臺灣博碩士論文加值系統

在任何運動賽事上，大家最關注的就是賽事的結果，也就是比賽的輸贏。然而，過去許多研究都顯示，不管在何種賽場上如:足球、棒球、賽馬或籃球等等，比賽結果往往與運動員在比賽中的表現有非常顯著的相關，因此我們可以透過運動選手過去在賽場上的表現，經由紀錄所呈現的數據資料來達到預測賽事的結果。本研究主要專注在籃球賽事的分析與預測，資料是採用美國職業籃球NBA的賽季資料。在過去，此領域的研究多採用統計相關分析的方式，找出何種屬性與比賽結果最具有顯著相關。但此種方式缺乏將隱含在大量資料裡的規則顯示出來且必須具有統計相關知識才能實行。因此，我們採用了機器學習方法。運用支援向量機(SVM)分類演算法，並結合了以相關性為基礎的屬性擷取方法來分析，最後產生出指導規則提供球隊做為改善依據。透過規則，教練可以很快知道該針對哪些必要項目做調整，並使球隊獲勝。本研究結果顯示，支援向量機模型可以得到令人滿意得分類結果，並與過去常用統計方法比較，可獲得相對較優異的分類準確率。因此，此研究所提出的模型是很有希望的替代方案在籃球賽事的預測領域上。

Support Vector Machines (SVM), which follows the principle of structural risk minimization, is an emerging and powerful technique in coping with classification problems. However, a lack of rule generation is a weakness of the SVM model, especially in analyzing sporting results. This investigation developed a hybrid model integrating the SVM technique and a decision tree approach (HSVMDT) to predict the results of basketball games, and to provide rules to aid coaches in developing strategies. The HSVMDT model employed the unique strength of SVM and decision tree in generating rules and predicting the outcomes of games. With predicted outcomes of games, and rules yielded from the HSVMDT model, coaches can easily and quickly learn essential factors increasing the chances to win games. Data collected from the National Basketball Association (NBA) were used to examine the performance of the designed HSVMDT model. Empirical results showed that the proposed HSVMDT model can obtain relatively satisfactory prediction accuracy by comparison with previous studies on analyzing basketball games. The developed model is therefore a promising alternative for analyzing the results of basketball competitions.

目 錄

誌謝 i
中文摘要 ii
Abstract iii
第一章 緒論 1
第二章 文獻探討 7
2.1 運動預測議題之相關研究 7
2.2籃球預測相關文獻回顧 13
2.3 基於相關性為基礎之特徵選取法相關文獻回顧 21
2.4支援向量機 26
2.5 C4.5決策樹 31
第三章 研究方法 35
3.1研究架構 35
3.2資料分析 37
3.3基於相關性為基礎之特徵選取法 39
3.4 支援向量機 42
3.5 粒子群演算法 47
3.6 C4.5決策樹 52
第四章 實驗結果 56
4.1 實驗結果 56
4.2規則產生: 59
4.3二因子變異數分析 61
4.4案例推理: 64
第五章 結論與未來展望 66
參考文獻 67
圖目錄
圖一 研究流程架構圖 36
圖二 特徵選取的四個步驟 40
圖三 基於相關性為基礎之特徵選取演算法流程圖 41
圖四 CFS+GA選取最佳化特徵子集合流程 42
圖五 比較最佳區分超平面 43
圖六 支援向量機結構 44
圖七 高維度轉變為低維度 46
圖八 粒子移動圖1 48
圖九 粒子移動圖2 48
圖十 PSO結合SVM流程圖 51
圖十一 決策樹圖 55
圖十二 二因子變異數分析分析流程 62
表目錄
表一 運動與運動資料間之階層關係 4
表二 運動預測議題之文獻回顧 10
表三 籃球預測相關議題之文獻回顧 15
表四 基於相關性為基礎之特徵選取法之文獻回顧 23
表五 支援向量機之文獻回顧 28
表六 決策樹文獻回顧 33
表七 本研究資料所包含之變項 37
表八 經過CFS後所得的條件屬性 56
表九 沒有經過屬性篩選所產生的五次交叉驗證結果 57
表十 經過屬性篩選所產生的五次交叉驗證結果 57
表十一 兩種模型統整表 57
表十二 HSVMDT模型與LR, DA之比較表 58
表十三 C4.5決策樹修剪前與修剪後支覆蓋率與準確率 59
表十四 透過C4.5決策樹所產生之決策規則 60
表十五 誤差變異量的Levene檢定等式 62
表十六 受試者間效應項的檢定 62
表十七 對比結果(K 距離) 63
表十八 Scheffe法多重比較 64
表十九 案例研究 64

中文文獻:
[1]蔡岱亨. (2004).臺灣職業棒球運動發展之研究. 屏東師範學院體育學系碩士班碩士論文 .
[2]王宗吉.(1999).台灣地區運動參與人口調查報告.體育白皮書.臺北:行政院體委會.
[3]張少熙.(2004).體育活動規劃與管理.體育行政與管理,249-297.
[4]蔡義川. (2004). 高中籃球聯賽(HBL)三位置球員攻守技術與名次相關之分析研究.國立台灣體育學院體育研究所碩士學位論文,1-61.
[5]潘彥甫. (2010). 以Probit回歸模型預測NBA籃球比賽結果.國立新竹教育大學應用數學系應用數學系碩士班碩士論文.1-24.
[6]王俊明 (1995). 從統計觀點分析男子社會甲組籃球聯賽的攻防技術。論文發表於中華民國大專院校八十四學年度體育學術研討會，高雄縣，陸軍官校。
[7]王景南 (2000). 模糊迴歸分析在籃球比賽攻防技術之應用. 國家科學委員會研究彙刊：人文及社會科學.民國八十九年七月，十卷三期，287-298
[8]李昕昕 (2006). 籃球比賽先發球員攻守能力隊比賽成績的影響~以高中籃球聯賽甲組聯賽(HBL)為例.國立台灣體育學院體育研究所碩士學位論文,1-48.
[9]吳尚書 (2005). 九十三學年度高中籃球聯賽之攻守策略技術分析. 中國文化大學運動教練研究所碩士學位論文,1-42.
[10]邱啟益 (2008).2006年杜哈亞運男子籃球比賽攻守紀錄分析之研究.台北巿立體育學院運動技術研究所碩士學位論文.1-51.
[11]邱玉青,林煥智,時超傑.(2010). 98學年度國中籃球聯賽冠軍隊得分影響因素之探討. 2010 年國際體育運動與健康休閒發展趨勢研討會專刊.332-339.
[12]簡明富.(2011). 第五季 SBL 超級籃球聯賽競賽之攻守數據統計分析. 中國文化大學教育學院運動教練研究所碩士論文.1-35.
[13]賴俊明.(2010). 2006~2008 年瓊斯盃籃球賽中華男子隊攻守技術分析. 國立臺灣師範大學體育學系碩士學位論文.1-55.
[14]劉信宏.(2006).九十四學年度高中女子籃球聯賽之攻守數據統計分析.臺北市立教育大學體育學位碩士班碩士論文.1-42.
[15]麥雅惠.(2004). 仙台亞洲盃女子籃球比賽攻守記錄之分析研究. 國立體育學院教練研究所碩士論文.1-32.
[16]施靖桓.(2009).2008年北京奧運會男子籃球前四強技術表現之研究. 中國文化大學運動教練研究所碩士學位論文.1-53.
[17]陳贊仁.(2009). 以倒傳遞網路設計籃球運動彩券推薦模式. 大同大學資訊工程研究所碩士論文.1-84.
[18]鄭志強.(2006). 以決策樹演算法建構台灣企業財務危機預警模式. 資訊管理學系碩士班碩士論文.1-47.
英文文獻:
[1]Agrawal, A., & Jaffe, J. F. (1993). Mangement Turnover and Governance Changes Following the Revelation of Fraud. Journal of Law and Economics, 36, 309-342.
[2]Wooden,J.R.(1998).Practical Modern Basketball.New York.
[3]Piatetsky-Shapiro, G. (2008). Difference between data mining and statistics. Retrieved Oct 2, 2008, from http://www.kdnuggets.com/faq/difference-data-mining-statistics.html.
[4]Schumaker, R., Solieman, O. and Chen, H. (2010). Sports Data Mining, Springer.
[5]Nùñez, H., Angulo, C., Catala, A. (2002). Rule-extraction from support vector machines, in: Proceedings of the European Symposium on Artificial Neural Networks, 107–112.
[6]Martens, D., Baesens, B., Gestel, T.V., Vanthienen , J.(2007). Comprehensible credit scoring models using rule extraction from support vector machines. European Journal of Operational Research, 183(3), 1466-1476.
[7]Boulier, B. L., & Stekler, H. O. (2003). Predicting the outcomes of National Football League games. International Journal of Forecasting, 19, 257-270.
[8]Stekler,H.O., David Sendor, Richard Verlander.(2010). Issues in sports forecasting. International Journal of Forecasting, 26, 606–621.
[9]Enn O., Andrew F. (1997). Using Neural Networks to Predict Binary Outcomes. IEEE International Conference on Intelligent Processing Systcms, October 28 - 31. Beijing. China.
[10]David F., Robert S. (2000). Forecasting sport: the behaviour and performance of football tipsters. International Journal of Forecasting, 16, 317–331.
[11]James H. L., Lee S.(2001). The forecasting accuracy and determinants of football rankings. International Journal of Forecasting, 17, 105–120..
[12]ChiUng S., Bryan L. B., Herman O. S. (2007). The comparative accuracy of judgmental and model forecasts of American football games. International Journal of Forecasting, 23, 405– 413.
[13]Taoya C., Deguang C., Zhimin F., Jie Z. and Siwei L. (2003). A New Model Forecast the Result of Matches Based on Hybird Neural Networks in the Soccer Rating System. Proceedings of the Fifth International Conference on Computational Intelligence and Multimedia Applications (ICCIMA’03).
[14]Burak G.A., Mustafa M.I. (2007). A Comparative Study on Neural Network based Soccer Result Prediction. Seventh International Conference on Intelligent Systems Design and Applications.
[15]Richard R., Anthony B. (2010). An optimized ratings-based model for forecasting Australian Rules football. International Journal of Forecasting, 26, 511–517.
[16]Julio d.C. , Juan Prieto-Rodr´ıguez. (2010). Are differences in ranks good predictors for Grand Slam tennis matches?. International Journal of Forecasting, 26, 551–563.
[17]Stefan L., Ming-Chien S., Johnnie E.V. J. (2009). Identifying winners of competitive events: A SVM-based classification model for horserace prediction. European Journal of Operational Research, 196, 569–577.
[18]Benter, W. (1994). Computer based horse race handicapping and wagering systems: A report. In: Hausch, D.B., Lo, V.S.Y., Ziemba, W.T. (Eds.), Efficiency of Racetrack Betting Markets. Academic Press, London, 183–198.
[19]Stefan L., Ming-Chien S., Johnnie E.V. J. (2010). Alternative methods of predicting competitive events: An application in horserace betting markets. International Journal of Forecasting, 26, 518–536.
[20]Breiman, L. (2001). Random forests. Machine Learning, 45(1),5–32.
[21]Ian M., Alex M. (2011). A Bradley-Terry type model for forecasting tennis match results. International Journal of Forecasting, 27, 619–630.
[22]Dursun D., Douglas C., Nihat K. (2012). A comparative analysis of data mining methods in predicting NCAA bowl outcomes. International Journal of Forecasting, 28, 543–552.
[23]Steven B.C. (2003). Predicting discrete outcomes with the maximum score estimator: the case of the NCAA men’s basketball tournament. International Journal of Forecasting, 19, 313–317.
[24]Boulier B. L., & Stekler, H. O. (1999). Are sports seedings good predictors?: An evaluation. International Journal of Forecasting, 15, 83–91.
[25]Kvam P., & Sokol, J. S. (2006). A Logistic Regression/Markov Chain Model For NCAA Basketball. Naval Research Logistics, 53.
[26]Z. Ivanković, M. Racković, B. Markoski, D. Radosav, M. Ivković. (2010). Analysis of basketball games using neural networks. 11th IEEE International Symposium on Computational Intelligence and Informatics , 18–20 November, Budapest, Hungary.
[27]Chuang, L.-Y., Yang, C.-S., Wu, K.-C., & Yang, C.-H. (2011). Gene selection and classification using Taguchi chaotic binary particle swarm optimization. Expert Systems with Applications, 38, 13367-13377.
[28]Moravej, Z., Banihashemi, S. A., & Velayati, M. H. (2009). Power quality events classification and recognition using a novel support vector algorithm. Energy Conversion and Management, 50, 3071-3077.
[29]O¨zcift, A. (2011). Random forests ensemble classifier trained with data resampling strategy to improve cardiac arrhythmia diagnosis. Computers in Biology and Medicine, 41, 265-271.
[30]Sadeghzadeh, M., & Teshnehlab, M. (2010). Correlation-based Feature Selection using Ant Colony Optimization. World Academy of Science, Engineering and Technology, 64.
[31]Wang, Y., Tetko, I. V., Hall, M. A., Frank, E., Facius, A., Mayer, K. F. X., & Mewes, H. W. (2005). Gene selection from microarray data for cancer classification—a machine learning approach. Computational Biology and Chemistry, 29, 37–46.
[32]Hall, M.A. Correlation-based Feature selection for Machine Learning, Ph.D. Thesis, Department of Computer Science. Hamilton, New Zeland: The University of Waikato, 1999.
[33]Liu, H., & Motoda, H. (1998). Feature selection for knowledge discovery and data mining. Boston: Kluwer Academic Publishers.
[34]Cortes, C., Vapnik, V. (1995). Support-vector networks. Machine Learning, 20(3), 273-297.
[35]Burbidge, R., Trotter, M., Buxton, B., & Holden, S. (2001). Drug design by machine learning: support vector machines for pharmaceutical data analysis. Computers and Chemistry, 26, 5–14.
[36]Crisler, S., Morrissey, M. J., Anch, A. M., & Barnett, D. W. (2008). Sleep-stage scoring in the rat using a support vector machine. Journal of Neuroscience Methods, 168, 524–534.
[37]Kim, K.-j. (2003). Financial time series forecasting using support vector machines. Neurocomputing, 55, 307 – 319.
[38]LIU, W.-k., WANG, R.-f., & ZHENG, X.-j. (2008). Estimating coal reserves using a support vector machine. J China Univ Mining & Technol, 18, 0103-0106.
[39]Shih, J.-Y., Chen, W.-H., & Wu, S. (2007). A Study of SVM Classification Models in Issuers' Credit Ratings. Journal of Information Management, 14.
[40]Tay, F. E. H., & Cao, L. (2001). Application of support vector machines in !nancial time series forecasting. Omega, 29, 309–317.
[41]Tripathi, S., Srinivas, V. V., & Nanjundiah, R. S. (2006). Downscaling of precipitation for climate change scenarios: A support vector machine approach. Journal of Hydrology, 330, 621– 640.
[42]Valentini, G. (2002). Gene expression data analysis of human lymphoma using support vector machines and output coding ensembles. Artificial Intelligence in Medicine, 26, 281–304.
[43]Yang, B.-S., Kim, E. Y., & Son, J.-D. (2009). Fault diagnosis of low speed bearing based on relevance vector machine and support vector machine. Expert Systems with Applications, 36, 7252–7261.
[44]Zhou, J., Shi, J., & Li, G. (2011). Fine tuning support vector machines for short-term wind speed forecasting. Energy Conversion and Management, 52, 1990-1998.
[45]Mahesh P., Paul M. M. (2003). An assessment of the effectiveness of decision tree methods for land cover classification. Remote Sensing of Environment, 86, 554–565.
[46]Quinlan, J. R. (1993). C4.5: Programs for machine learning. San Mateo:Morgan Kaufmann.
[47]Kirchner, K., To¨lle, K.-H., Krieter, J. (2004). Decision tree technique applied to pig farming datasets. Livestock Production Science, 90, 191–200.
[48]Piroonratana T., Wongseree W., Assawamakin A., Paulkhaolarn N, Kanjanakorn C., Sirikong M., Thongnoppakhun W., Limwongse C., Chaiyaratana N. (2009). Classi fi cation of haemoglobin typing chromatograms by neural networks and decision trees for thalassaemia screening. Chemometrics and Intelligent Laboratory Systems, 99, 101–110.
[49]Mohmad Badr Al Snousy, Hesham Mohamed El-Deeb, Khaled Badran, Ibrahim Ali Al Khlil. (2011). Suite of decision tree-based classification algorithms on cancer gene expression data. Egyptian Informatics Journal , 12, 73–82.
[50]Amuthan Prabakar Muniyandi, R. Rajeswari , R. Rajaram. (2012). Network Anomaly Detection by Cascading K-Means Clustering and C4.5 Decision Tree algorithm. Procedia Engineering, 30, 174 – 182.
[51]http://www.nba.com/
[52]http://www.basketball-reference.com/