傳統的羽球在訓練上步驟繁雜且費力，不僅教練在人力資源上的缺乏以及
在過去記錄運動的方法是觀看影像，但是影像可能會由於角度或距離而失真，
並且難以從影像中識別出細微的運動。
如今，由於各種類型的運動感測器的出現，體育數據量化的方法已越來越
廣泛地被使用。為了提升訓練效率以及人力資源不足的情形，本論文提出了一
套即時羽球擊球資訊系統，此系統包括一個無線球拍感測器和一個手機 APP。
無線球拍感測器將動作資料透過藍牙傳送給手機。手機 APP 讀取資料後使用機
器學習進行資料分析分類並即時辨識擊球次數以及三種不同的擊球球種，包含
殺球、挑球和網前小球。
此外，本系統也提供羽球速度、擊球力道等資訊。本系統估計的羽球速度
與高速攝影機所量測的瞬時速度的皮爾遜相關性 r = 0.96，顯示其具有高度正相
關性。本系統估計的擊球力道則是使用牛頓第二運動定律作為依據。利用估計
的羽球速度和擊球力道，使用者可以分析他們的擊球狀況與擊球穩定度去協助
他們調整訓練方式和提升技能。

Traditional badminton training is complicated and laborious. For coaches,
recording a video was the only way to decipher and analyze the exercises of an athlete.
It may be distorted due to the angle or distance, and it is challenging to identify details.
Nowadays, due to the various types of motion sensors, quantifying sports data has
been widely used. In this thesis, we proposed a real-time badminton stroke information
system which includes a wireless racket sensor and a smartphone APP. The wireless
racket sensor transmits the motion data to the smartphone via Bluetooth. The
smartphone APP reads the data and use machine learning to analyze and classify the
data, and instantly recognize the number of strokes and three different actions,
including smash, lob, and net shot.
In addition, the system also provides the information of estimated shuttlecock
speed and stroke force. The Pearson correlation between the shuttlecock speed
estimated by this system and the instantaneous speed measured by the high-speed
camera is r = 0.96, showing that it has a high correlation. The estimated stroke force is
based on Newton's second law of motion. Using the estimated shuttlecock speed and
stroke force, users can analyze their hitting conditions and hitting stability to help them
adjust training methods and improve skills.

[1] 張妙瑛 and 張婷翔, “台灣羽球運動的引進與發展,” 興大體育學刊, no. 10, pp. 85-94, 2010.
[2] A. Anand, M. Sharma, R. Srivastava, L. Kaligounder, and D. Prakash, “Wearable Motion Sensor Based Analysis of Swing Sports,” in 2017 16th IEEE International Conference on Machine Learning and Applications (ICMLA), 18-21 Dec. 2017 2017, pp. 261-267.
[3] M. Rusydi, “Pattern Recognition of Overhead Forehand and Backhand in Badminton Based on the Sign of Local Euler Angle,” Indonesian Journal of Electrical Engineering and Computer Science, vol. 2, pp. 625-635, 06/07 2016.
[4] X. Zhang, H. Duan, M. Zhang, Y. Zhao, X. Sha, and H. Yu, “Wrist MEMS Sensor for Movements Recognition in Ball Games,” in 2019 IEEE 9th Annual International Conference on CYBER Technology in Automation, Control, and Intelligent Systems (CYBER), 29 July-2 Aug. 2019 2019, pp. 1663-1667.
[5] H. Saito, T. Watanabe, and A. Arifin, “Ankle and Knee Joint Angle Measurements during Gait with Wearable Sensor System for Rehabilitation,” in World Congress on Medical Physics and Biomedical Engineering, September 7-12, 2009, Munich, Germany, 2009: Springer, pp. 506-509.
[6] Y. W. Huang, S. H. Chang, Y. C. Tsai, and Y. H. Lin, “A Heart Rate Monitoring and Activities Recognition System for Badminton Training,” in 2019 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS), 3-6 Dec. 2019 2019, pp. 1-2.
[7] Y. Hong and Y. M. Tong, “The Playing Pattern of The World's Top Single Badminton Players in Competition - A Notation Analysis,” Journal of Human Movement Studies, vol. 38, pp. 185-200, 01/01 2000.
[8] M. Phomsoupha and G. Laffaye, “Shuttlecock Velocity during A Smash Stroke in Badminton Evolves Linearly with Skill Level,” (in eng), Comput Methods Biomech Biomed Engin, vol. 17 Suppl 1, pp. 140-1, 2014.
[9] M. King, H. Towler, R. Dillon, and S. McErlain-Naylor, “A Correlational Analysis of Shuttlecock Speed Kinematic Determinants in the Badminton Jump Smash,” Applied Sciences, vol. 10, no. 4, 2020.
[10] M. S. Salim, H. N. Lim, M. S. M. Salim, and M. Y. Baharuddin, “Motion Analysis of Arm Movement during Badminton Smash,” in 2010 IEEE EMBS Conference on Biomedical Engineering and Sciences (IECBES), 30 Nov.-2 Dec. 2010 2010, pp. 111-114.
[11] K. Weeratunga, A. Dharmaratne, and K. B. How, “Application of Computer Vision and Vector Space Model for Tactical Movement Classification in Badminton,” in 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 21-26 July 2017 2017, pp. 132-138.
[12] A. Ghosh, S. Singh, and C. V. Jawahar, “Towards Structured Analysis of Broadcast Badminton Videos,” in 2018 IEEE Winter Conference on Applications of Computer Vision (WACV), 12-15 March 2018 2018, pp. 296-304.
[13] S. Barris and C. Button, “A Review of Vision-Based Motion Analysis in Sport,” Sports medicine (Auckland, N.Z.), vol. 38, pp. 1025-43, 02/01 2008.
[14] C. Z. Shan, E. S. L. Ming, H. A. Rahman, and Y. C. Fai, “Investigation of Upper Limb Movement during Badminton Smash,” in 2015 10th Asian Control Conference (ASCC), 31 May-3 June 2015 2015, pp. 1-6.
[15] M. A. I. Anik, M. Hassan, H. Mahmud, and M. K. Hasan, “Activity Recognition of a Badminton Game Through Accelerometer and Gyroscope,” in 2016 19th International Conference on Computer and Information Technology (ICCIT), 18-20 Dec. 2016 2016, pp. 213-217.
[16] Z. Wang, M. Guo, and C. Zhao, “Badminton Stroke Recognition Based on Body Sensor Networks,” IEEE Transactions on Human-Machine Systems, vol. 46, no. 5, pp. 769-775, 2016.
[17] P. Weiping, W. Jun, X. Xubin, W. Zhengwei, and D. Xiaorong, “An Embedded 6-axis Sensor Based Recognition for Tennis Stroke,” in 2017 IEEE International Conference on Consumer Electronics (ICCE), 8-10 Jan. 2017 2017, pp. 55-58.
[18] Y. Wang, M. Chen, X. Wang, R. H. M. Chan, and W. J. Li, “IoT for Next-Generation Racket Sports Training,” IEEE Internet of Things Journal, vol. 5, no. 6, pp. 4558-4566, 2018.
[19] S. S. Tabrizi, S. Pashazadeh, and V. Javani, “Comparative Study of Table Tennis Forehand Strokes Classification Using Deep Learning and SVM,” IEEE Sensors Journal, pp. 1-1, 2020.
[20] C. J. Burges, “A Tutorial on Support Vector Machines for Pattern Recognition,” Data mining and knowledge discovery, vol. 2, no. 2, pp. 121-167, 1998.
[21] J. C. Platt, “Sequential Minimal Optimization: A Fast Algorithm for Training Support Vector Machines,” Advances in Kernel Methods-Support Vector Learning, vol. 208, Jul. 1998.
[22] 楊瑞珠, “羽球正手放網前球動作之定性分析,” 政大體育研究, no. 23, pp. 93+ 95-107, 2014.
[23] M. Hall, E. Frank, G. Holmes, B. Pfahringer, P. Reutemann, and I. H. Witten, “The WEKA Data Mining Software: An Update,” SIGKDD Explor. Newsl., vol. 11, no. 1, pp. 10–18, 2009.
[24] Nordic Semiconductor, “nRF52832,” Accessed: Apr. 23, 2020. [Online]. Available: https://www.nordicsemi.com/Products/Low-power-short-range-wireless/nRF52832.
[25] InvenSense, “ICM-20649,” Accessed: Apr. 23, 2020. [Online]. Available: https://invensense.tdk.com/wp-content/uploads/2016/06/DS-000192-ICM-20649-v1.0.pdf.
[26] STMicroelectronics, “H3LIS331DL,” Accessed: Apr. 23, 2020. [Online] Available: https://www.st.com/resource/en/datasheet/h3lis331dl.pdf.
[27] 張家偉, “智慧羽球拍應用於球種分類,” 國立交通大學, 2016.
[28] U. Jensen, M. Ring, and B. Eskofier, “Generic Features for Biosignal Classification,” Sportinformatik 2012, vol. 112, 2012.
[29] M. S. Stephen, “Francis Galton's Account of the Invention of Correlation,” Statistical Science, vol. 4, no. 2, pp. 73-79, 5/1 1989.
[30] P. Schober, C. Boer, and L. A. Schwarte, “Correlation Coefficients: Appropriate Use and Interpretation,” Anesthesia & Analgesia, vol. 126, no. 5, 2018.