臺灣博碩士論文加值系統

本研究提出使用支持向量機結合基因演算法(GA-SVM)應用於跆拳道動態動作評估。為了對動態動作進行分類，我們將原始運動訊號轉換至頻譜加以分析。然而，並非所有頻譜特徵都是有效的，沒有用的特徵會導致分類器的準確率下降，運算時間上升，降低分類器的效能。因此，本研究提出一種使用GA-SVM對動態動作分類的方法，並應用於跆拳道運動。基因演算法(Genetic Algorithm, GA)，藉由訂定適當的目標函數，能夠搜尋出有用的頻譜特徵，藉以降低特徵維度並改善分類器的效能；支持向量機(Support Vector Machine, SVM)可以有效率的解決樣本數量少、非線性及高維度的問題，應用在動態動作的分類上有很好的表現。在實驗過程中我們收集了12位跆拳道校隊選手(八名女性、四名男性)的運動訊號，並使用GA-SVM對每一位選手建立分類模型。為了展現研究成果，最後我們將GA-SVM與SVM、C4.5方法進行比較。

This research proposes a GA–SVM classification method for the dynamic action evaluation of taekwondo. For classifying a dynamic action, we converted a dynamic action signal to a frequency spectrum signal for analysis. However, the useful features were concentrated in a part of the frequency spectrum, and the useless features led to a decline in accuracy, operation speed, and efficiency of the classifier. Therefore, we propose a classification method that involves using a support vector machine (SVM) with a genetic algorithm (GA) for the dynamic action evaluation of taekwondo. The GA determines the useful features by setting the appropriate objective function, and the useless features are eliminated, thus reducing the dimensionality and improving the accuracy of the classifier. The SVM can solve problems of small, nonlinear, and high-dimension samples efficiently, exhibiting superior performance in the classification of a dynamic action. In a simulation process, motion signals were collected from 12 athletes (eight female and four male) from a taekwondo school team. We established a classification module for each athlete by using the GA-SVM. The experimental results of the proposed GA–SVM classification method showed that the GA can effectively determine useful classification information and improve the accuracy of the classifier. Moreover, we compared the GA–SVM classification method with the C4.5 classification algorithm. The results showed that the GA–SVM classification method is superior and more efficient in classifying a dynamic action.

第一章 緒論 1
第一節 研究背景 1
第二節 研究目的 2
第三節 論文架構 3

第二章 文獻探討 4
第一節 支持向量機與動態動作辨識 4
第二節 特徵選擇 6
第三節 基因演算法應用於特徵選擇 7
第四節 跆拳道的基本動作 9
第五節 Android Wear智慧型穿戴式裝置 13

第三章 研究方法 17
第一節 利用基因演算法搜尋有用的分類特徵 18
第二節 利用SVM對跆拳道資料建立分類模型 22
第三節 GA-SVM 24
第四節 Android Wear感測器APIs 26

第四章 實驗規劃與結果分析 30
第一節 受測選手及感測器穿戴位置 30
第二節 運動訊號收集及前處理 32
第三節 使用GA-SVM實作分類器 37
第四節 模擬結果與分析 38
第五節 跆拳道分類器程式實作 40

第五章 結論與建議 42
第一節 結論 42
第二節 建議 42

參考文獻 43
一 網頁參考文獻 43
二 中文參考文獻 43
三 英文參考文獻 44

附錄 47

一、 網頁參考文獻
[1] Digitimes。智慧型手機中感測元件。線上檢索日期：2016年6月16號。網址：http://www.digitimes.com.tw/tw/dt/n/shwnws.asp?id=0000303127_NXY2VSZR1SBT5X81BOLNV
[2] Nike Plus Running。線上檢索日期：2016年6月16號。網址：
http://www.nike.com/us/en_us/c/running/nikeplus/gps-app
[3] Runkeeper。線上檢索日期：2016年6月16號。網址：https://runkeeper.com/
[4] 馬拉松世界。線上檢索日期：2016年6月16號。網址：http://www.marathonsworld.com/
[5] Endomondo。線上檢索日期：2016年6月16號。網址：https://www.endomondo.com/
[6] mySports。線上檢索日期：2016年6月16號。網址：https://www.mysports.net.tw/
[7] Runtastic。線上檢索日期：2016年6月16號。網址：https://www.runtastic.com/
[8] World Martial Arts Academy。THE HISTORY OF TAEKWONDO。線上檢索日期：2016年6月16號。網址： http://www.worldtaekwondo.com/history.htm
[9] 百度經驗。運動跆拳道實戰基本腿法。線上檢索日期：2016年6月16號。網址：http://jingyan.baidu.com/article/9c69d48f679e4913c9024e8a.html
[10] Asus。ZenWatch。線上檢索日期：2016年6月16號。網址：https://www.asus.com/tw/ZenWatch/ZenWatch_WI500Q/specifications/
[11] Intelligent Control Techniques in Mechatronics - Genetic algorithm。線上檢索日期：2016年3月11號。網址：http://www.ro.feri.uni-mb.si/predmeti/int_reg/Predavanja/Eng/3.Genetic%20algorithm/_05.html
[12] Android Developers。SensorEvent。線上檢索日期：2016年6月16號。網址：http://developer.android.com/reference/android/hardware/SensorEvent.html


二、 中文參考文獻
[13] 相子元，石又，何金山(2012)。感測科技於運動健康科學之應用，中華民國體育學報，第45卷第1期。
[14] 林哲英，黃志鵬(2015)。利用模糊推論結合基因演算法應用於LEGO Mindstorms NXT兩輪自體平衡機器人，中華民國，臺北，臺北市立大學資訊科學系碩士班碩士論文。
[15] 黃瀞萱，洪瑞鍾(2015)。支援向量迴歸結合真實波動分類預測股票指數，中華民國，臺北，臺北市立大學資訊科學系在職進修碩士班碩士論文。


三、 英文參考文獻
[16] Varkey, J. P., Pompili, D., & Walls, T. A. (2012). Human motion recognition using a wireless sensor-based wearable system. Personal and Ubiquitous Computing, Vol. 16, pp. 897-910.
[17] Martin, T., Jovanov, E., & Raskovic, D. (2000, October). Issues in wearable computing for medical monitoring applications: a case study of a wearable ECG monitoring device. In Wearable Computers, The Fourth International Symposium on. IEEE, pp 43-49.
[18] Jiang, P., Winkley, J., Zhao, C., Munnoch, R., Min, G., & Yang, L. T. (2014). An intelligent information forwarder for healthcare big data systems with distributed wearable sensors, IEEE Systems Journal, pp. 1-9.
[19] DeVaul, R. W., & Dunn, S. (2001). Real-time motion classification for wearable computing applications. 2001 Project Paper.
[20] Sun, Z., Mao, X., Tian, W., & Zhang, X. (2008). Activity classification and dead reckoning for pedestrian navigation with wearable sensors. Measurement science and technology, Vol. 20, pp.1-10.
[21] Cho, Y., Nam, Y., Choi, Y. J., & Cho, W. D. (2008, June). SmartBuckle: human activity recognition using a 3-axis accelerometer and a wearable camera. In Proceedings of the 2nd International Workshop on Systems and Networking Support for Health Care and Assisted Living Environments ACM, No. 7, pp.1-3.
[22] Quinlan, J. R. (1993). C4.5: Programs for machine learning. Morgan Kaufmann press, San Mateo, CA.
[23] Cortes, C., & Vapnik, V. (1995). Support-vector networks. Machine learning, Vol. 20, pp. 273-297.
[24] X. Wu, V. Kumar, J.R. Quinlan, J. Ghosh, Q. Yang, H. Motoda, G.J. McLachlan, A. Ng, B. Liu, P.S. Yu, Z.H. Zhou, M. Steinbach, D.J. Hand, D. Steinberg. (2008). Top 10 algorithms in data mining. Knowledge and information systems, Vol. 14, pp. 1-37.
[25] Shawe-Taylor, J., & Cristianini, N. (2004). Kernel methods for pattern analysis. Cambridge university press, Cambridge, UK.
[26] Foody, G. M., & Mathur, A. (2004). Toward intelligent training of supervised image classifications: directing training data acquisition for SVM classification. Remote Sensing of Environment, Vol. 93, pp 107-117.
[27] Bahlmann, C., Haasdonk, B., & Burkhardt, H. (2002). Online handwriting recognition with support vector machines-a kernel approach. In Frontiers in handwriting recognition, 2002. proceedings. eighth international workshop on IEEE, pp. 49-54.
[28] Karchin, R., Karplus, K., & Haussler, D. (2002). Classifying G-protein coupled receptors with support vector machines. Bioinformatics, Vol. 18, pp 147-159.
[29] Bagheri-Khaligh, A., Raziperchikolaei, R., & Moghaddam, M. E. (2012, April). A new method for shot classification in soccer sports video based on SVM classifier. In Image Analysis and Interpretation (SSIAI), 2012 IEEE Southwest Symposium on IEEE, pp. 109-112.
[30] Wang, W. F., Yang, C. Y., & Guo, J. T. (2015). A Sport Recognition Method with Utilizing Less Motion Sensors. In Genetic and Evolutionary Computing. Springer International Publishing, pp. 155-167.
[31] Rui, L., Honglei, W., Qingxin, Z., Shujiao, L., Hongyao, D. (2016). A Fast Detection and Recognition Algorithm for Pedestrian at Night Based on Entropy Weight Fast Support Vector Machine. International Journal of Security and Its Applications, Vol. 10, pp. 243-252.
[32] Dash, M., Liu, H. (1997). Feature selection for classification. Intelligent data analysis, Vol. 1, pp. 131-156.
[33] Liu, H., & Motoda, H. (2012). Feature selection for knowledge discovery and data mining. Springer Science & Business Media, Berlin, DE.
[34] Li, X., & Yin, M. (2013). Multiobjective binary biogeography based optimization for feature selection using gene expression data. IEEE transactions on nanobioscience, Vol. 12, pp. 343-353.
[35] Xue, B., Zhang, M., & Browne, W. N. (2013). Particle swarm optimization for feature selection in classification: a multi-objective approach. IEEE transactions on cybernetics, Vol. 43, pp. 1656-1671.
[36] Chandrashekar, G., & Sahin, F. (2014). A survey on feature selection methods. Computers & Electrical Engineering, Vol. 40, pp. 16-28.
[37] Eesa, A. S., Orman, Z., & Brifcani, A. M. A. (2015). A novel feature-selection approach based on the cuttlefish optimization algorithm for intrusion detection systems. Expert Systems with Applications, Vol. 42, pp. 2670-2679.
[38] Holland, J. H. (1975). Adaptation in natural and artificial systems: an introductory analysis with applications to biology, control, and artificial intelligence. U Michigan Press, Ann Arbor, MI.
[39] Maimon, O. Z., & Braha, D. (1998). A genetic algorithm approach to scheduling PCBs on a single machine. International Journal of Production Research, Vol. 36, pp. 761-784.
[40] George, A., Rajakumar, B. R., & Binu, D. (2012, August). Genetic algorithm based airlines booking terminal open/close decision system. In proceedings of the International Conference on Advances in Computing, Communications and Informatics. ACM, pp. 174-179.
[41] Gen, M., & Cheng, R. (2000). Genetic algorithms and engineering optimization. John Wiley & Sons, Hoboken, NJ.
[42] Huang, C. L., & Wang, C. J. (2006). A GA-based feature selection and parameters optimizationfor support vector machines. Expert Systems with applications, Vol. 31, pp. 231-240.
[43] Zhao, M., Fu, C., Ji, L., Tang, K., & Zhou, M. (2011). Feature selection and parameter optimization for support vector machines: A new approach based on genetic algorithm with feature chromosomes. Expert Systems with Applications, Vol. 38 , pp. 5197-5204.
[44] Tsai, C. F., Eberle, W., Chu, C. Y. (2013). Genetic algorithms in feature and instance selection. Knowledge-Based Systems, Vol. 39, pp. 240-247.
[45] De Stefano, C., Fontanella, F., Marrocco, C., Di Freca, A. S. (2014). A GA-based feature selection approach with an application to handwritten character recognition. Pattern Recognition Letters, Vol. 35, pp. 130-141.
[46] Welikala, R. A., Fraz, M. M., Dehmeshki, J., Hoppe, A., Tah, V., Mann, Barman, S. A. (2015). Genetic algorithm based feature selection combined with dual classification for the automated detection of proliferative diabetic retinopathy. Computerized Medical Imaging and Graphics, Vol. 43, pp. 64-77.
[47] Ahmad, F., Isa, N. A. M., Hussain, Z., Osman, M. K., & Sulaiman, S. N. (2015). A GA-based feature selection and parameter optimization of an ANN in diagnosing breast cancer. Pattern Analysis and Applications, Vol. 18, pp. 861-870.
[48] Kang, W. S., & Lee, K. M. (1999). A Modern History of Taekwondo. Pogyŏng Munhwasa, Seoul, KR.
[49] Gillis, A. (2008). A killing art: The untold history of Tae Kwon Do. ECW press, Toronto, CA.
[50] Suykens, J. A., & Vandewalle, J. (1999). Least squares support vector machine classifiers. Neural processing letters, Vol. 9, pp. 293-300.
[51] Kuhn, H. W., Tucker, A. W. (1951). Nonlinear programming: Proceedings of 2nd Berkeley Symposium. University of California Press, Oakland, US, pp. 481-492.
[52] Chang, C. C., & Lin, C. J. (2011). LIBSVM: a library for support vector machines. ACM Transactions on Intelligent Systems and Technology , Vol. 2, pp. 27.