(34.237.124.210) 您好!臺灣時間:2021/02/25 19:50
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果

詳目顯示:::

我願授權國圖
: 
twitterline
研究生:王致皓
研究生(外文):Wang, Chih-Hao
論文名稱:基於類神經網路反回饋機制的可適性羽球擊球分類
論文名稱(外文):Adaptive Badminton Stroke Classification by ANN Backward Propagation
指導教授:易志偉易志偉引用關係
指導教授(外文):Yi, Chih-Wei
口試委員:溫瓌岸易志偉曾煜棋王志全
口試委員(外文):Wen, Kuei-AnnYi, Chih-WeiTseng, Yu-CheeWang, Chih-Chuan
口試日期:2017-10-26
學位類別:碩士
校院名稱:國立交通大學
系所名稱:網路工程研究所
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2017
畢業學年度:106
語文別:英文
論文頁數:49
中文關鍵詞:羽球智慧球拍穿戴式設備球種分類可適性模型神經網路
外文關鍵詞:Wearable SensorMachine LearningStroke ClassificationBadminton
相關次數:
  • 被引用被引用:0
  • 點閱點閱:323
  • 評分評分:系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔
  • 下載下載:42
  • 收藏至我的研究室書目清單書目收藏:1
我們設計了智慧羽球拍,並利用機器學習技術,分析Random Forest,SMO(Polynomial Kernel, RBF Kernel)和Naïve Bayes四種分類器對於球種分類的準確度。在以前的研究中,發現了在一般模型和個人模型之間有個明顯的差距,約15-20%。然而,以前的機器學習技術是批量處理,沒有從一般模型到個人模型微調的方法。在本研究中,我們想基於神經網路和應用反向傳播,有機會將一般模型個人化,藉由使用即時的使用者資料來微調模型,可以讓一般模型從80%的準確度提升至93%的準確度,平均只要5組資料便能提升10%的效能。
另一方面,我們開發一個手機應用程式來實現我們的想法。它基於穿戴式設備和行動計算技術,讓使用者可以透過我們的智慧球拍建立自我訓練和比賽時的擊球記錄,通過錄影輔助可以靈活地標記球種,讓使用者標記優良測資和更正錯誤的資料,透過兩個手機程序互相連接交換資料,實現對戰計分的功能,再結合雲端服務,可以長時間地分析個人的打球風格和練習記錄。藉由發現選手的弱點來提升選手的羽毛球能力。
We have developed a smart badminton racket prototype with machine learning labeled technique to do automatic stroke type classification by Random Forest, SMO and Naïve Bayes. In the previous works, it shown that there is a gap between general model and personal model with accuracy 80% to 95% in average. However, the previous machine learning technique such as Random Forest, SMO and Naïve Bayes is batch processing and don’t have fine-tune method from general to personal model. In this work, we would like to design based on Neural Network and applied back-propagation to have the chance to modify general to personal.
On the other hand, we develop an App to realize our ideas. It is based on wearable devices and mobile computing to log stroke types in real time. Through the video program can label stroke types in flexible and automatic. Let two mobile phone programs communicate with each other to battle a game and score points. By combining with cloud service, it could be used to analyze personal style of play and game record in a long period. To improve the badminton rally ability of players by finding out the weakness of them.
Contents
Abstract i
Acknowledgement ii
List of Tables iii
List of Figures iv
Chapter 1 Introduction 1
1.1 Motivation 1
1.2 Organization 2
Chapter 2 Preliminary Research 3
2.1 Related Work 3
2.1.1 Stroke Type Classification 3
2.1.2 Automatic Scoring 4
2.2 Dataset 5
2.2.1 Define Stroke Type and Attributes 5
2.2.2 Experimental Description of Collected Data 5
2.2.3 Number of Data 6
2.2.4 Data Architecture Diagram 7
2.2.5 File Format 8
Chapter 3 Neural Networks Background 12
3.1 Introduction of Neural Network 12
3.2 Activation Function 16
3.3 Backward Propagation Algorithm 19
Chapter 4 Smart Racket Framework 23
4.1 System Architecture 23
4.2 Coordinate Transformation 25
4.3 Voiceprint Detection 26
4.4 Classification Algorithm 28
4.5 Result 29
Chapter 5 From General to Personalize 32
5.1 Our Network Architecture 32
5.2 Compare Different Classifier 34
5.3 Improve Accuracy of General Model 38
5.4 Field Trial Testing 39
5.5 SmartRecorder Application 42
5.5.1 Personalized Model 44
5.5.2 Stroke Record 44
5.5.3 Real-Time Battle 45
Chapter 6 Conclusions and Future Works 46
Reference 48
[1] P. Blank, J. Hoßbach, D. Schuldhaus, and B. M. Eskofier, “Sensorbased stroke detection and stroke type classification in table tennis,” in Proceedings of the 2015 ACM International Symposium on Wearable Computers. ACM, 2015, pp. 93–100.
[2] H. El-Gizawy and A.-R. Akl, “Relationship between reaction time and deception type during smash in badminton,” Journal of Sports Research, vol. 1, no. 3, pp. 49–56, 2014.
[3] C. T. Kiang, C. K. Yoong, and A. C. Spowage, “Local sensor system for badminton smash analysis,” in Instrumentation and Measurement Technology Conference, 2009. I2MTC ’09. IEEE, May 2009, pp. 883–888.
[4] S. Ramasinghe, K. G. M. Chathuramali, and R. Rodrigo, “Recognition of badminton strokes using dense trajectories,” in 7th International Conference on Information and Automation for Sustainability, Dec 2014, pp. 1–6.
[5] M. I. Rusydi, M. Sasaki, M. H. Sucipto, N. Windasari et al., “Study about backhand short serve in badminton based on the euler angle,” in 2015 4th International Conference on Instrumentation, Communications, Information Technology, and Biomedical Engineering (ICICI-BME). IEEE, 2015, pp. 108–112.
[6] M. Phomsoupha and G. Laffaye, “The science of badminton: game characteristics, anthropometry, physiology, visual fitness and biomechanics,” Sports Medicine, vol. 45, no. 4, pp. 473–495, 2015.
[7] H. Shishido, Y. Kameda, I. Kitahara, and Y. Ohta, “Trajectory estimation of a fast and anomalously moving badminton shuttle,” in International Workshop on Advanced Image Technology, January 2015.
[8] F. Alam, H. Chowdhury, C. Theppadungporn, and A. Subic, “Measurements of aerodynamic properties of badminton shuttlecocks,” Procedia Engineering, vol. 2, no. 2, pp. 2487–2492, 2010.
[9] H. Shishido, Y. Kameda, I. Kitahara, and Y. Ohta, “3d position estimation of badminton shuttle using unsynchronized multiple-view videos,” in Proceedings of the 7th Augmented Human International Conference 2016, ser. AH ’16. New York, NY, USA: ACM, 2016, pp. 47:1–47:2. [Online]. Available: http://doi.acm.org/10.1145/2875194.2875235
[10] A. Raina, N. Mokashi, P. Nimkar, and S. Gujar, “Shuttlecock tracking and trajectory estimation using microsoft kinect sensor,” vol. 4, October 2015.
[11] J. L. Personnic, F. Alam, L. L. Gendre, H. Chowdhury, and A. Subic, “Flight trajectory simulation of badminton shuttlecocks,” Procedia Engineering, vol. 13, pp. 344–349, 2011
[12] Tang, Jenn, and P. K. Wang. "An auto-scoring billiards system." Machine Learning and Cybernetics, 2009 International Conference on. Vol. 6. IEEE, 2009.
[13] Chin, Yuan-Chieh, et al. "Automatic score device of table tennis." System Integration (SII), 2015 IEEE/SICE International Symposium on. IEEE, 2015.
[14] Ju-Yi Lin, Chia-Wei Chang, Chih-Hao Wang, Hong-Chuan Chi, Chih-Wei Yi, Yu-Chee Tseng, and Chih-Chuan Chi. 2017. Design and Implement a Mobile Badminton Stroke Classification System. In Proceedings of the 19th Asia-Pacific Network Operations and Management Symposium (APNOMS2017).
[15] Neural network notes
http://darren1231.pixnet.net/blog/post/338810666-%E9%A1%9E%E7%A5%9E%E7%B6%93%E7%B6%B2%E8%B7%AF%28backpropagation%29-%E7%AD%86%E8%A8%98
[16] Android Developers, Motion Sensors
https://developer.android.com/guide/topics/sensors/sensors_motion.html
[17] Weka 3: Data Mining Software in Java
https://developer.android.com/guide/topics/sensors/sensors_motion.html
[18] Firebase
https://firebase.google.com/
連結至畢業學校之論文網頁點我開啟連結
註: 此連結為研究生畢業學校所提供,不一定有電子全文可供下載,若連結有誤,請點選上方之〝勘誤回報〞功能,我們會盡快修正,謝謝!
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
系統版面圖檔 系統版面圖檔