姿態辨識近年來在機算機科學領域裡面是一個很熱門的話題，他的目標是能夠透過數學演算法來表達人類的姿態，它可以應用在許多不同技術上，例如：行動電話上的應用、穿戴式的無線裝備上、運動上的偵測、電視遊戲或是與藝術的結合。
在這篇論文中，我們將會在手腕內側配戴9軸感測器 (包誇加速度計、陀螺儀及磁力計) 來紀錄8種動作的訊號並放到電腦裡去計算與分析，使用論文所提出的演算法加以辨識受測者的動作。我們使用的是機器學習的流程來建立的辨識系統。除了使用機器學習的方式來分類所要辨識的動作，我們還開發了一個使用閥值來判斷動作的方法，這個方法較為簡單與直觀，然而並非所有的動作都可以透過如此簡單的方式來偵測，所以我們最終是以機器學習的分類方法來建立我們
的系統，這兩種方法的驗證與比較也將會呈現在實驗結果的章節裡。
為了達到較高的辨識準確度，我們使用機器學習的分類流程，並且更進一步做特徵的選取與萃取，我們使用的方法為主成分分析法 (principal componentanalysis) 在加上線性判別分析 (linear discriminant analysis) 來萃取出較明確的特徵，主成分分析法與線性判別分析的優點為可以減少資料的維度並且減少後面分類的訓練時間，也能盡可能的保留原始資料的最大資訊量，我們也開發了一個方法來建立一個適合後面分類器的特徵矩陣以達到較好的表現。最後我們使用的分類器是支持向量機 (support vector machine)，這個分類器可以使辨識的精準度更高、計算時間較少、也可以支援高維度的數據，在實驗中，我們把動作分成8類，20個人一人做每個動作5次為實驗數據，在使用者相依的狀況下可以得到99.63%的準確度，而在使用者無關的狀況下我們收集了12個人的測試資料並得到88.43%的準確度。

Gesture recognition is a topic in computer science with the goal of describing human gestures through mathematical algorithms in recent year. In the field of hand gesture recognition,it apply in many kinds of technologies such as mobile phone applications, wearable wireless devices, sports detection, video game or art combination.
In this thesis, we will record signals of eight kinds of hand movements into computer using wearable wireless device with nine axis sensor (including accelerometer, gyroscope and magnetometer) worn on the wrist, then recognized gestures using the algorithms being described later. We built a system of recognition with machine learning classification process. Besides classification process, we also developed a thresholding method to easily detect movements. In the thresholding method, for each movement, we defined threshold value for each kind of data and filtered the movements data with threshold combined with detection windows. However, not all the movements can be detected by this easy and less calculation method so that we finally used a machine learning process to solve problems. The analyzing
of the two method will be introduced later.
In order to achieve higher recognition accuracy, we used machine learning process in the system and did feature extraction to get well distinguished features. We used principal component analysis (PCA) and linear discriminant analysis (LDA) to extract features. The
advantages of PCA and LDA are reducing dimensions of data while preserving as much of the class discriminatory information as possible and reducing the training time of classification. Last, with support vector machine (SVM), we can recognize movement with higher accuracy
with less computation time, and it also support data with high dimension. We can model even non-linear relations with more precise classification due to SVM kernels. In our experiment, we can get the accuracy of recognition at 99.63% for 8 classes with 20 subjects data for 5 times each in user-dependent case, and 12 subjects testing data for user-independent case with recognition rate at 88.43%.

1 Introduction 1
1.1 Background . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1
1.2 Motivation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2
1.3 Main Contributions . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3
1.4 Organization . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4
2 Overview of Gesture Recognition Technologies 5
2.1 Different Sensing Technologies in Gesture Recognition . . . . . . . . . . . . 5
2.1.1 Inertial Sensing Technology . . . . . . . . . . . . . . . . . . . . . . 6
2.1.2 Image Based Technology . . . . . . . . . . . . . . . . . . . . . . . . 6
2.1.3 Inertial Sensing Integrate with Image Based Technology . . . . . . . 7
2.1.4 Glove Sensing Technology . . . . . . . . . . . . . . . . . . . . . . . 8
2.1.5 Optical Sensing Technology . . . . . . . . . . . . . . . . . . . . . . 8
2.1.6 Acoustic Sensing Technology . . . . . . . . . . . . . . . . . . . . . 9
2.1.7 Radio frequency Sensing Technology . . . . . . . . . . . . . . . . . 9
2.1.8 Summary of Different Technologies . . . . . . . . . . . . . . . . . . 10
2.2 Gesture Recognition Algorithms of Inertial Sensing Technology . . . . . . . 12
2.2.1 Characteristics of Features . . . . . . . . . . . . . . . . . . . . . . . 12
2.2.2 Detection Methods . . . . . . . . . . . . . . . . . . . . . . . . . . . 13
2.3 Comparison of Different Classifier using Inertial Sensing Technology . . . . 16
3 Proposed System and Algorithms 21
3.1 Overview . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 21
3.2 Architecture of System . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 21
3.3 Introduction to Inertial Body Sensor (Nine Axis Sensor) . . . . . . . . . . . 23
3.3.1 MPU9250 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 23
3.3.2 Signals of Nine-Axis Sensor . . . . . . . . . . . . . . . . . . . . . . 25
3.4 Definition of Movements to be Recognized . . . . . . . . . . . . . . . . . . 30
3.5 Thresholding Method with Scanning Window . . . . . . . . . . . . . . . . . 32
3.6 Dimension Reduction and Feature Extraction . . . . . . . . . . . . . . . . . 36
3.6.1 Dimension Reduction using Principal Component Analysis Algorithm 37
3.6.2 Feature Extraction using Linear Discriminant Analysis Algorithm . . 42
3.6.3 Comparison of PCA and LDA Algorithm . . . . . . . . . . . . . . . 46
3.7 Data Classification . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 46
3.7.1 Theory . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 47
3.7.2 Feature Vectors for Support Vector Machine . . . . . . . . . . . . . . 48
3.7.3 System Classification using SVM Classifier . . . . . . . . . . . . . . 49
4 Implementation Results 53
4.1 Experiment . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 53
4.1.1 Experimental Environments . . . . . . . . . . . . . . . . . . . . . . 53
4.1.2 Experiment Procedure . . . . . . . . . . . . . . . . . . . . . . . . . 55
4.2 Analysis of Received 9-Axis Signals . . . . . . . . . . . . . . . . . . . . . . 56
4.3 Result Analysis . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 59
4.3.1 Thresholding Method Analysis . . . . . . . . . . . . . . . . . . . . . 59
4.3.2 SVM Analysis in User-dependent/User-independent Case . . . . . . 60
4.3.3 Comparison of Thresholding and SVM . . . . . . . . . . . . . . . . 64
4.3.4 Comparison between Our Work and Some Related Studies . . . . . . 66
5 Conclusions and Future Works 71
5.1 Conclusions . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 71
5.2 Future Works . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 72

[1] Z. Zhang, Z. Wu, J. Chen, and J.-K. Wu, “Ubiquitous human body motion capture using micro-sensors,” in Pervasive Computing and Communications, 2009. PerCom 2009. IEEE International Conference on, March 2009, pp. 1–5.
[2] J. S. Wang and F. C. Chuang, “An accelerometer-based digital pen with a trajectory recognition algorithm for handwritten digit and gesture recognition,” IEEE Transactions on Industrial Electronics, vol. 59, no. 7, pp. 2998–3007, July 2012.
[3] M. Zhang and A. A. Sawchuk, “A customizable framework of body area sensor network for rehabilitation,” in 2009 2nd International Symposium on Applied Sciences in Biomedical and Communication Technologies, Nov 2009, pp. 1–6.
[4] H. P. Gupta, H. S. Chudgar, S. Mukherjee, T. Dutta, and K. Sharma, “A continuous hand gestures recognition technique for human-machine interaction using accelerometer and gyroscope sensors,” IEEE Sensors Journal, vol. 16, no. 16, pp. 6425–6432, Aug 2016.
[5] K. Kuroki, Y. Zhou, Z. Cheng, Z. Lu, Y. Zhou, and L. Jing, “A remote conversation support system for deaf-mute persons based on bimanual gestures recognition using
finger-worn devices,” in Pervasive Computing and Communication Workshops (PerCom Workshops), 2015 IEEE International Conference on, March 2015, pp. 574–578.
[6] J. Ducloux, P. Colla, P. Petrashin, W. Lancioni, and L. Toledo, “Accelerometer-based hand gesture recognition system for interaction in digital tv,” in 2014 IEEE International Instrumentation and Measurement Technology Conference (I2MTC) Proceedings, May 2014, pp. 1537–1542.
[7] L. Chen, F. Wang, H. Deng, and K. Ji, “A survey on hand gesture recognition,” in Computer Sciences and Applications (CSA), 2013 International Conference on, Dec 2013, pp. 313–316.
[8] M. Panwar, “Hand gesture recognition based on shape parameters,” in 2012 International Conference on Computing, Communication and Applications, Feb 2012, pp. 1–6.
[9] P. Pawiak, T. Sonicki, M. Niedwiecki, Z. Tabor, and K. Rzecki, “Hand body language gesture recognition based on signals from specialized glove and machine learning algorithms,” IEEE Transactions on Industrial Informatics, vol. 12, no. 3, pp. 1104–1113, June 2016.
[10] X. Zhao, A. M. Naguib, and S. Lee, “Kinect based calling gesture recognition for taking order service of elderly care robot,” in The 23rd IEEE International Symposium on Robot and Human Interactive Communication, Aug 2014, pp. 525–530.
[11] D. H. Shin and W.-S. Jang, “Utilization of ubiquitous computing for construction fARg technology,” Automation in Construction, vol. 18, no. 8, pp. 1063 – 1069, 2009. [Online]. Available: http://www.sciencedirect.com/science/article/pii/S0926580509000922
[12] G. Welch and E. Foxlin, “Motion tracking: no silver bullet, but a respectable arsenal,” IEEE Computer Graphics and Applications, vol. 22, no. 6, pp. 24–38, Nov 2002.
[13] S. Zhou, Q. Shan, F. Fei, W. J. Li, C. P. Kwong, P. C. K. Wu, B. Meng, C. K. H. Chan, and J. Y. J. Liou, “Gesture recognition for interactive controllers using mems motion sensors,” in Nano/Micro Engineered and Molecular Systems, 2009. NEMS 2009. 4th IEEE International Conference on, Jan 2009, pp. 935–940.
[14] L. Huan and R. Bo, “Human gesture recognition based on image sequences,” in Control Conference (CCC), 2015 34th Chinese, July 2015, pp. 8388–8392.
[15] Y. Tao, H. Hu, and H. Zhou, “Integration of vision and inertial sensors for 3d arm motion tracking in home-based rehabilitation,” The International Journal
of Robotics Research, vol. 26, no. 6, pp. 607–624, 2007. [Online]. Available: http://ijr.sagepub.com/content/26/6/607.abstract
[16] S. Zhou, F. Fei, G. Zhang, J. D. Mai, Y. Liu, J. Y. J. Liou, and W. J. Li, “2d human gesture tracking and recognition by the fusion of mems inertial and vision sensors,” IEEE Sensors Journal, vol. 14, no. 4, pp. 1160–1170, April 2014.
[17] M. A. Amin and H. Yan, “Sign language finger alphabet recognition from gabor-pca representation of hand gestures,” in 2007 International Conference on Machine Learning and Cybernetics, vol. 4, Aug 2007, pp. 2218–2223.
[18] M. Elmezain, A. Al-Hamadi, S. S. Pathan, and B. Michaelis, “Spatio-temporal feature extraction-based hand gesture recognition for isolated american sign language and arabic numbers,” in Image and Signal Processing and Analysis, 2009. ISPA 2009. Proceedings of 6th International Symposium on, Sept 2009, pp. 254–259.
[19] A. Seniuk and D. Blostein, “Pen acoustic emissions for text and gesture recognition,” in 2009 10th International Conference on Document Analysis and Recognition, July 2009, pp. 872–876.
[20] R. Angeles, “Rfid technologies: Supply-chain applications and implementation issues,” Information Systems Management, vol. 22, no. 1, pp. 51–65, 2005. [Online]. Available: http://dx.doi.org/10.1201/1078/44912.22.1.20051201/85739.7
[21] G. Borriello, W. Brunette, M. Hall, C. Hartung, and C. Tangney, Reminding About Tagged Objects Using Passive RFIDs. Berlin, Heidelberg: Springer Berlin Heidelberg,
2004, pp. 36–53. [Online]. Available: http://dx.doi.org/10.1007/978-3-540-30119-6 3
[22] L. Vlaming, J. Smit, and T. Isenberg, “Presenting using two-handed interaction in open space,” in Horizontal Interactive Human Computer Systems, 2008. TABLETOP 2008. 3rd IEEE International Workshop on, Oct 2008, pp. 29–32.
[23] M. Buettner, R. Prasad, M. Philipose, and D. Wetherall, “Recognizing daily activities with rfid-based sensors,” in Proceedings of the 11th International Conference on Ubiquitous Computing, ser. UbiComp ’09. New York, NY, USA: ACM, 2009, pp. 51–60. [Online]. Available: http://doi.acm.org/10.1145/1620545.1620553
[24] K. P. Fishkin, B. Jiang, M. Philipose, and S. Roy, I Sense a Disturbance in the Force: Unobtrusive Detection of Interactions with RFID-tagged Objects. Berlin, Heidelberg: Springer Berlin Heidelberg, 2004, pp. 268–282. [Online]. Available:
http://dx.doi.org/10.1007/978-3-540-30119-6 16
[25] O. Kubitz, M. O. Berger, M. Perlick, and R. Dumoulin, “Application of radio frequency identification devices to support navigation of autonomous mobile robots,” in Vehicular Technology Conference, 1997, IEEE 47th, vol. 1, May 1997, pp. 126–130 vol.1.
[26] M. Atif, L. Kulik, and E. Tanin, “Autonomous navigation of mobile agents using rfidenabled
space partitions.”
[27] P. Asadzadeh, L. Kulik, and E. Tanin, “Gesture recognition using rfid technology,” Personal and Ubiquitous Computing, vol. 16, no. 3, pp. 225–234, 2012. [Online]. Available: http://dx.doi.org/10.1007/s00779-011-0395-z
[28] C. Hu, M. Li, S. Song, W. Yang, R. Zhang, and M. Q. H. Meng, “A cubic 3-axis magnetic sensor array for wirelessly tracking magnet position and orientation,” IEEE Sensors Journal, vol. 10, no. 5, pp. 903–913, May 2010.
[29] J. S. Wang and F. C. Chuang, “An accelerometer-based digital pen with a trajectory recognition algorithm for handwritten digit and gesture recognition,” IEEE Transactions on Industrial Electronics, vol. 59, no. 7, pp. 2998–3007, July 2012.
[30] S. D. Choi and S. Y. Lee, “3d stroke reconstruction and cursive script recognition with magnetometer-aided inertial measurement unit,” IEEE Transactions on Consumer Electronics, vol. 58, no. 2, pp. 661–669, May 2012.
[31] A. Akl, C. Feng, and S. Valaee, “A novel accelerometer-based gesture recognition system,” IEEE Transactions on Signal Processing, vol. 59, no. 12, pp. 6197–6205, Dec 2011.
[32] J. S. Wang and F. C. Chuang, “An accelerometer-based digital pen with a trajectory recognition algorithm for handwritten digit and gesture recognition,” IEEE Transactions on Industrial Electronics, vol. 59, no. 7, pp. 2998–3007, July 2012.
[33] G. Marqus and K. Basterretxea, “Efficient algorithms for accelerometer-based wearable hand gesture recognition systems,” in Embedded and Ubiquitous Computing (EUC), 2015 IEEE 13th International Conference on, Oct 2015, pp. 132–139.
[34] M. Brown and L. Rabiner, “Dynamic time warping for isolated word recognition based on ordered graph searching techniques,” in Acoustics, Speech, and Signal Processing, IEEE International Conference on ICASSP ’82., vol. 7, May 1982, pp. 1255–1258.
[35] A. Kailas, “Basic human motion tracking using a pair of gyro + accelerometer mems devices,” in e-Health Networking, Applications and Services (Healthcom), 2012 IEEE 14th International Conference on, Oct 2012, pp. 298–302.
[36] “MPU-9250 Product Specification,” InvenSense, Datasheet, Jan. 2014, rev. 1.0. [Online]. Available: http://store.invensense.com/datasheets/invensense/MPU9250REV1.0.pdf.
[37] X. Yun and E. Bachmann, “Design, Implementation, and Experimental Results of a Quaternion-Based Kalman Filter for Human Body Motion Tracking,” IEEE Trans. Robot., vol. 22, no. 6, pp. 1216–1227, Dec. 2006.
[38] R. Zhu and Z. Zhou, “A Real-Time Articulated Human Motion Tracking Using Tri-Axis Inertial/Magnetic Sensors Package,” IEEE Trans. Neural Syst. Rehabil. Eng., vol. 12, no. 2, pp. 295–302, Jun. 2004.
[39] “Accelerometer,” Jul. 2015, page Version ID: 671645806. [Online]. Available: https://en.wikipedia.org/w/index.php title=Accelerometer&oldid=671645806.
[40] R. O’Reilly, K. Harney, and A. Khenkin, “Sonic Nirvana: MEMS Accelerometers as Acoustic Pickups in Musical Instruments,” Jun. 2009.
[Online]. Available: http://www.sensorsmag.com/sensors/acceleration-vibration/
sonic-nirvana-mems-accelerometers-acoustic-pickups-musical-i-5852.
[41] P. Prendergast and B. Kropf, “How to Use Programmable Analog to Measure MEMS Gyroscopes,” Jan. 2007. [Online]. Available: http://www.eetimes.com/document.asp?
doc id=1274559.
[42] “Lorentz force,” Jul. 2015, page Version ID: 671382070. [Online]. Available: https://en.wikipedia.org/w/index.php?title=Lorentz force&oldid=671382070.
[43] W. Storr, “Hall Effect Sensor and How Magnets Make It Works.” [Online]. Available: http://www.electronics-tutorials.ws/electromagnetism/hall-effect.html.
[44] I. Fodor, “A survey of dimension reduction techniques,” Tech. Rep., 2002.
[45] H. T. Hung, “Principal component analysis, pca,” [Online; accessed 04- August-2016]. [Online]. Available: http://120.118.226.200/member/hunght/ł(iem) /principalcomponentanalysis.pdf
[46] “Linear discriminant analysis,” Mar 2014, [Online; accessed 05-August-2016]. [Online]. Available: http://sebastianraschka.com/articles/2014 python lda.html
[47] R. A. Fisher, “The use of multiple measurements in taxonomic problems,” Annals of Eugenics, vol. 7, no. 2, p. 179188, 1936.
[48] C. R. Rao, “The utilization of multiple measurements in problems of biological classification,” Journal of the Royal Statistical Society. Series B (Methodological),
vol. 10, no. 2, pp. 159–203, 1948. [Online]. Available: http://www.jstor.org/stable/2983775
[49] E. Alpaydin, Introduction to machine learning. MIT Press, 2010.
[50] C.-C. Chang and C.-J. Lin, “LIBSVM: A library for support vector machines,” ACM Transactions on Intelligent Systems and Technology, vol. 2, pp. 27:1–27:27, 2011, software available at http://www.csie.ntu.edu.tw/cjlin/libsvm.