臺灣博碩士論文加值系統

目前有兩百種以上不同種類的癌症，每一種癌症的症狀和治療方法都不盡相同，即便是專業的醫護人員對於正確的分類癌症樣本都是有困難的。因此，我們利用特徵選取和整體學習分類法對癌症做樣本分類。
微陣列晶片在微小面積上種植高密度的生物探針，做為大量篩檢及平行分析上千個基因的工具。上千個基因對於癌症的樣本分類並不是都有幫助的，我們使用特徵選取中資訊獲利的方法來挑選對於癌症樣本分類有幫助的特徵值，我們再對做完特徵選取的癌症資料做樣本分類。
我們所使用的癌症資料有白血病以及乳癌。使用模糊類神經網路、K個最近鄰居、二次分類法、和它們個別的整體學習分類法，以及整合它們的整體學習分類法來對癌症做樣本分類。實驗的結果發現，整體學習分類法可以提升個別分類法的正確率。

There are over 200 various types of cancer, each of which has a unique set of clinical characteristics, and different chances of being cured. Unfortunately, it is sometimes difficult, for even the experienced specialists, to determine among particular cancers and their subtypes. Therefore we use the feature selection methods and machine learning classifiers for cancer classification.
DNA microarray technology can simultaneously monitor the expression of thousands of genes. It can offer the analyses of gene expression data to the physician for diagnose cancer or the research of classifying cancer. To accurately classify cancer we need to select the related genes because some extracted genes form microarray are useless for classify.
In this study we classify two kinds of cancers. One is Leukemia cancer gene expression data set. Another is breast cancer of medical diagnostic data set. In the research, information gain has been used for feature selections. Neural fuzzy (NF), k-nearest neighbor (KNN), quadratic classifier (QC), and their associated, ensemble models, and as well as these three combined model have been utilized for classification. Experimental results show the ensemble learning performs better then individual classifiers in classification.

摘要 i
Abstract ii
致謝 iii
Contents iv
List of Table v
List of Figure v
Chapter 1 Introduction 1
1.1 Research Motivations 2
1.2 Report Outline 3
Chapter 2 Backgrounds 4
2.1 Microarray Technology 4
2.2 Gene Selection 6
2.2.1 Information Gain 7
2.3 Classifiers 9
2.3.1 Neural Fuzzy System 9
2.3.2 K Nearest Neighbor 12
2.3.3 Quadratic classifier 14
Chapter 3 Methodology 17
3.1 Ensemble Machine Learning 17
3.2 Training and Testing Strategy 20
3.3 Neural Fuzzy Ensemble Model 22
3.4 K Nearest Neighbor Ensemble Model 24
3.5 Quadratic Classifier Ensemble Model 25
3.6 The Ensemble Model contains NF KNN QC classifiers 26
Chapter 4 Experimental Results 28
4.1 Cancer Data Sets 28
4.1.1 Leukemia Cancer Data Set 29
4.1.2 Breast Cancer Data set 29
4.2 Experiment Environment 30
4.3 Feature Selection Results 30
4.3.1 Leukemia Cancer Data Set 30
4.3.2 Breast Cancer Data Set 30
4.4 Results and Comparisons 31
4.4.1 Results of NF and NFE 32
4.4.2 Results of KNN and KNNE 35
4.4.3 Results of QC and QCE 37
4.4.4 The result of Ensemble Model contains NF KNN QC classifiers 39
4.4.5 The Comparison of 4 Ensemble Model 41
Chapter 5 48
5.1 Conclusions 48
5.2 Future Work 49
References 50
Appendix 52

[1] Christina A Harrington, et al., “Monitoring gene expression using DNA microarrays,” Science, Volume 3, Issue 3, Pages 285-291, June 2000
[2] Mitchell, T., “Machine learning,” McGraw-Hill, New York, 1997
[3] Baumgartner, R., Windischberger, C. & Moser, E., “Quantification in functional magnetic resonance imaging: fuzzy clustering vs. correlation analysis,” Magn Reson Imaging, 16, 115–25, 1998
[4] Brown, M.P.S., et al., “ Knowledge-based analysis of microarray gene expression data using support vector machines,” In Proceedings of National Academy of Science, 262–267, 2000
[5] Furey, T.S., et al., “Support vector machine classification and validation of cancer tissue samples using microarray expression data,” Bioinformatics, 16, 906–914, 2000
[6] Khan, J., Wei, et al., “Classification and diagnostic prediction of cancers using gene expression profiling and artificial neural networks,” Nature Medicine, 7, 673–679, 2001
[7] Li, L., Weinberg, et al., “Gene selection for sample classification based on gene expression data: study of sensitivity to choice of parameters of the ga/knn method,” Bioinformatics, 17, 1131–1142, 2001
[8] Ding, C.H.Q. & Peng, H., “Minimum redundancy feature selection from microarray gene expression data,” In CSB, 523–529, 2003
[9] Thomas, G.D., “Ensemble methods in machine learning,” In Proc. of the first International Workshop on Multiple Classifier System (MCS 2000), 1–15, 2000
[10] Wikipedia, DNA. http://en.wikipedia.org/wiki/DNA
[11] Lashkari DA, et al., “Yeast microarrays for genome wide parallel genetic and gene expression analysis,” Proc Natl Acad Sci USA 94: 13057–13062, 1997
[12] Xing, E.P., et al., “Feature selection for highdimensional genomic microarray data,” In ICML ’01: Proceedings of the Eighteenth International Conference on Machine Learning, 601–608, Morgan Kaufmann Publishers Inc., San Francisco, CA, USA, 2001
[13] Yao, X. & Liu, Y., “A new evolutionary system for evolving artificial neural networks,” IEEE Transactions on Neural Networks, 8, 694–713, 1997
[14] Jang, J.S.R. & Sun, C.T., “Neuro-fuzzy and soft computing: a computational approach to learning and machine intelligence,” Prentice-Hall, Inc.,Upper Saddle River, NJ, USA, 1997
[15] Jang, J.S.R., “Neuro-Fuzzy Modeling: Architectures, Analyses and Application,” Phd thesis, University of California Berkeley, 1992
[16] J. Wesley Hines, Matlab Supplement to Fuzzy and Neural Approaches in Engineering, Wiley, New York, 1997
[17] Bressan, M. & Vitri J., “Nonparametric discriminant analysis and nearest neighbor classification,” Pattern Recogn. Lett., 24, 2743–2749, 2003
[18] H. Brunzell & J. Eriksson, “Feature reduction for classification of multidimensional data,” Pattern Recognition 33 1741-1748, 2000
[19] Schaffer, C., “Selecting a classification method by cross-validation,” Machine learning, 13, 135–143, 1993
[20] Z. Wang, “Neuro-Fuzzy Ensemble Approach for Microarray Cancer Gene Expression Data Analysis,” 2006 International Symposium on Evolving Fuzzy Systems, September, 2006
[21] O. L. Mangasarian and W. H. Wolberg, “Cancer diagnosis via linear programming,” SIAM News, Volume 23, Number 5, September 1990, pp 1 & 18.
[22] Golub, T.R., et al., “Molecular classification of cancer: class discovery and class prediction by gene expression monitoring,” Science, 286, 531–537, 2002
[23] BROAD INSTITUTE http://www.broad.mit.edu/
[24] UC Irvine Machine Learning Repository http://archive.ics.uci.edu/ml/
[25] WEKA http://www.cs.waikato.ac.nz/ml/weka/
[26] The MathWorks Fuzzy Logic Toolbox http://www.mathworks.com/products/fuzzylogic/index.html
[27] DCPR (Data Clustering and Pattern Recognition) Toolbox http://neural.cs.nthu.edu.tw/jang/matlab/toolbox/dcpr/