臺灣博碩士論文加值系統

類別不平衡問題(Class Imbalance Problems)在機器學習領域已經十分受到重視。此問題主因在於訓練範例中，某一類別數量會遠大於另一類別。當從不平衡資料(Imbalanced Data)中進行資料探勘時，傳統機器學習方法，對於多數類範例將會產生比較高的準確率，而對於偵測少數類別有很高的錯誤率。為了解決此一問題，本研究提出了兩個新的方法，分別稱為「修改分群抽樣法」，「Modified cluster based sampling, MCBS」與「植基倒傳遞類神經網路之投票機制」，「BPN based voting scheme, BPS」方法。並利用七組類別不平衡資料與三個實際部落格語意分類案件，以四摺交叉驗證法(4-fold cross-validation)來驗證所提方法之有效性。MCBS法是要改善傳統分群抽樣法的缺點。而BPS法藉由BPN網路的訓練，以獲得各投票分類器的最佳權重，來強化傳統的投票分類機制。另外，將所提之方法，應用於文件資料分類上，主要是因為文件資料具有高維度和小樣本等問題。實驗結果顯示，相較於傳統處理不平衡資料的方法如隨機增加少數法、分群抽樣法、自組織映射網路權重法、兩階段學習法、單類別學習等。本研究所提方法不僅在偵測少數類別有較高的能力，同時在分類績效表現上也比較穩定。

Class imbalance problems have attracted much attention in the field of machine learning. This problem is mainly attributed to training examples, in which, the number of particular class examples will be much larger than the other classes. When learning from such imbalance data, traditional machine learning algorithm will have a relatively high accuracy over the majority examples, and lead to an unacceptable error rate for the minority class instances which are usually important. In order to solve this problem, this study attempts to propose two novel methods, called “Modified cluster based sampling, MCBS” and “BPN based voting scheme, BPS”. Seven data sets from UCI data bank and three real cases of bloggers’ sentiment classification have been provided to verify the effectiveness of the proposed methods. In addition, four fold cross validation experiments have been implemented for obtaining high quality solutions. MCBS is to improve the shortcomings of traditional clustering sampling method. The BPS method enhance traditional voting scheme by using BPN network to get the optimal vote weights. In addition, the proposed methodologies have been applied to classify textual sentiment data which usually has problems of high dimension and small sample size problems. Experimental results indicated that, compared with conventional treatment methods for imbalance data, such as under-sampling, cluster based sampling, self-organizing map network weights method, two stage learning strategy, and one class learning, the proposed methods can not only increase the ability of detecting minority examples, but also have stable classification performance.

目錄
摘要 I
Abstract II
誌謝 III
目錄 IV
表目錄 VII
圖目錄 XII
第一章 緒論 1
1.1 研究背景 1
1.2 研究動機 5
1.3 研究目的 7
1.4 研究架構 8
1.5 研究步驟 10
第二章 文獻探討 12
2.1 資料探勘 12
2.1.1決策樹 13
2.1.2倒傳遞類神經網路(Back-propagation Neural Network) 18
2.1.3單類別支撐向量機學習(One class SVM) 23
2.2 類別不平衡問題 28
2.2.1 增加少數法 32
2.2.2 減少多數法 32
2.2.3 分群抽樣法 33
2.2.4 調整錯誤分類成本法 35
2.2.5 調整決策臨界值 35
2.2.6自組織映射網路權重法(Self Organizing Map Weights) 36
2.2.7植基於馬氏距離兩階段學習法 40
2.3 多專家分類器 41
第三章 研究方法 43
3.1 MCBS方法與步驟 43
3.1.1 MCBS1方法與流程 45
3.1.2 MCBS2方法與流程 49
3.1.3 MCBS3方法與流程 52
3.1.4 MCBS4方法與流程 54
3.1.5 MCBS5方法與流程 56
3.1.6 MCBS6方法與流程 58
3.2 MCBS1~6方法之簡單說明例 60
3.3 植基於類神經網路之投票機制方法(BPS) 66
3.4 BPS方法之簡單說明例 69
第四章 實驗與分析 73
4.1 資料前處理 73
4.2 評估指標 75
4.3 實驗結果 77
4.4 MCBS法小結 93
4.5 BPS法小結 109
第五章 個案分析 120
5.1 文件語意分類 120
5.2 實驗步驟 123
5.3 實驗結果 124
5.4 目前處理類別不平衡與所提BPS方法的參數設定 169
5.4.1馬氏距離參數設定 169
5.4.2 SWAI2群數、學習速率與鄰近半徑參數 171
5.4.3 BPN based voting scheme訓練次數與學習速率參數 173
第六章 結論與建議 175
6.1 討論 175
6.2 結論 176
6.3 未來研究方向 177
參考文獻 179



表目錄
表2-1 機器學習各種方法比較表 12
表2-2 各種決策樹演算法比較表 16
表2-3 回饋式與前饋式的不同比較表 19
表2-4 類神經網路優缺點 19
表2-5 One class SVM訓練中調整V值所得分類結果 27
表2-6 國外處理不平衡資料方法 28
表2-7 國內處理不平衡資料方法 30
表3-1 Haberman data範例 60
表3-2 MCBS分類結果與實際類別結果的比較 65
表3-3 Haberman data範例 69
表3-4 各分類器訓練組分類結果 70
表3-5 各分類器測試組分類結果 71
表3-6 BPS方法的訓練結果 71
表3-7 BPS方法分類結果與實際類別比較表 72
表4-1 為本研究所使用之資料集 74
表4-2 Confusion matrix 75
表4-3 Habermab data六種分群抽樣法分類結果 79
表4-4 Ionosphere data六種分群抽樣法分類結果 80
表4-5 TAE data六種分群抽樣法分類結果 81
表4-6 Diabetes data五種分群抽樣法分類結果 82
表4-7 CMC data五種分群抽樣法分類結果 83
表4-8 醫學資料(輕重傷害) 五種分群抽樣法分類結果 84
表4-9 醫學資料(有無傷害) 五種分群抽樣法分類結果 85
表4-10 分群抽樣法七組資料總結 86
表4-11 分群抽樣法七組資料總結 87
表4-12 分群抽樣法低度不平衡資料總結 88
表4-13 分群抽樣法高度不平衡資料總結 89
表4-14 不平衡資料比較表 93
表4-15 最好分群抽樣法與傳統方法比較 94
表4-16 最好分群抽樣法與傳統方法比較 95
表4-17 Haberman data BPS法分類結果 96
表4-18 Ionosphere data BPS法分類結果 97
表4-19 TAE data BPS法分類結果 98
表4-20 Diabetes data BPS法分類結果 99
表4-21 CMC data BPS法分類結果 100
表4-22 醫學資料(輕重傷害) BPS法分類結果 101
表4-23 醫學資料(有無傷害) BPS法分類結果 102
表4-24 BPS法所有資料總結 103
表4-25 BPS法所有資料總結 104
表4-26 BPS法低度不平衡資料總結 105
表4-27 BPS法高度不平衡資料總結 106
表4-28 不平衡資料比較表 110
表4-29 Haberman (one class與MCBS、BPS)分類比較表 111
表4-30 Ionosphere (one class與MCBS、BPS)分類比較表 112
表4-31 TAE (one class與MCBS、BPS)分類比較表 113
表4-32 Diabetes (one class與MCBS、BPS)分類比較表 114
表4-33 CMC (one class與MCBS、BPS)分類比較表 115
表4-34 輕重傷害 (one class與MCBS、BPS)分類比較表 116
表4-35 有無傷害 (one class與MCBS、BPS)分類比較表 117
表4-36 低度不平衡資料(one class與MCBS、BPS)分類結果比較 118
表4-37 高度不平衡資料(one class與MCBS、BPS)分類結果比較 118
表5-1 實驗文集與資料量 122
表5-2為設置小樣本的情況 122
表5-3 詞彙-文件矩陣 123
表5-4 分群抽樣法MP3(原始資料)小樣本實驗結果 125
表5-5 分群抽樣法MP3(2:1)小樣本實驗結果 126
表5-6 分群抽樣法MP3(4:1)小樣本實驗結果 127
表5-7 分群抽樣法EC(原始資料)小樣本實驗結果 128
表5-8 分群抽樣法EC(2:1)小樣本實驗結果 129
表5-9 分群抽樣法EC(4:1)小樣本實驗結果 130
表5-10 分群抽樣法Movie(原始資料)小樣本實驗結果 131
表5-11 分群抽樣法Movie(2:1)小樣本實驗結果 132
表5-12 分群抽樣法Movie(4:1)小樣本實驗結果 133
表5-13 MP3分群抽樣法小樣本實驗結果總表 134
表5-14 EC分群抽樣法小樣本實驗結果總表 135
表5-15 Movie分群抽樣法小樣本實驗結果總表 136
表5-16 BPS法MP3(原始資料)小樣本實驗結果 141
表5-17 BPS法MP3(2:1)小樣本實驗結果 142
表5-18 BPS法MP3(4:1)小樣本實驗結果 143
表5-19 BPS法EC(原始資料)小樣本實驗結果 144
表5-20 BPS法EC(2:1)小樣本實驗結果 145
表5-21 BPS法EC(4:1)小樣本實驗結果 146
表5-22 BPS法Movie(原始資料)小樣本實驗結果 147
表5-23 BPS法Movie(2:1)小樣本實驗結果 148
表5-24 BPS法Movie(4:1)小樣本實驗結果 149
表5-25 BPS法MP3小樣本實驗結果總表 150
表5-26 BPS法EC小樣本實驗結果總表 151
表5-27 BPS法Movie小樣本實驗結果總表 152
表5-28 七種方法對於高維度、不平衡、小樣本資料的適配度 156
表5-29 MP3(原始資料) (one class與MCBS、BPS)分類結果比較 157
表5-30 MP3(2:1) (one class與MCBS、BPS)分類結果比較表 158
表5-31 MP3(4:1) (one class與MCBS、BPS)分類結果比較表 159
表5-32 EC(原始資料) (one class與MCBS、BPS)分類結果比較表160
表5-33 EC(2:1) (one class與MCBS、BPS)分類結果比較表 161
表5-34 EC(4:1) (one class與MCBS、BPS)分類結果比較表 162
表5-35 Movie(原始資料)(one class與MCBS、BPS)分類結果比較表 163
表5-36 Movie(2:1) (one class與MCBS、BPS)分類結果比較表 164
表5-37 Movie(4:1) (one class與MCBS、BPS)分類結果比較表 165
表5-38 MP3小樣本 (one class與MCBS、BPS)分類結果總表 166
表5-39 EC小樣本 (one class與MCBS、BPS)分類結果總表 166
表5-40 Movie小樣本 (one class與MCBS、BPS)分類結果總表 166
表5-41 Haberman data臨界值參數 169
表5-42 TAE data臨界值參數 169
表5-43 Ionosphere data臨界值參數 169
表5-44 Diabetes data臨界值參數 170
表5-45 CMC data臨界值參數 170
表5-46 語意分類(MP3)臨界值參數 170
表5-47 Haberman data Dimension map、學習速率、鄰近半徑 171
表5-48 TAE data Dimension map、學習速率、鄰近半徑 171
表5-49 Ionosphere data Dimension map、學習速率、鄰近半徑171
表5-50 Diabetes data Dimension map、學習速率、鄰近半徑 172
表5-51 CMC data Dimension map、學習速率、鄰近半徑 172
表5-52 語意分類(MP3) Dimension map、學習速率、鄰近半徑 172
表5-53 Haberman data BPN訓練次數與學習速率 173
表5-54 TAE data BPN訓練次數與學習速率 173
表5-55 Ionosphere data BPN訓練次數與學習速率 173
表5-56 Diabetes data BPN訓練次數與學習速率 174
表5-57 CMC data BPN訓練次數與學習速率 174
表5-58 語意分類(MP3) BPN訓練次數與學習速率 174



圖目錄
圖1-1 資料不平衡問題 3
圖1-2 不平衡問題論文的發表數量 3
圖1-3 導致不平衡資料分類效能降低因素 4
圖1-4 導致不平衡資料分類效能降低因素 4
圖1-5 研究架構圖 9
圖1-6 本研究之研究步驟 11
圖2-1 決策樹架構圖 17
圖2-2 決策樹流程圖 17
圖2-3 BPN架構圖 20
圖2-4支撐向量機示意圖 24
圖2-5支撐向量機(非線性分類)示意圖 25
圖2-6 二維矩陣的SOM架構圖 37
圖2-7 SOM流程圖 39
圖2-8馬氏距離示意圖 40
圖3-1 MCBS研究流程 44
圖3-2 MCBS1方法與流程 45
圖3-3 MCBS2方法與流程 49
圖3-4 MCBS3方法與流程 52
圖3-5 MCBS4方法與流程 54
圖3-6 MCBS5方法與流程 56
圖3-7 MCBS6方法與流程 58
圖3-8 BPN based voting scheme流程圖 66
圖3-9 BPN based voting scheme架構圖 68
圖4-1 低度不平衡資料MCBS1~MCBS6分類結果比較 90
圖4-2 高度不平衡資料MCBS1~MCBS6分類結果比較 90
圖4-3 低度不平衡資料七種方法分類結果 107
圖4-4 高度不平衡資料七種方法分類結果 107
圖5-1 MP3小樣本MCBS1~MCBS6分類結果 137
圖5-2 EC小樣本MCBS1~MCBS6分類結果 137
圖5-3 Movie小樣本MCBS1~MCBS6分類結果 137
圖5-4 MP3小樣本七種方法分類結果 153
圖5-5 EC小樣本七種方法分類結果 153
圖5-6 Movie小樣本七種方法分類結果 153

參考文獻
中文文獻
[1]吳柏宏 (2008)，自組織映射圖應用於聽覺場景式語音分離，碩士論文，國立交通大學，電信工程學系，新竹。
[2]杜逸普 (2008)，部落格探勘—以網路電話產品為例，碩士論文，朝陽科技大學，資訊管理系，台中。
[3]周欣怡 (2008)，「房屋貸款違約預測-存活分析模型之應用」，碩士論文，真理大學，財經研究所，台北。
[4]林瑞山 (2004)，「類神經網路於預測晶圓測試良率之應用」，碩士論文，國立成功大學，工學院工程管理系，台南。
[5]邱慧如 (2009)，發展新語意導向指標以分類部落客之語意，碩士論文，朝陽科大資管系，台中。
[6]姚志成 (2005)，運用資料探勘技術建構脂肪肝預測模式，碩士論文，中原大學，資訊管理學系，中壢。
[7]凌士雄 (2004)，「非對稱性分類分析解決策略之效能比較」，碩士論文，中山大學，資訊管理學系，高雄。
[8]張保中 (2008)，C-Kano Model之發展以探索魅力品質要素，碩士論文，朝陽科技大學，資訊管理系，台中。
[9]張琦、吳斌、王柏 (2005)，「非平衡數據訓練方法概述」，計算機科學，第三二卷，第十期，第181-186頁。
[10]張毓珊 (2009)，發展處理類別不平衡問題之資料探勘模式，碩士論文，朝陽科技大學，資訊管理系，台中。
[11]陳世彥 (2008)，植基於規則推導的電腦輔助醫療診斷，碩士論文，東海大學，資訊工程與科學研究所，台中。
[12]陳秋婷 (2002)，一個適用於不平衡訓練資料集的多變量決策樹之研究，碩士論文，國立臺南大學，資訊教育研究所，台南。
[13]曾憲雄、蔡秀滿、蘇東興、曾秋蓉、王慶堯(2007)，資料探勘，旗標出版股份有限公司，5-10頁-5-19頁。
[14]葉怡成 (1993)二版，類神經網路模式應用與實作，儒林圖書有限公司，第70-77頁，第173-178頁。
[15]葉怡成 (1997)初版，應用類神經網路，儒林圖書有限公司，第1-28頁。
[16]塗宜昆，2003，以單類支持向量機為基礎之階層式文件分類，碩士論文，國立成功大學資訊工程學系，台南。
[17]潘致誠 (2008)，強健式網路入侵偵測演算法則之研究，碩士論文，國防大學理工學院，資訊科學系，桃園。
[18]蕭宇翔 (2005)，應用MTS 於非平衡資料分析之穩健性研究—以行動電話檢測流程為例，碩士論文，國立交通大學，工業工程與管理學系，新竹。
[19]鍾依芸 (2003)，行動電話系統業服務品質滿意度之研究─應用統計分析與決策樹法，碩士論文 元智工業工程與管理，中壢。
英文文獻
[1]A. Fernandez, M. J. del Jesus, and F. Herrera, (2009), “On the Influence of an Adaptive Inference System in Fuzzy Rule based Classification Systems for Imbalanced Data Sets,” Expert Systems with Application, vol. 36, pp. 9805-9812.
[2]A. Estabrooks, T. Jo, and N. Japkowicz, (2004), “A Multiple Resampling Method for Learning from Imbalanced Data Sets,” Computational Intelligence, vol. 20, no. 1, pp.18-36.
[3]A. C. Konig, and E. Brill, (2006), “Reducing the Human Overhead in Text Categorization,” In Proceedings of the 12th ACM SIGKDD Conference on Knowledge Discovery and Data Mining Philadelphia, Pennsylvania, USA, pp. 598-603.
[4]A. Folleco, T. M. Khoshgoftaar, A. Napolitano, (2008), “Comparison of Four Performance Metrics for Evaluating Sampling Techniques for Low Quality Class-Imbalanced Data,” Proceeding of International Conference on Machine Learning and Applications, pp. 153-158.
[5]B. Zadrozny and C. Elkan, (2001), “Learning and Making Decisions when Costs and Probabilities are Both Unknown”, Proceedings of the 7th International Conference on Knowledge Discovery and Data Mining, pp. 204-213.
[6]B. Kessler, G. Nunberg, and H. SchAutze, (1997), “Automatic Detection of Text Genre,” Proceedings of the 35th ACL/8th EACL, pp. 32-38.
[7]B. Pang, L. Lee, and S. Vaithyanathan, (2002), “Thumbs up? Sentiment Classification Using Machine Learning Techniques,” In P. Isabelle (Ed.), Proceeding of 2002 Conference on Empirical Methods in Natural Language, Philadelphia, US, pp. 79-86.
[8]B. Li, S. Xu, J. Zhang, (2007), “Enhancing Clustering Blog Documents by Utilizing Author/Reader Comments,” Proceedings of the 45th Annual Southeast Regional Conference, pp. 94-99.
[9]B. Scholkopf, J.C. Platt, J.Shawe-Taylor, A.J. Smola, and R.C. Williamson, (1999), “Estimating the Support of a High-Dimensional Distribution,” Technical Report, Microsoft Research, MSR-TR- 99-87.
[10]C. Seiffert; T. M. Khoshgoftaar; J. Van Hulse, A. Napolitano, (2008), “RUSBoost: Improving Classification Performance when Training Data is Skewed,” IEEE Pattern Recoqnition, pp.1-4.
[11]C. Cortes, and V. Vapnik, (1995), “Support-vector networks,” Machine Learning, vol. 20, pp. 273-297.
[12]C. C. Chang and C. J. Lin, (2001), “LIBSVM: a library for support vector machines,” http://www.csie.ntu.edu.tw/~cjlin/libsvm.
[13]C. W. Hsu, C. C. Chang,, C. J. Lin, ( 2003),“A Practical Guideto Support Vector,Classification,” Available at http://www.csie.ntu.edu.tw/~cjlin/papers/guide/guide.pdf.
[14]C. E. Shannon, (1948), “A Mathematical Theory of Communication,” Bell System Technical Journal, vol. 27, pp. 379-423 and 623-656, July and October.
[15]C. T. Su, L. S. Chen, Y. Yih, (2006a), “Knowledge Acquisition through Information Granulation for Imbalanced Data,” Expert System with Applications, vol. 31, pp. 531-541.
[16]C. G. Weng, and J. Poon, (2006), “A Data Complexity Analysis on Imbalanced Datasets and an Alternative Imbalance Recovering Strategy,” International Conference on IEEE/WIC/ACM, pp.270-276.
[17]C. T. Su and Y. H. Hsiao, (2007), “An Evaluation of the Robustness of MTS for Imbalanced Data,” IEEE Trans. Knowledge and Data Eng, vol. 19, no. 10, pp. 1321-1332.
[18]C. I. Lee, C. J. Tsai, T. Q. Wu, W. P. Yang, (2008), “An Approach to Mining the Multi-Relational Imbalanced Database,” Expert Systems with Applications, vol. 34, pp. 3021-3032.
[19]C. G. Carrier, and O. Povel, (2003), “Characterising Data Mining Software,” Intelligent Data Analysis, vol. 7, pp. 181–192.
[20]C. Apte, S. Weiss, (1997), “Data Mining with Decision Trees and Decision Rules,” Future Generation Computer Systems, vol. 13, pp.197-210.
[21]C. M. Tseng, C. D. Jan, J. S. Wang, and C. M. Wang., (2007), “Application of Artificial Neural Networks in Typhoon Surge Forecasting,” Journal of Ocean Engineering, vol. 34, pp.1757-1768.
[22]C. T. Su, L. S. Chen, and T. L. Chiang, (2006b), “A Neural Network based Information Granulation Approach to Shorten the Cellular Phone Test Process,” Computers In Industry, vol. 57, no. 5, pp. 412-423.
[23]C. M. Hung and Y. M. Huang, (2008), “Conflict-Sensitivity Contexture Learning Algorithm for Mining Interesting Patterns Using Neuro-Fuzzy Network with Decision Rules,” Expert Systems with Applications, vol.34, pp. 159–172.
[24]D. Tax and R. Duin, (2004), “Support Vector Data Description,” Machine learning, vol. 54, pp. 45-66.
[25]D. M. J. Tax and R. P. W. Duin, (2001), “Uniform Object Generation
for Optimizing One-Class Classifiers,” Journal of Machine Learning Research, 2: pp. 155-173.
[26]D. Wang and L. Shi, (2008), “Selecting Valuable Training Samples for SVMs Via Data Structure Analysis,” Journal of Neurocomputing, vol. 71, pp. 2772-2781.
[27]D. Lewis, and J. Catlett, (1994), “Heterogeneous Uncertainty Sampling for Supervised learning,” Proceedings of the 11th International Conference on Machine Learning, pp. 144-156.
[28]E. Turban, J. E. Aronson, T. P. Liang, and R. Sharda, (2007), “Decision Support and Business Intelligence Systems (Eighth ed.),” Pearson Education.
[29]E. Cohen and B. Krishnamurthy, (2006), “A Short walk in the Blogistan,” Computer Networks, vol. 50, no. 5, April 2006, pp. 615-630.
[30]E. Spertus, (1997), “Smokey: Automatic recognition of hostile messages,” Proceeding of IAAI.
[31]G. Cohen, M. Hilario, H. Sax, S. Hugonnet, A. Geissbuhler, (2006), “Learning from Imbalanced Data in Surveillance of Nosocomial Infection,” Artificial Intelligence in Medicine, vol. 37, pp. 7-18.
[32]G. Weiss, and F. Provost, (2003), “Learning when Training Data are Costly: The Effect of Class Distribution on Tree Induction,” Journal of Artificial Intelligence Research, vol. 19, pp. 315-354.
[33]G. M. Weiss, and F. Provost, (2001), “The Effect of Class Distribution on Classifier Learning,” Technical Report, MLTR43, Department of Computer Science, Rutgers University.
[34]G. Weiss, (2004) “Mining with Rarity: a Unifying Framework,” SIGKDD Exploration, vol. 6, no. 1, pp. 7-19.
[35]G. Wu and E. Y. Chang, (2005), “KBA Kernel Boundary Alignment Considering Imbalance data Distribution,” IEEE Transactions on Knowledge and Data Engineering, vol. 17, no. 6, pp. 786-795.
[36]G. E. Batista, A. P. A., Prati, R. C., and M. C. Monard, (2004), “A Study of the Behaviour of Several Methods for Balancing Machine Learning Training Data,” ACM SIGKDD Explorations, vol. 6, no. 1, pp. 20-29.
[37]G. T. Zhou; Y. L. Yin; X. J. Guo; C. L. Dong; Q. Y. Wang, (2008), “VOTCL and a Case Study of Its Application,” Proceeding of IEE International Conference on natural Computation, vol. 2, pp. 222-227.
[38]G. V. Kass, (1980), “An Exploratory Technique for Investigating Large Quantities of Categorical Data,” Applied Statistics, vol. 29, no. 2, pp. 119- 127.
[39]H. He and E. A. Garcia, (2009), “Learning from Imbalanced Data,” Journal of IEEE Transacions on Knowledge and Data Engineering, vol. 21, no. 9, pp.1263-1284.
[40]H. Altincay and C. Ergun, (2004), “Clustering based Undersampling for Improving Speaker Verification Decisions Using AdaBoost,” Lecture Notes in Computer Science, vol. 3138, pp. 698- 706.
[41]H. Ahumada, G. L. Grinblat, L. C. Uzal, P. M. Granitto, and A. Ceccatto, (2008), “REPMAC: A New Hybrid Approach to Highly Imbalanced Classification Problems,” Proceeding of IEEE International Conference on Hybrid Intelligent, pp. 386-391.
[42]H. H. Nguyen, C.W. Chan, and M. Wilson, (2004), “Prediction of Oil Well Production: A Multiple-Neural-Network Approach,” Journal of Intelligent Data Analysis, vol. 8, pp. 183-196.
[43]H. Yu, C. Zhai, J. Han, (2003), “Text Classification from Positive and Unlabeled Documents,” Proceedings of the twelfth international conference on Information and knowledge management, pp. 232-239.
[44]I. Bose and R. K. Mahapatra, (2001), “Business Data Mining A Machine Learning Perspective,”Information&Management, vol. 39, pp. 211-225.
[45]J. H. Lei, J. J. He, (2009), “The Comparative Analysis and Study of Mobile-Based Customer Data Churn Prediction Model,” World Congress on Software Engineering, vol. 4, pp. 524-528.
[46]J. Zhang and I. Mani, (2003), “KNN Approach to Unbalanced Data Distributions: A Case Study Involving Information Extraction,” Proceeding of Int’l Conf. Machine Learning (ICML ’2003), Workshop Learning from Imbalanced Data Sets.
[47]J. B. MacQueen, (1967), “Some Methods for Classification and Analysis of Multivariate Observations,” Proceeding of Mathematics, Statistics, and Probability, pp.281-297.
[48]J. V. Hulse, T. M. Khoshgoftaar, A. Napolitano, (2009), “An Empirical Comparison of Repetitive Undersampling Techniques,” Proceeding of IEEE International Conference on Information Reuse & Integration, pp. 29-34.
[49]J. Xie, and Z. Qiu, (2007), “The Effect of Imbalanced Data Sets on LDA: A Theoretical and Empirical Analysis. Journal of Pattern Recognition,” vol.40, no.2, pp. 557-562.
[50]J. V. Hulse, T. M. Khoshgoftaar, and A. Napolitano, (2007), “Experimental Perspectives on Learning from Imbalanced Data,” Proceedings of the 24th International Conference on Machine Learning, Corvallis, OR, USA, pp. 935-942.
[51]J. Liu, Q. Hu, and D. Yu, (2008), “A Weighted Rough set based Method Developed for Class Imbalance Problem,” Information Sciences, vol. 178, pp. 1235-1256.
[52]J. W. Grzymala-Busse, J. Stefanowski, and S. Wilk, (2004), “A Comparison of Two Approaches to Data Mining from Imbalanced Data,” Lecture Notes in Computer Science, vol. 3213, pp. 757-763.
[53]J. R. Quinlan, (1986), “Induction of Decision Trees,” Machine Learning, vol. 1, no. 1, pp. 81-106.
[54]J. R. Quinlan, (1993), C4.5: Programs for Machine Learning, Morgan-Kaufmann, San Francisco.
[55]J. Thongkam, G. Xu, Y. Zhang, F. Huang, (2009), “Toward Breast Cancer Survivability Prediction Models Through Improving Training Space,” Expert Systems with Applications, vol. 36, no. 10, pp. 12200-12209.
[56]J. C. NaT, C. Khoo, P. H. J. Wu, (2005), “Use of Negation Phrases in Automatic Sentiment Classification of Product Reviews,” Journal of Library Collections, Acquisitions, and Technical Services, vol. 29, no. 2, pp. 180-191.
[57]J. Wiebe and E. Riloff, (2005), “Creating Subjective and Objective Sentence Classifiers from Unannotated Texts,” Proceeding of Sixth international conference on intelligent text processing and computational linguistics.
[58]J. Yi, T. Nasukawa, W. Niblack, and R. Bunescu, (2003), “Sentiment analyzer: Extracting Sentiments about a Given Topic Using Natural Language Processing Techniques,” In Proceedings of the 3rd IEEE international conference on data mining (ICDM 2003), pp. 427-434.
[59]K. Hiroshi, N. Tetsuya, and W. Hideo, (2004), “Deeper Sentiment Analysis Using Machine Translation Technology,” Proceedings of the 20th international conference on computational linguistics (COLING 2004) Geneva, Switzerland, pp. 494-500.
[60]K. Dave., S. Lawrence, and D. M. Pennock, (2003), “Mining the Peanut Gallery: Opinion Extraction and Semantic Classification of Product reviews,” The 12th WWW, pp. 519-528.
[61]L. Lin, G. Ravitz, M. L. Shyu, S. C. Chen, (2008), “Effective Feature Space Reduction with Imbalanced Data for Semantic Concept Detection,” Proceeding of IEEE International Conference on Sensor Networks, Ubiquitous, and Trustworthy Computing, pp. 262-269.
[62]L. Autio, M. Juhola, J. Laurikkala, (2007), “On the Neural Network Classification of Medical Data and an Endeavour to Balance Non-Uniform Data Sets with Artificial Data Extension,” Journal of Computers in Biology and Medicine, vol. 37, no. 3, pp. 388-397.
[63]L. Xu, M. Y. Chow, and L. S. Taylor, (2007), “Power Distribution Fault Cause Identification with Imbalanced data Using the Data Mining-based Fuzzy Classification E-Algorithm,” IEEE Transactions on Power Systems, vol. 22, no. 1, pp. 164-171.
[64]L. M. Manevitz and M. Yousef, (2001), “One Class SVMs for Document Classification,” Journal of Machine learning Research, vol. 2, pp. 139-154.
[65]L. Shoemaker, R.E. Banfield, L.O. Hall, K.W. Bowyer, W.P. Kegelmeyer, (2006), “Learning to Predict Salient Regions from Disjoint and Skewed Training Sets,” Proceeding of IEEE International Conference on Tools with Artificial Intelligence, pp. 116-126.
[66]L. Breiman, J. Friedman, R. Olshen, C. Stone, (1984), “Classification and Regression Tree,” Wadsworth International Group, Belmont, California.
[67]L. Lam and C. Y. Suen, (1997), “Application of Majority Voting to
Pattern Recognition: An Analysis of Its Behavior and Performance,” Proceeding of IEEE Transactions on systems, Man, and Cybernetics, vol. 27, no. 5, pp. 553-567.
[68]L. Shi, Y. J. Zuo, L. Y. Jun, Y. Qiang, (2008), “An Experimental Research on Sentiment Classification of Chinese Reviews by Semantic Orientation Method,” IEEE Control and Decision, pp. 3999-4004.
[69]L. Wang, (2005), “Support Vector Machines: Theory and Applications,” Berlin : Springer, pp.11-34.
[70]M. Kubat, and S. Matwin, (1997), “Addressing the Curse of Imbalanced Training Sets: One Sided Selection,”Machine Learning, pp. 179-186.
[71]M. Mazurowski, P. Habas, J. Zurada, J. Lo, J.Baker, and G. Tourassi, (2008), “Training Neural Network Classifiers for Medical Decision Making: The effects of Imbalanced Datasets on Classification Performance,” Neural Networks, vol. 21, no. 2-3, pp. 427-436.
[72]M. Makrehchi, M. S. Kamel, (2007), “A Text Classification Framework with a Local Feature Ranking for Learning Social Networks,” Proceeding of Sventh IEEE International Conference on Data Mining, pp. 589-594.
[73]M. J. Shaw, C. Subramaniam, G. W.Tan, and M. E.Welge, (2001), “Knowledge Management and Data Mining for Marketing,” Decision Support Systems, vol. 31, pp. 127-137.
[74]M. C. Chen, L. S. Chen, C. C. Hsu, and W. R. Zeng, (2008), “An Information Granulation based Data Mining Approach for Classifying Imbalanced Data,” Information Sciences, vol. 178, no.16, pp. 3214-3227.
[75]M. Z. Kukar and I. Kononenko, (1998), “Cost Sensitive Learning with Neural Networks,” Proceeding of European Conference. Artificial Intelligence, pp. 445-449.
[76]N. Seliya, Zhiwei Xu; T.M. Khoshgoftaar, (2008), “Addressing Class Imbalance in Non-Binary Classification Problems,” IEEE International Conference on Tools with Artificial Intelligence, vol. 1, pp. 460-486.
[77]N. Japkowicz and S. Stephan, (2002), “The Class Imbalance Problem: A Systematic Study,” Intelligent Data Analysis, vol. 6, no. 5, pp. 429-450.
[78]N. Kwaka and J. Oh, (2009), “Feature Extraction for One Class Classification Problems: Enhancements to Biased Discriminant Analysis,” Pattern Recognition, vol. 42, pp. 17-26.
[79]N. Chawla, K. Bowyer, L. Hall, and W. Kegelmeyer, (2002), “Smote: Synthetic Minority Over Sampling Technique,” J. Artificial Intelligent Res, vol. 16, pp. 321-357.
[80]N. V. Chawla, N. Japkowicz and A. Kolcz, (2004), “Editorial: Special Issue on Learning from Imbalanced Data Sets,” SIGKDD Explorations, vol. 6, no. 1, pp. 1-6.
[81]N. C. de Condorcet, (1785), “Essai sur l’Application de l’Analyze `a la Probabilit ´e des D´ecisions Rendues `a la Pluralit´e des Voix,” Paris, France:Imprim´erie Royale.
[82]N. Godbole, M. Srinivasaiah, and S. Skiena, (2007), “Large Scale Sentiment Analysis for News and Blogs,” In N. Glance & N. Nicolov (Eds.), International conference on weblogs and social media (ICWSM’2007).
[83]P. Li, P. L. Qiao and Y. C. Liu, (2008), “A Hybrid Re-sampling Method for SVM Learning from Imbalanced Data Sets,” IEEE Fuzzy Systems and Knowledge Discovery, vol. 2, pp.65-69.
[84]P. C. Mahalanobis, (1936), “On the Generalized Distance in Statistics,” Proceedings of the National Institute of Science of India, vol. 2, no. 1, pp. 49-55.
[85]P. K. Chan, W. Fan, A. L. Prodromidis, and S. J. Stolfo, (1999), “Distributed Data Mining in Credit Card Fraud Detection,” IEEE Intelligent Systems, November/December, pp. 67-74.
[86]P. Beineke, T. Hastie, and S. Vaithyanathan, (2004), “The Sentimental Factor: Improving Review Classification Via Human-Provided Information,” In Proceedings of the 42nd annual meeting of the association for computational linguistics (ACL), pp. 263–270.
[87]P. Chaovalit and L. Zhou, (2005), “Movie Review Mining: A Comparison between Supervised and Unsupervised Classification Approaches,” In Proceedings of IEEE international conference on system sciences, pp.1-9.
[88]P. D. Turney and M. L. Littman, (2003), “Measuring Praise and Criticism: Inference of Semantic Orientation from Association,” ACM Transactions on Information Systems, vol. 21, no. 4, pp. 315-346.
[89]P. D. Turney, (2002), “Thumbs Up or Thumbs Down? Semantic Orientation Applied to Unsupervised Classification of Reviews,” Proceedings of the 40th annual meeting of the Association for Computational Linguistics (ACL) Philadelphia, PA, USA, pp. 417-424.
[90]Q. Gu , Z. Cai, L. Zhu, B. Huang, (2008),“Data Mining on Imbalanced Data Sets,” Proceeding of IEE International Conference on Advanced Computer Theory and Engineering, pp.1020-1024.
[91]Q. Ye, Z. Zhang, R. Law, (2009), “Sentiment Classification of Online Reviews to Travel Destinations by Supervised Machine Learning Approaches,” Expert Systems with Application, vol. 36, no. 3, pp. 6527-6535.
[92]R. Barandela,, J. S. Sanchez, V. Garcia, and E. Rangel, (2003), “Strategies for Learning in Class Imbalance Problems,” Pattern Recognition, vol. 36, no. 3, pp. 849-851.
[93]R. Prabowo1, M. Thelwall, (2009), “Sentiment Analysis: A Combined Approach,” Journal of Informetrics, vol. 3, pp. 143-157.
[94]S. J. Yen, Y. S. Lee, (2009), “Cluster-based Under-Sampling Approaches for Imbalanced Data Distributions,” Expert Systems with Applications, vol. 36, no. 3, Part 1, pp. 5718-5727.
[95]S. R. Ahmed, (2004), “Applications of Data Mining in Retail Business,” Information Technology: Coding and Computing, vol. 2, pp. 455-459.
[96]S. Mitra, S. K. Pal, and P. Mitra, (2002), “Data Mining in Soft Computing Framework: A Survey,” IEEE Transactions on Neural Networks, vol. 13, pp. 3-14.
[97]S. Chen, W. Wang, (2009), “Decision Tree Learning for Freeway Automatic Incident Detection,” Expert Systems with Applications, vol. 36, pp. 4101-4105.
[98]S. Argamon, M. Koppel, and G. Avneri, (1998), “Routing Documents According to Style,” Proceeding of First international workshop on innovative information systems.
[99]S. Wang and X. Yao, (2009), “Diversity Analysis on Imbalanced Data Sets by Using Ensemble Models,” IEEE Symposium on Computational and Data mining, pp. 324-331.
[100]T. Varga, F. Szeifert, and J. Abonyi, (2009), “Decision Tree and First Principles Model based Approach for Reactor Runaway Analysis and Forecasting,” Journal of Engineering Applications of Artificial Intelligence, vol. 22, no. 4-5, pp. 569-578.
[101]T. L. Lee, D. S. Jeng, G. H. Zhang, and J. H. Hong, (2007), “Neural Network Modeling For Estimation Of Scour Depth Around Bridge Piers,” Journal of Hydrodynamics , vol. 19, no. 3, pp. 378-386.
[102]T. Jo and N. Japkowicz, (2004), “Class Imbalances versus Small Disjuncts,” SIGKDD Explorations, vol. 6, no. 1, pp. 40-49.
[103]T. K. Paul, H. Iba, (2009), “Prediction of Cancer Class with Majority Voting Genetic Programming Classifier Using Gene Expression Data,” Journal of IEEE/ACM Transactions on Computation Biology and Bioinformatics, vol.6, no. 2, pp. 353 -367.
[104]T. Kohonen, (1990), “The Self-Organizing Map,” Proceedings of the IEEE, vol. 78, no.9, pp. 1464-1480.
[105]T. Joachims, (1998), “Making Large Scale SVM Learning Practical,” In B. Scholkopf, C. J. C. Burges, & A. J. Smola (Eds.), Advances in Kernel Methods: Support Vector Learning. The MIT Press.
[106]T. Miyoshi and Y. Nakagam, (2007), “Sentiment Classification of Customer Reviews on Electric Products,” Proceeding of IEEE, pp. 2028-2033.
[107]T. Nasukawa and J. Yi, (2003), “Sentiment Analysis: Capturing Favorability Using Natural Language Processing,” Proceedings of the 2nd international conference on knowledge capture Florida, USA, pp. 70-77.
[108]T. Singh, L. Veron-Jackson, J. Cullinane, (2008), “Blogging: A New Play in Your Marketing Game Plan,” Business Horizons, vol. 51, no.4, July-August 2008, pp.281-292.
[109]T. Wilson, J. Wiebe, and P. Hoffmann, (2005), “Recognizing Contextual Polarity in Phrase-Level Sentiment Analysis,” Proceedings of human language technologies conference/conference on empirical methods in natural language processing (HLT/ EMNLP 2005), Vancouver, Canada.
[110]W. Zhu, (2007), “Topological Approaches to Covering Rough Sets,” Information Sciences, vol. 177, no. 6, pp. 1499-1508.
[111]X. Guo, Y. Yin, C. Dong, G. Yang, G. Zhou, (2008), “On the Class Imbalance Problem,” Proceeding of IEEE International Conference on Natural Computation, pp. 192-201.
[112]Y. Xie, X. Li, E.W.T. Ngai, W. Ying, (2009), “Customer Churn Prediction Using Improved Balanced Random Forests,” Expert Systems with Applications, Vol. 36, PP. 5445-5449.
[113]Y. M. Huang, C. M. Hung, and H. C. Jiau, (2006), “Evaluation of Neural Networks and Data Mining Methods on a Credit Assessment Task for Class Imbalance Problem,” Nonlinear Analysis: Real World Applications, vol. 7, no. 4, pp. 720-747.
[114]Y. Sun, M. S. Kamel, A. K. C Wong, and Y. Wang, (2007), “Cost Sensitive Boosting for Classification of Imbalanced Data,” Pattern Recognition, vol. 40, pp. 3358-3378.
[115]Y. Zhao and Y. Zhang, (2008), “Comparison of Decision Tree Methods for Finding Active Objects,” proceeding of Advances in Space Research, vol. 41, pp. 1955-1959.
[116]Y. Q. Liu, C. Wang, and L. Zhang, (2009), “Decision Tree based Predictive Models for Breast Cancer Survivability on imbalanced data,” Proceeding of IEEE International Conference On Bioinformatics and Biomedical Engineering, pp. 1-4.
[117]Z. H. Zhou and X. Y. Liu, (2006), “Training Cost Sensitive Neural Networks with Methods Addressing the Class Imbalance Problem,” IEEE Transactions on Knowledge and Data Engineering, vol. 18, no. 1, pp. 63-77.
[118]Z. Zhang, Y. Li, Q. Ye, R. Law, (2008), “Sentiment Classification for Chinese Product Reviews Using an Unsupervised Internet-based Method,” Management Science and Engineering, pp. 3-9.