(3.227.208.0) 您好!臺灣時間:2021/04/20 16:36
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:傅篤棟
研究生(外文):Fuh Duu-Tong
論文名稱:類神經網路系統自動辨識不穩定摩斯碼
論文名稱(外文):Unstable Morse Code Auto-Recognition System using Neural Networks
指導教授:羅錦興羅錦興引用關係
指導教授(外文):Ching-Hsing Luo
學位類別:博士
校院名稱:國立成功大學
系所名稱:電機工程學系碩博士班
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:2003
畢業學年度:91
語文別:英文
論文頁數:80
中文關鍵詞:摩斯碼類神經
外文關鍵詞:Bayesian decision boundarySelf-Organizing-MapExpert-GatingBack Propagationneural networkMorse code
相關次數:
  • 被引用被引用:0
  • 點閱點閱:190
  • 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:25
  • 收藏至我的研究室書目清單書目收藏:1
摩斯碼是現今最重要的通訊工具之一。標準摩斯碼定義有聲及無聲的長短音比皆為3:1,除專業人士外,一般人無法精確掌控此比率且兩種比率--有聲及無聲長短音比--是不相同的;因此摩斯碼自動辨識系統僅限於專業人士鍵入的穩定速率及穩定比率。對於不穩定的摩斯碼自動辨識系統,文獻上並無足夠好的演算法可應用。在此論文中提出四種以類神經網路架構的演算法自動辨識不穩定摩斯碼:第一種是以倒傳遞(Back Propagation)類神經網路演算法辨識有聲及無聲摩斯碼,第二種是以專家(Expert)類神經網路演算法辨識有聲摩斯碼,以柵欄(Gating)類神經網路演算法辨識無聲摩斯碼,第三種是以自我組織映射的學習向量量化類神經網路演算法辨識有聲摩斯碼,以修正追蹤Bayesian界面(Bayesian decision boundary)類神經網路演算法辨識無聲摩斯碼,第四種是以修正追蹤Bayesian界面類神經網路演算法辨識有聲及無聲摩斯碼。實驗對象以腦性麻痺患者、初學者、截肢者及專業人士等。由實驗結果顯示四種演算法對於腦性麻痺患者的平均辨識率可高到91%以上,初學者的平均辨識率在96%以上,截肢者使用義肢打摩斯碼的平均辨識率可高到97%以上;與專業人士的99%摩斯碼平均辨識率比較,以上的結果是相當滿意。四種類神經網路演算法都集中精神於分類長短音,而不是長短音比;所以以上四種類神經網路都能克服困難而成功的分析不穩定摩斯碼。雖然類神經網路的學習及辨識需大量的運算時間,由於人類的打字速度相較於電腦的訊號處理慢很多,所以可用類神經網路做即時的訊號辨識。
Morse code continues to be one of the most important communication tools in use nowadays. Standard Morse code specifies tone ratios (dash/dot) and silence ratios (dash-space/dot-space) of 3:1. An effective Morse code auto-recognition system requires the operator to maintain these ratios precisely and to demonstrate a consistent typing speed. However, these requirements are seldom met by even the most experienced operators, while for operators with disabilities, they are virtually impossible to satisfy. Studies have shown that the auto-recognition algorithms published previously do not compensate adequately for the resultant unstable Morse code. Therefore, this thesis presents four single-chip neural networks designed to perform a more effective online auto-recognition of such code. The first method employs a Back Propagation Neural (BPN) network which recognizes the tone and silence signals of Morse code individually. The second proposal adopts a Modified Expert-Gating neural network, in which the Expert network recognizes the tone signals, and the Gating network identifies the silence signals. The third approach implements a modular neural network (MNN) which uses a Self-Organizing-Map (SOM) neural network to recognize the tone signals and a Modified Track Bayesian (MTB) decision boundary neural network to recognize the silence signals. The final method adopts two MTB decision boundary neural networks to recognize the tone and silence signals individually. The effectiveness of each network is verified by analyzing the auto-recognition results for Morse code transmissions generated by four test subjects of varying abilities, i.e. a skilled operator, a novice operator, an amputee and a cerebral palsy sufferer. The experimental results for the cerebral palsy sufferer demonstrate a maximum average recognition rate of 91% for the four proposed neural networks, while the average recognition rate for the amputee, who used a prosthesis to carry out typing, is shown to be 97%. The average recognition rate for the novice operator is found to be slightly lower, i.e. 96%. However, these results all compare favorably with the recognition rate of 99% obtained for the skilled operator. In order to overcome the difficulties involved in recognizing a severely unstable Morse code transmission, the algorithms presented in this thesis focus upon the classification of long to short intervals (dash to dot) rather than upon the classification of the tone and silence ratios. In general, the proposed neural networks must undergo a learning process before they are capable of performing an accurate classification of the input Morse code. This necessarily involves a significant amount of computational effort. However, since a typical operator’s typing speed is far slower than the signal processing time required by the computer, the neural networks are still capable of processing the input Morse code on a virtually real-time basis.
1 INTRODUCTION………………………………………………………………1
1.1 Back Propagation Neural Network Recognition System………..…..….....…3
1.2 Modified Expert-Gating Neural Network Recognition System…..…….……6
1.3 SOM-LVQ and Modified Track Bayesian (MTB) Decision Boundary Neural Network Recognition System………………………………………………….9
2 METHOD…………………………………………………………….…………12
2.1 Back Propagation Neural Network Recognition Method…………….……12
2.1.1 BPN Learning Algorithm Steps………………………………………..14
2.1.2 BPN Recalling Algorithm Steps………………………………………..16
2.1.3 Linear BPN Recalling……………………………………..…….….…..16
2.2 Modified Expert-Gating Neural Network Recognition Method……...……17
2.2.1 Expert Algorithm……………………………………………..……….18
(a) Perceptron Learning Method…………………………………………..19
(b) Perceptron Predicted Recognition Method……………...…………….20
2.2.2 Gating Algorithm……………………………………………..………..21
2.2.3 Modified Expert-Gating Neural Network Supervised Learning Correction Rule …………………………………………………………………...22
2.2.4 Integration of the Expert Algorithm and Gating algorithm……………23
2.3 SOM-LVQ and MTB Recognition Method…………………………….…...25
2.3.1 Tone Classification System with the LVQ-SOM Neural Network……25
2.3.2 Silence Classification System with the MTB Neural Network…….….27
2.3.3 Integration of the LVQ-SOM Algorithm and MTB Algorithm………...28
2.4 Two-MTB Neural Network Recognition Method……………………..……29
3. EXPERIMENTAL RESULTS…………………………………………………..31
3.1 Back Propagation Experimental Results……………………………..……..31
(a) Non-linear BPN Recalling Experiment………………………………..36
(b) Linear BPN Recalling Experiment…………………………………….41
3.2 Modified Expert-Gating Experimental Results…………………….……42
3.3 Self-Organizing-Map and Modified Track Bayesian Decision Boundary Experimental Results……………………………..………………………50
3.4 Two-MTB Neural Network Experimental Results……………….……..54
3.5 Pattern Analysis and Comparison…………………………………….…56
4. DISCUSSION………………………..………….………..…………………62
4.1 BPN Discussion…………………………..….……….…………………62
4.2 Expert-Gating discussion………………………………...………………64
4.3 SOM-MTB and Two-MTB Discussion…………………………………..65
5. CONCLUSION……………………………………………...……………….69
References………………………………………………………...…………….74
Appendix A……………………………………………………...……………...79
[1] Arnott, J. L., and Javed, M.Y., “Probabilistic character disambiguation for reduced keyboards using small text samples,” AAC Augmentative and Alternative Communication, 8, pp.215-223, 1992.
[2] Higginbotham, D. J., “Evaluation of keystroke savings across five assistive communication technologies.” AAC Augmentative and Alternative Communication, vol. 8, pp.258-272, 1992.
[3] Hauck, L. T., “SAM: An improved input device.” Johns Hopkins APL Technical Digest, 13, pp.490-493, 1992.
[4] Korba, L. W., Nelson, P. J., and Park, G. C., “Morse code computer input using the MOD keyboard,” RESNA 8th annual conference, Memphis, Tennessee, pp. 58-60, 1985.
[5] Russel, M., and Rego, R., “A Morse code communication device for a deaf-blind individual.” ICAART 88, Montreal, pp.52-53, 1988.
[6] Levine, S. P., Gauger, J. R. D., Bwers, L. D., and Khan, K. J., “A comparison of mouth stick and Morse code text inputs,” AAC Augmentative and Alternative Communication, vol. 2, pp.51-55, 1986.
[7] Hsieh, M. C., and Luo, C. H., “Morse code typing training of an adolescent with cerebral palsy using micrcomputer technology: Case study,” AAC Augmentative and Alternative Communication, vol. 15, pp. 216-221, 1999.
[8] Luo, C. H., and Shih, C. H., “Adaptive Morse-coded single-switch communication system for the disabled.” International Journal of Bio-Medical Computing, 41, pp.99-106, 1996.
[9] Shih, C. H., and Luo, C. H., “A Morse-code recognition system with LMS and matching algorithms for persons with disabilities.” International Journal of Medical Informatics, 44, pp.193-202, 1997.
[10] Hsieh, M. C., Luo, C. H. and Mao, C. W., “Unstable Morse Code Recognition with Adaptive Variable Ratio Threshold Prediction for Physically Disabled Persons.” IEEE Trans. on Rehabilitation Engineering, vol. 8, pp.405-413, 2000.
[11] Rumelhart, D.E., Hinton, G.E. and Williams, R.J., “Learning internal representation by error propagation,” in Parallel Distribution Processing, vol. 1, Chapter 8, edited by D.E. Rumelhart and J.L. McClelland (Cambridge, MA: M.I.T. Press), pp. 318-362, 1986.
[12] Werbos, P. J., “Generalization of back propagation with application to a recurrent gas market model.” Neural Networks. vol. 1, pp. 339-356, 1988.
[13] Darken, C., and Moody, J., “Towards faster stochastic gradient search,” Advances in Neural Information Processing Systems, vol. 4, pp.1009-1016, 1992.
[14] Martin, G. L., and Pittman, J. A., “Recognizing Hand-Printed Letters and Digits Using Back propagation Learning,” Neural Computation, 3, 258-267, 1991.
[15] Tollenaeer, T., “SuperSAB: fast adaptive back propagation with good scaling properties,” Neural Networks. vol. 3, pp. 561-573, 1990.
[16] Ooyen, A. V., “Improving the convergence of the back propagation algorithm.” Neural Networks. vol. 5, pp. 465-471, 1992.
[17] Sperduti, A., and Starita, A., “Speed up learning and network optimization with extended back propagation,” Neural Networks. vol. 6, pp. 365-383, 1993.
[18] Fang, Y., “Faster learning for dynamic recurrent back propagation.” Neural Computation. vol. 2, pp. 270-273, 1990.
[19] Batruni, R., “A multiplayer neural network with piecewise linear structure and back propagation learning,” IEEE Transactions on neural network, vol.2, pp. 395-403, 1991.
[20] Denoeux, T., and Lengelle, R., “Initializing back propagation networks with prototypes,” Neural Networks. vol. 6, pp. 351-363, 1993.
[21] Kim, H., and Nam, K., “Object recognition of one-DOF tools by a back propagation neural net,” IEEE transactions on neural networks, vol. 6, pp. 484-487, 1995.
[22] Kim, S. K., “Implementation of the recognition system of the Korean stenographic characters by error back propagation algorithm.” IEEE international fuzzy systems conference proceedings, pp.II-1086-II1091, August 22-25, 1999, Seoul, Korea.
[23] Haykin, S., “Neural network, A comprehensive foundation.” (Engelwood Cliffs, NJ: Prentice Hall International, Inc.)., Prentice Hall International, Inc. pp. 156-184, 1999.
[24] Jacobs, R. A., and Jordan, M. I. “MI: Learning piecewise control strategies in a Expert-Gating neural network architecture.” IEEE Transactions on Systems, Man, and Cybernetics, vol.23, pp.337-345, 1993.
[25] Jordan, M. I., and Jacobs, R. A. “Hierarchical mixtures of experts and EM algorithm.” Neural Computation, vol. 6, pp.181-214, 1994.
[26] Chen, K., Xie, D., and Chi, H. “A Modified HME Architecture for Text-Dependent Speaker Identification.” IEEE Transactions on neural networks, vol. 7, pp.1309-1313, 1996.
[27] Mitra, S., and Pal, S. K., “Fuzzy Multi-Layer Perceptron, Inferencing and Rule Generation.” IEEE Transactions on neural networks, vol. 6, pp.51-63, 1995.
[28] Souheil, B. Y., Yousri, A., and Eddy, M., “Fusion of Face and Speech Data for Person Identity Verification.” IEEE Transactions on neural networks, vol. 10, pp.1065-1074, 1999.
[29] Gutta, S., Huang, R. J., Jonathon, P., and Wechsler, H., “Mixture of Experts for Classification of Gender, Ethnic Origin, and Pose of Human Faces.” IEEE Transactions on neural networks, vol.11, pp.948-960, 2000.
[30] Rahman, AFR., Howells, WGJ., and Fairhurst, M. C., “A Multiexpert Framework for Character Recognition: A Novel Application of Clifford Networks.” IEEE Transactions on neural networks, vol. 12, pp.101-112, 2001.
[31] Murphy, O. J., “Nearest neighbor pattern classification perceptrons,” Proceeding of the IEEE, vol. 78, pp. 1595-1598, 1990.
[32] Atlas, L., Cole, R., Muthusamy, Y., Lippman, A., Connor, J., Park, D., Mohamed, E. S., and Mark, R. J., “A performance comparison of trained multiplayer perceptrons and trained classification trees,” Proceeding of the IEEE, vol. 78, pp. 1614-1619, 1990.
[33] Gallant, S. I., “Perceptron-Based Learning Algorithms.” IEEE Transactions on neural networks, vol. 1, pp.179-191, 1990.
[34] Geva, A. B., “ScaleNet Multiscale Neural Network Architecture for Time Series Prediction” IEEE Transactions on neural networks, vol. 9, pp.1471-1482, 1998.
[35] Pal, S. K., and Mitra, S., “Multiplayer perceptron, fuzzy sets, and classification.” IEEE Transactions on neural networks, vol. 3, pp.683-697, 1992.
[36] Barnard, E., and Casasent, D., “A comparison between criterion functions for linear classifiers, with an application to neural nets,” IEEE Transactions on Systems, Man, and Cybernetics., vol. 19, pp. 1030-1041, 1989.
[37] Kohonen, T., “The Self-Organizing-Map,” Proceeding of The IEEE, vol. 78, pp. 1464-1480, 1990.
[38] Kanaya, F., and Miyake, S., “Bayes statistical behavior and valid generalization of pattern classifying neural network,” IEEE Transactions on neural networks, vol. 2, pp. 171-175, 1991.
[39] Shinoda, K., and Lee, C. H., “A structural Bayes approach to speaker adaptation,” IEEE Trans. Speech Audio Processing., vol. 9, pp. 276-287, 2001.
[40] Vesanto, J., and Alhoniemi, E., “Clustering of the Self-Organizing-Map,” IEEE Transactions on neural networks., vol. 11, pp. 586-600, 2000.
[41] Liou, C. Y., and Shiah, C. Y., “Perception of speech signals using self-organization on linear neuron array,” Proceedings of international joint conference on neural networks, pp. 251-254, 1993.
[42] Kohonen, T., “Generalization of the Self-Organizing-Map,” Proceeding of international joint conference on neural networks, pp. 457-462, 1993.
[43] Kohonen, T., Oja, E., Simula, O., Visa, A., and Kangas, J., “Engineering applications of the self-organizing map.” Proceedings of the IEEE, vol. 84, pp. 1358-1383, 1996.
[44] Haykin, S., “Neural network, A comprehensive foundation.” (Engelwood Cliffs, NJ: Prentice Hall International, Inc.)., Prentice Hall International, Inc. pp. 443-454, 1999.
[45] Wright, W. A., “Bayesian approach to neural-network modeling with input uncertainty,” IEEE transactions on neural networks, vol. 10, pp. 1261-1270, 1999.
連結至畢業學校之論文網頁點我開啟連結
註: 此連結為研究生畢業學校所提供,不一定有電子全文可供下載,若連結有誤,請點選上方之〝勘誤回報〞功能,我們會盡快修正,謝謝!
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