臺灣博碩士論文加值系統

在本篇論文中，我們提出一個使用最近的m個群中心的一般化模糊
k均值分群法來將一組資料分成k個群。在傳統的模糊k均值分群法中，一個資料點i對於群中心j的membership 的範圍是從0到1之間。提出的方法中，如果Cj 是Xi最近的M個群中心之一，那麼 的範圍是從0到1之間；否則 的值為0。 M的值為群中心的數量，其範圍在1跟k之間；Cj為第j群的群中心；Xi為第i個資料點。當M的值等於k時，提出的方法跟模糊k均值分群法是一樣的。從實驗結果來看，我們可以發現與模糊k均值分群法相比，我們得到了更好的分群品質及較少的計算時間。實驗結果顯示提出的方法可以大量減少模糊k均值分群法的計算時間。使用資料”Yeast Data”時，提出的方法跟模糊k均值分群法相比，減少 Xie-Beni參數VXB 的值為41.5%。較低的VXB值代表較好的分群結果。

摘要…………………………………………………………………………i
Abstract……………………………………………………………………..ii
致謝……………………………………………………………………….iii
目錄………………………………………………………………………..iv
Chapter 1 Introduction……………………………………………………….1
1.1 Background…………………………………………………………...1
1.2 Motivatoin……………………………………………………………1
1.3 Organization………………………………………………………….2
Chapter 2 Fuzzy k-mean Clustering…………………………………………...3
2.2 Introduction to the Fuzzy k-mean Clustering ……………………………..3
2.2 Algorithm of the Fuzzy k-mean Clustering……………………………….4
Chapter 3 Proposed Method…………………………………………………..6
3.1 Introduction to the General Fuzzy k-meanClustering ……………………...6
3.2 Algorithm of the General Fuzzy k-mean Clustering..………………………9
Chapter 4 Experimental Results……………………………………………..10
4.1 Cluster Validity Criterion……………………………………………..10
4.2 Data set obtained from images:”Lena,” “Baboon,” and “Peppers………….12
4.3 The Statlog (Landsat Satellite) data set……………………………….. 13
4.4 The “Image Segmentation” data set…………………………………...15
4.5 The “Yeast” data set…………………………………………………16
Chapter 5 Conclusions……………………………………………………...18
References…………………………………………………………………18

[1] A. Gersho and R. M. Gray, Vector Quantization and Signal Compression. Kluwer Academic Publishers, Boston MA., 1991.
[2] Y. C. Liaw, J. Z. C. Lai, and Winston Lo, “Image restoration of compressed image using classified vector quantization,” Pattern Recognition, vol. 35, no. 2, pp. 181-192, February 2002.
[3] J. Foster, R. M. Gray, and M. O. Dunham, “Finite state vector quantization for waveform coding,” IEEE Trans. on Information Theory, vol. 31, no. 3, pp. 348-359, May 1985.
[4] J. Z. C. Lai, Y. C. Liaw, and Winston Lo, “Artifact reduction of JPEG coded images using mean-removed classified vector quantization,” Signal Processing, vol. 82, no. 10, pp. 1375-1388, October 2002.
[5] S. Theodoridis and K. Koutroumbas, Pattern Recognition. Academic Press, 2nd edition, New York, 2003.
[6] U. M. Fayyad, G. Piatetsky-Shapiro, P. Smyth, and R. Uthurusamy, Advances in Knowledge Discovery and Data Mining. MIT Press, Boston MA., 1996,
[7] D. Liu, and F. Kubala, “Online speaker clustering,” Proc. IEEE Conf. on Acoustic, Speech, and Signal Processing, vol. 1, pp. 333-336. 2004.
[8] P. Hojen-Sorensen, N. de Freitas, and T. Fog, “On-line probabilistic classification with particle filters,” Proc. IEEE Signal Processing Society Workshop, vol. 1, pp. 386-395, 2000.
[9] M. Eirinaki and M. Vazirgiannis, “Web mining for web personalization,” ACM Trans. on Internet Technology, vol. 3, no. 1, pp. 1-27, February 2003.
[10] I. Berget, B. H. Mevik, and T. Naæs, “New modifications and applications of fuzzy c-means methodology,” Computational Statistics &; Data Analysis, vol. 52, no. 5, pp. 2403-2418, 2008.
[11] J. Z. C. Lai and T. J. Huang, “Fast global k-means clustering using cluster membership and inequality,” Pattern Recognition. Vol. 43, no. 5, pp. 1954-1963, May 2010.
[12] X. L. Xie, and G. A. Beni, “Validity measure for fuzzy clustering,” IEEE Trans. on PAMI, vol. 13, no. 4, April 1991, pp. 841-847.
[13] http://archive.ics.uci.edu/ml].
[14] D.L. Davies and D.W. Bouldin, “A cluster separation measure,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 13, no. 8, 1979, pp. 224-227.
[15] J. Bezdek, Pattern Recognition wit Fuzzy Objective Algorithms, New York: Plenum Press, 1981.