    [18] 蘇木春,張孝德, 機器學習—類神經網路、模糊系統以及基因演算法則,
       全華科技圖書股份有限公司, 二版, 1997.
    [19] 吳志峰, 具有QAM/VSB雙模式等化器之數位積體電路設計,
       中央大學電機工程研究所碩士論文,1998.
    Advisor
  • Chia-Lu Ho(賀嘉律)
  • Files
  • 89521066.pdf
  • approve immediately
    Date of Submission 2002-06-20

    [Back to Results | New Search]


    Browse | Search All Available ETDs

    If you have dissertation-related questions, please contact with the NCU library extension service section.
    Our service phone is (03)422-7151 Ext. 57407,E-mail is also welcomed.