臺灣博碩士論文加值系統

基因規劃法(Genetic Programming)在分類與預測上都有許多文獻的研究，而且都有相當的成果，在某些應用方面更可以與類神經網路或其他演化式計算相提並論，然而基因規劃法在基因運算的樹狀結構的表示方法複雜，在計算適應值時，重組此樹狀所表示的結構解時會變的相當繁複。
因此本研究參考積木型基因規劃法(Block Type Genetic Programming)中結合基因演算法的操作易懂與基因規劃法以變數與運算子當基因的特性，在學習的過程中可減少處理的步驟，並且以MATLAB設計，利用能找出複雜非線性關係分類的能力，將鳥類聲音的樣本以積木型基因規劃法取得分類函數來達到鳥類聲音辨識的目的，能夠有78.4%的辨識率。

Genetic Programming is widely used in field of classification and prediction. In order to find the best solution, Genetic Programming uses complex tree structure to help calculate value of adaptation. It has already proved to be one of the effective ways to solve complicate relations by many research and documentations.
In this research, we use BGP to identify bird by birdsong. Our BGP uses variable and operator as gene to reduce the complexly of learning process. By working under MATLAB environment, and using ability of GP to identify non-linear relations by connecting with bird/birdsong database, the research has successfully achieved purpose of identification. The literacy rate occupies 78.4% in the research.

摘要................................................................i
Abstract ...........................................................ii
致謝..............................................................iii
目錄...............................................................iv
表目錄.............................................................vi
圖目錄............................................................vii
第一章 緒論.........................................................1
第一節 目的...................................................1
第二節 動機...................................................1
第三節 研究限制...............................................2
第四節 論文架構...............................................2
第二章 文獻探討.....................................................4
第一節 鳥聲辨識...............................................4
第二節 基因規劃法.............................................6
第三章 聲音特徵參數擷取............................................13
第一節 鳥類聲音辨識流程......................................13
第二節 前置處理..............................................14
第三節 特徵值取得............................................23
第四章 積木型基因規劃法............................................26
第一節 原理介紹..............................................26
第二節 分類法則..............................................33
第五章 研究方法....................................................35
第一節 建立鳥類聲音樣本資料庫................................35
第二節 實驗介紹..............................................37
第三節 實驗一................................................40
第四節 實驗二................................................48
第五節 實驗三................................................52
第六節 實驗四................................................59
第七節 實驗五................................................65
第六章 實驗結果與未來研究方向......................................78
參考文獻...........................................................80
附錄一.............................................................86

[1] 楊鎮光，“Visual Basic 與語音辨識” ，松崗出版社，2002。

[2] 王小川，“語音訊號處理” ，全華科技，2004。

[3] 許聰海，“積木型遺傳規劃法於最佳化組合之應用” ，國立臺
北科技大學電機工程系，碩士論文，2004。

[4] 黃祥恩，“結合隱藏式馬可夫模型的模糊聚類做特徵萃取之研
究應用於鳥音辨識系統” ，國立東華大學電機工程學系，碩士論文，2004。

[5] 張勇富，“以語料分析為主的鳥音辨識系統研究” ，國立東華
大學電機工程學系，碩士論文，2002。

[6] 楊青于，“鳥聲辨識之初步研究與分析” ，國立清華大學資訊
工程學系，碩士論文，2005。

[7] 臺北縣政府農業局，2007臺北縣賞鳥季活動開鑼了！，來源：
http://www.agriculture.tpc.gov.tw/web/News?command=showDetail&postId=1588 ，2007。

[8] 陳松琳，“以類神經網路為架構之語音辨識系統”，碩士論文，國立中山大學電機工程學系研究所，2001。

[9] 蕭宜昌，“結合決策樹與基因規劃法於資料分類研究”，屏東
科技大學資訊管理所，碩士論文，2007。

[10]倪慧雯，“以HMM建立音節類型模型的鳥種辨識系統” ，中華
大學資訊工程學系，碩士論文，2005。

[11]劉邦信，“以決策類神經網路為基礎的鳥聲辨識系統” ，中華
大學資訊工程學系，碩士論文，2005。

[12]郭桂廷，“基於基因遺傳演算法最佳時序濾波器之應用強健型
語音辨識”，暨南國際大學電機工程學系，碩士論文，2006。

[13]王宗梅，“語音辨識專利地圖專題研究” ，工業技術研究院電腦與通訊工業研究所，1996。

[14] J.R. Koza,“Genetic Programming On the Programming of
Computers by means of Natural Selection”,MIT press,
1992 .

[15]Sven E. Anderson,Amish S.Dave,and Daniel Margoliash,
“Template-base automatic recognition of birdsong syllables from continuousrecordings”,Acoustic Society America 1996.
[16]Seppo Fagerlund,“Automatic Recognition of bird
species by Their Sounds”.

[17]Whigham, P.A.,Crapper, P.F.“Modeling Rainfall-Runoff
using Genetic Programming”,Mathematical and Computer Modeling 33,pp. 707-721,2001

[18]J.H. Holland, Outline for a Logical Theory of Adaptive
Systems, Journal of ACM, 3, 297-314,1962.

[19]Demura Tetesuya ,“The face image recognition system
based on the Genetic Programming technique” ，Papers
of Technical Meeting on Information System , IEE Japan
VOL.ls-04,NO.9-19,page 7-12 , 2004

[20] S. Katagiri and C. H. Lee, “A New Hybird Algorithm for Speech Recognition Based on HMM Segmentation and Learning Vector Quantization,” IEEE Trans. on Speech and Audio Processing, Vol. 1, No. 4, pp. 421-430, October 1993.

[21]J.A. Kogan and D. Margoliash, "Automated Recognition of Bird Song Elements from Continuous Recordings Using Dynamic Time Warping and Hidden Markov Models: A comparative Study," Journal of the Acoustical Society of America, vol. 103, No. 4, pp. 2185-2195, April 1998.

[22]Alex L. Mcllraith and Card C. Howard, “Birdsong Recognition with DSP and Neural Networks,” IEEE WESCANEX 95. Communications, Power, and Computing. Conference Proceedings, Vol. 2, pp. 409-414, May 1995.

[23]Alex L. Mcllraith and Card C. Howard, “Birdsong identification using artificial neural network and statistical analysis,”IEEE Electrical and Computer Engineering Conference Proceeding, Vol. 1, pp. 63-66, May 1997

[24]A. L. McIlraith and H. C Card, “A comparison of backpropagation and statistical classifiers for bird identification,” Prof. Of IEEE Int. Conf. Neural Networks, vol. 1 pp. 100-104, 1997.

[25]Dimopoulos, C. and Zalzala, A. M. S., “Investigating the Use of Genetic Programming for A Classic One-Machine Scheduling Problem,” Advances in Engineering Software, Vol. 32, pp. 489-498, 2001.

[26]A. L. McIlraith; H. C. Card, “Birdsong recognition using backpropagation and multivariate statistics,” IEEE Trans. Signal Processing, vol. 45, pp. 2740-2748, 1997.

[27]P. Somervuo; A. Harma, ”Bird song recognition based on syllable pair histograms,”IEEE CNF, Acoustics, Speech and Signal Processing, vol. 5, pp. 825-828, 2004.

[28]A. Harma, “Automatic Identification of Bird Species Based on Sinusoidal Modeling of Syllables,” in Proceedings of International Conference Acoustics, Speech, and Signal Processing, Vol. 5, pp. 545-548, 2003.

[29]D.P. Muni, N. R. Pal and J. Das, “Genetic programming for simultaneous feature selection and classifier design,” IEEE Transactions on Systems, Man and Cybernetics, Part B, Vol. 36, No. 1, pp. 106-117, Feb 2006.

[30]K. Sasaki and M. Yamazaki, “Vector compression of bird songs spectra in water sites by using the linear prediction method and its application to an automated Bayesian species classification”, SICE Annual, 38th Annual Conference Proceedings, PP. 1083 —1088, Aug. 1999.

[31]C. Rogers, “High resolution analysis of bird sounds”, Acoustics, Speech, and Signal Processing International Conference, Vol. 5, PP. 3011-3014, May 1995.

[32]C. Kwan; G. Mei; X. Zhao; Z. Ren; R. Xu; V. Stanford; C. Rochet; J. Aube; K.C. Ho, “Bird classification algorithms: theory and experimental results,” IEEE CNF, Acoustics, Speech and Signal Processing, vol. 5, pp. 289-292, 2004.

[33]A. Harma; P. Somervuo, ”Classification of the harmonic structure in bird vocalization ” IEEE CNF, Acoustics, Speech and Signal Processing, vol. 5, pp. 701-704, 2004.

[34]R.J. Dooling, M.R. Leek, O. Gleich, and M.L. Dent, "Auditory temporal resolution in birds: Discrimination of harmonic complexes " Journal of the Acoustical Society of America, vol. 112, pp. 748-759, August 2002.

[35]B. W. Zhang, “The Study on Corpus-Based Analysis for Bird Sound Recognition System ” Master Thesis, National Dong Hwa University, July 2003.

[36]G.B. Mindlin, T.J. Gardner, F. Goller, and R. Suthers, "Experimental support for a model of birdsong production " Physical Review E 68, 041908 October 2003.

[37]Nikolaev, N. and Iba, H. “Genetic Programming of Polynomial Models for Financial Forecasting. ”, Kluwer Academic Publishers, pp. 103-123,2002.

[38]Chen S. H., C.H. Yeh and W. C. Lee, “Option Pricing with Genetic Programming”, Third Annual International Genetic Programming Conference, pp.22-25. , July 1998.

[39]Bojarczuk C. C., Lopes, H. S., Freitas, A. A., and Michalkiewicz, “A constrained-syntax genetic programming system for discovering classification rules: application to medical data sets”,Artificial Intelligence in Medicine.

[40]Bojarczuk C. C., Lopes, H. S., & Freitas, Alex A., Genetic Programming for Knowledge Discovery in Chest Pain Diagnosis, Engineering in Medicine and Biology Magazine, IEEE, Vol.19, Issue.4, pp.38-44, 2000.

[41]A. Song, V. Ciesielski, H. E. Williams, “Texture classifiers generated by genetic programming ” in Proc. IEEE Int. Conf. Evolutionary Computation, vol. 1, pp. 243-248, May. 2002.

[42]T. Loveard and V. Ciesielski, “Representing classification problems in genetic programming ” in Proc. IEEE Int. Conf. Evolutionary Computation, vol. 2, pp. 1070-1077, May 27-30 2001.

[43]J. K. Kishore, L. M. Patnaik, V. Mani, and V. K. Agrawal, “Application of genetic programming for multicategory pattern classification ” IEEE Trans. on Evolutionary Computation vol. 4, no. 3, pp. 242-258, Sep. 2000.

[44]A. Bastian, “Identifying fuzzy models utilizing genetic programming,” Fuzzy Sets Systems, vol. 113, no. 3, pp. 333–350,

[45]Y. S. Yeun, W. S. Ruy, Y. S. Yang and N. J. Kim, “Implementing linear models in genetic programming,” IEEE Trans. on Evolutionary Computation, vol. 8, no. 6, pp. 542-566, Dec. 2004.