(18.206.177.17) 您好!臺灣時間:2021/04/23 05:50
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:蔡明宏
研究生(外文):Ming-hung Tsai
論文名稱:應用類神經網路於適應性通道等化器之設計
論文名稱(外文):Design of Artificial Neural Network Based Adaptive Channel Equalizer
指導教授:翁萬德
指導教授(外文):Wan-de Weng
學位類別:碩士
校院名稱:國立雲林科技大學
系所名稱:電機工程系碩士班
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:2013
畢業學年度:101
語文別:中文
論文頁數:33
中文關鍵詞:多層感知機網路線性最小均方等化器非線性通道等化器類神經網路Chebyshev函數連結類神經網路
外文關鍵詞:nonlinear channel equalizersCFLANNLINMLPneural network
相關次數:
  • 被引用被引用:0
  • 點閱點閱:129
  • 評分評分:系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔
  • 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,我們主要採用Chebyshev函數連結類神經網路 (Chebyshev functional link artificial neural network, CFLANN) 架構,實現於4-quadrature amplitude modulation (4-QAM) 數位通訊系統之通道等化器,並與2種不同架構的通道等化器進行比較,即 linear-least-mean-square based equalizer (LIN) 以及multilayer perceptron (MLP)。我們利用CFLANN非線性函數近似的特點,將原本較低輸入訊號空間維度下的線性不可分類問題,擴展至較高訊號空間的維度上,藉此形成線性可分類,解決了通道等化問題。另外,由於CFLANN主要是透過函數展開的方式,所以可以將MLP中較為複雜的隱藏層取代,因此CFLANN具有架構簡單、低計算複雜度以及收斂速度快的優點。由模擬結果顯示,CFLANN在網路訓練期間比LIN及MLP兩種通道等化器收斂更為快速,且在具有嚴重非線性失真及符際干擾的最差通道環境下,其BER之性能表現比MLP好3.8 dB,比LIN好7.7 dB。
In this thesis, we use Chebyshev functional link neural network (CFLANN) architecture to design a channel equalizer for 4-quadrature amplitude modulation (4-QAM) transmission systems. System performance was compared with two commonly used channel equalizers, namely, linear-least-mean-square based equalizer (LIN) and multilayer perceptron (MLP). The nonlinear approximation characteristics of Chebyshev functions can expand the low spatial dimensions of original input signals to higher ones, so as to solve the linearly unclassifiable problem. In addition, because CFLANN uses functional expansions instead of hidden layers, it has much simpler structure, lower computational complexity and higher speed of convergence. Simulation results show that CFLANN indeed present higher convergence rate than LIN and MLP during training mode. Under the circumstances of highly nonlinear distortion and severe inter-symbol interference, the bit error rate (BER) performance of CFLANN equalizer is 3.8 dB and 7.7 dB better than MLP and LIN, respectively.
目錄
中文摘要 i
ABSTRACT ii
誌謝 iii
目錄 iv
表目錄 v
圖目錄 vi
第一章 緒論 1
第二章 通道等化器及類神經網路之應用 4
2.1 類神經網路應用在通道等化器 4
2.2 適應性等化 4
2.3 假雜訊序列 5
2.4 等化器之操作 6
2.5 類神經網路簡介 7
第三章 CFLANN通道等化器設計 15
3.1 MLP架構 15
3.2 LIN架構 16
3.3 CFLANN架構 17
3.4系統描述 18
3.5 Chebyshev多項式 19
第四章 模擬結果 20
4.1 模擬背景 20
4.2 計算複雜度之比較 22
4.3 學習曲線效能比較 23
4.4 BER效能比較 27
第五章 結論 31
參考文獻 32
[1]F. Rosenblatt, “ The perceptron : A probabilistic model for information storage andorganization in the brain,” Psychological Review, Vol. 65, pp. 386-408, 1958.
[2]J. Hopfield, “Neural networks and physical systems with emergent collective computational abilites,” Proceedings of the National Academy of Sciences, Vol. 79, pp. 2554-2558, 1982.
[3]D. Rumelhart and J. McClelland, eds., Parallel Distributed Processing : Explorations in the Microstructure of Cognition, Vol. 1, Cambridge, MA : MIT Press, 1986.
[4]S. Siu et al, “Decision feedback equlization using neural network structures and performance comparison with standard architecture,” Proc. Inst. Elect. Eng, vol. 137, pt. 1, pp.221-225, Aug. 1990.
[5]S. Chen et al, “Adaptive channel equalization using a polynomial perceptron
structure,” Proc. IEE, Pt. I, Vo1.137, pp.257-264, October 1990.
[6]D. Jianping et al, “Communication channel equalization using complex–valued minimal radial basis function neural networks,” IEEE Trans. Neural Networks, vol. 13, no. 3, pp. 687-696, May 2002.
[7]I. Cha and S. Kassam, “Channel equalization using adaptive complex radial basis function networks,” IEEE J. Select. Area Commun., vol. 13, pp. 122-131, Jan. 1995.
[8]T. Kohonen, “The self-organizing,” Proc. IEEE, vol. 78, no. 9, pp. 1464-1480, 1990.
[9]Y. Guo and Z. Zhang, “Wavelet Blind Equalization Algorithm Based on Support
Vector Machine.”, pp.329-332, June. 2010.
[10]S. Choi and D. Hong, “Equalization using the bilinear recursive polynomial perceptron with decision feedback,” Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks, Volume: 5, pp. 366-71, July
2000.
[11]R. G. Bartle and D. R. Sherbert, Introduction to Real Analysis, 3nd ed., New York: Wiley, 2000.
[12]Y. H. Pao and Y. Takefuji, “Functional-link net computing: theory, system architecture, and functionalities,”Computer, Volume: 25 Issue: 5, pp. 76-79, May 1992.

[13]K. Hornik, M. Stinchcombe, and H. White,“Multilayer feedforward networks are universal approximators,”Neural Networks, vol. 2, no. 5, pp. 359-366, 1989.
[14]W. S. Gan, J. J. Soraghan, and T. S. Durrani,“New Functional-link based Equalizer,”Electronics Letters, vol. 28, no. 17, pp. 1643-1645, Aug. 1992.
[15]C. Y. Lee et al,“A MLP/BP-based equalizer for NRZ signal recovery in band-limited channels,”Proceedings of the 43rd IEEE Midwest Symposium on Circuits and Systems, vol. 3, pp. 1340 –1342, 2000.
[16]J. C. Patra et al., “ Nonlinear dynamic system identification using Chebyshev functional link artificial neural networks,” IEEE Trans. Syst., Man Cybern.-B, vol. 32, pp. 505-511, Aug. 2002.
[17]S. Haykin, Communication Systems, 4th ed., New york: Wiley,2001.
[18]A. Cichocki and R. Unbehauen, “Neural Networks for Optimization and Signal Processing,” New York: Wiley, 1993.
[19]D. G. Luenberger, Optimization by Vector Space Methods, New York: Wiley,
1969.
[20]C. Charalambous, “Conjugate gradient algorithm for efficient training of
artificial neural networks,” IEE Proceedings, vol. 139, no. 3, pp. 301-310, 1992.
[21]M. T. Hagan and M. Menhai, “Training feedforward networks with the
Marquardt algorithm,” IEEE Trans. Neural Networks, vol. 5, no. 6, 1994.
[22]D. E. Rumelhart, G. E. Hinton, and R. J. Williams, “Learning representations by
backpropogating errors,” Nature, vol. 323, pp. 533-536, 1986.
[23]C. You and D. Hong, “ Adaptive equalization using the complex backpropagation
algorithm,” IEEE International Conference on Neural Networks, vol. 4, pp. 2136
–2141, Jun. 1996.
[24]J. G. Proakis, Digital Communications, 3rd ed., New York: McGraw-Hill, 1995.
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
系統版面圖檔 系統版面圖檔