跳到主要內容

臺灣博碩士論文加值系統

(44.210.85.190) 您好!臺灣時間:2022/12/06 02:16
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

我願授權國圖
: 
twitterline
研究生:游騰元
研究生(外文):YOU,TENG-YUAN
論文名稱:粒子群聚演算法連結類神經網路適應性通道等化器之設計
論文名稱(外文):Design of Particle Swarm Optimization Link Artificial Neural Network Based Adaptive Channel Equalizer
指導教授:翁萬德
指導教授(外文):WENG,WAN-DE
口試委員:翁萬德竇 奇陳永隆
口試委員(外文):WENG,WAN-DEDOU,CHIECHEN,YOUNG-LONG
口試日期:2017-07-06
學位類別:碩士
校院名稱:國立雲林科技大學
系所名稱:電機工程系
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2017
畢業學年度:105
語文別:中文
論文頁數:54
中文關鍵詞:符際效應類神經網路粒子群聚演算法最小均方演算法
外文關鍵詞:ISIFLANNPSOLMS
相關次數:
  • 被引用被引用:0
  • 點閱點閱:125
  • 評分評分:
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:0
在本論文中,我們選擇使用三角多項式基底函數(trigonometric polynomial basis functions),並連結類神經網路(functional link artificial neural network, FLANN) 架構,及應用粒子群演算法(particle swarm optimization,簡稱PSO),來設計一通道等化器來補償信號傳輸過程所造成的失真現象。
PSO在收斂最佳解的過程中,會記下自己所經歷的最大的值為區域最佳值(local optimal),所有區域最佳值中的最大值把訊息分享之後,而得知的全域最佳值(global optimal),也會被記錄下來為群體的記憶,藉由記憶訊息的分享,亦即經由與個別最佳(local best)、群體最佳(global best)的比較,來調整收斂的方向,決定下一步收斂的速度,包括下一步收斂的方向和距離,迭代演算搜尋找到最佳解。
由實驗結果顯示,網路訓練期間FLANN(PSO)及FLANN(LMS)在同等條件時,相比之下FLANN(PSO)收斂速度較FLANN(LMS)快,例如在CH1、NL1的情況下,以收斂在10e-4時為例,FLANN(PSO)約收斂在15000左右,FLANN(LMS)約收斂在30000,而在非線性失真與符際效應(inter-symbol interference, ISI)的通道環境下,以學習因子 =0.006,及訊噪比 (signal to noise ratio, SNR)於14dB的位元錯誤率(bit error rate, BER)來觀察,在10e-4時FLANN(PSO)約在12.7 dB,FLANN(LMS)約在13 dB。故可得知PSO比LMS在效能上較優秀。

In this thesis, utilize a trigonometric polynomial basis functions link artificial neural network (FLANN) structure particle swarm optimization (PSO) is used in the design of a channel equalizer to compensate signal distortion during transmission.
PSO in the convergence process, will store the maximum value that they have experienced, call “local optimal”. All the maximum value of “local optimal” to share the message after the know “global optimal”, will also be recorded for the memory of the group, by sharing the memory of the message. That is, by “local best and “global best” comparison, to adjust the convergence direction and the next step of convergence speed. Iteration calculus search to find the best solution.
From the experimental results show, we can know under the same conditions FLANN(PSO) has faster speed of convergence in network training stage than FLANN(LMS). For example, in the case of CH1,NL1, to converge in 10e-4 as a benchmark, FLANN (PSO) converges about 15,000, while FLANN (LMS) converges about 30000. In the nonlinear distortion and inter-interference (ISI) channel environment, the learning factor =0.006 and SNR at 14 dB BER to observe, at 10e-4 , FLANN(PSO) is approximately 12.7 dB, FLANN (LMS) is approximately 13 dB. It can be learned that PSO is superior to LMS in terms of performance.

目錄
摘要 i
ABSTRACT ii
誌謝 iii
目錄 iv
圖目錄 vi
第一章 緒論 1
1.1前言 1
1.2研究動機與目的 4
1.3研究方法 5
1.4各章節題要 5
第二章 類神經網路、演算法及通道介紹 6
2.1類神經網路介紹 6
2.1.1神經網路簡介 6
2.1.2類神經網路模型 7
2.1.3類神經網路工作原理 11
2.1.4倒傳遞類神經網路(back propagation neural network, BPN) 13
2.2傳輸通道介紹 16
2.2.1多重路徑傳輸(multipath propagation) 16
2.2.2符際干擾(inter symbol interference,ISI) 17
2.3類神經網路演算法之介紹 18
2.3.1最小均方演算法(least mean square, LMS) 18
2.3.2粒子群聚演算法(particle swarm optimization, PSO) 21
第三章 FLANNPSO通道等化器之設計 24
3.1 類神經網路-FLANNPSO 24
3.1.1 FLANNPSO之架構模型 24
3.1.2基底函數(basis function) 26
3.1.3 FLANN之PSO演算法 27
第四章 實驗結果與分析 29
4.1 函數展開系統效能分析 30
4.2 BER效能之比較 37
第五章 結論與未來發展 43
參考文獻 44


[1] W. D. Weng and C.T. Yen, “Reduced-decision feedback FLANN nonlinear
channel equaliser for digital communication systems”, IEE Proceedings-
Communications, vol. 151, pp. 305 -311, 2004.
[2] J. Kennedy and R. C. Eberhart, “Particle swarm optimization”, in: Proc.
IEEE Int. Conf. on Neural Networks, Perth, Australia, vol. 4, pp. 1942-
1948, 1995.
[3] R. C. Eberhart, J. Kennedy, “A new optimizer using particle swarm theory,”
in: Proc. IEEE Int. Symposium on Micro Machine and Human Science, Nagoya,
Japan, pp. 39-43, 1995
[4] Sandhya Yogi*, Prof. K.R. Subhashini**, Prof. J.K.Satapathy***, “A PSO
based Functional Link Artificial Neural Network training algorithm for
Equalization of Digital Communication Channels”, 2010 5th International
Conference on Industrial and Information Systems, ICIIS 2010, Jul 29 - Aug
01, 2010, India
[5] 张媛媛,徐科军,许耀华.改进PSO演算法结合FLANN在传感器动态建模中的应用.震动与冲
击,2009,28(1):01-03,08
[6] Abolfazl Amiri† and Behrouz Maham‡, “Inter-Symbol Interference Analysis in
Neuro-Synaptic Communications”, 2016 8th International Symposium on
Telecommunications (IST’2016),pp.478-483
[7] 陳清良,應用類神經網路與粒子群演算法於冰水主機負載分配最佳化,國立台北科技大學能源與
冷凍空調工程系博士班,2004
[8] Pournamasi Parhi , Debahuti Mishra, Sashikala Mishra, Kailash Shaw. Author
links open the author workspace, “A Novel PSO-FLANN Framework of Feature
Selection and Classification for Microarray Data”, Procedia Engineering 38
( 2012 ) 1644 – 1649
[9] 王郁淳,結合粒子群演算法及類神經網路技術於塑膠射出成型產品之成本預估,國立台北科技大
學,工業工程與管理系碩士班,2007
[10]Young-Long Chen*,Wan-Ren Chen, “Particle Swarm Optimization with Taguchi
for Cluster Heads Election in Wireless Sensor Networks”, Appl. Math. Inf.
Sci. 9, No. 4, 2015-2022 (2015)
[11]Zhijin Zhao, Mingming Jin, “The Decorrelated Kernel Least-Mean-Square
Algorithm,School of Telecommunication Engineering of Hangzhou Dianzi
University, Hangzhou , China,2016,pp.367-371.
[12]I. A. Basheer, and M. Hajmeer, "Artificial neural networks:
Fundamentals,computing, design, and application," Journal of
Microbiological Methods, vol.43, iss. 1, 2000, pp. 3-31.
[13]T. T. Chow, Z. Lin, C. L. Song, G. Q. Zhang, “Applying neural network and
genetic algorithm in chiller system optimization”, Building Simulation,
Seventh International IBPSA Conference (2001) 1059-1065.
[14]A. Vellido, P. J. G. Lisboa, J. Vaughan, “Neural Networks in Business: A
Survey of Applications (1992-1998)”, Expert Systems with Applications
(17), 1999, pp. 51-70.
[15]趙景明,導入LM法之平行倒傳遞演算法,資訊管理展望,第8卷,第2期,2006。
[16]Jun Liu ,”Wireless Multipath Fading Channels Modeling and Simulation Based
on Sum-of-Sinusoids,” First IEEE International Conference on Computer
Communication and the Internet, pp. 165-168, 2016
[17]Bingham, J.A.C. ”Multicarrier Modulation for Data Transmission : An Idea
Whose Time Has Come,” IEEE Commun., Mag., May 1990;28: 14
[18]吳奇峰,適應性分碼多工多用戶檢測,國立中山大學通訊工程研究所,2003
[19]Frans van den Bergh and Andries P.Engelbrecht,” A Cooperative Approach to
Particle Swarm Optimization,” IEEE Transactions on Evolutionary
Computation,VOL.8,NO.3,2004,pp225-239
[20]R.C. Eberhart, Y. Shi., “Comparison between genetic algorithms and
particle swarm optimization”, Annual Conference on Evolutionary
Programming, San Diego, 1998.
[21]D. Srinivasan, W.H. Loo, R.L. Cheu, “Traffic incident detection using
particle swarm optimization”, Swarm Intelligence Symposium, Proceedings of
the 2003 IEEE, pp.144-151.

電子全文 電子全文(網際網路公開日期:20221231)
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
無相關期刊