本研究實做一個重現老人跌倒意外過程姿態的系統。在身上放置多個加速度感測器、陀螺儀裝置與無線模組來偵測跌倒的發生。在到跌倒發生後，利用運動學公式計算人體骨架的運動，於電腦端3D環境中重現跌倒過程姿態。
本研究主要的架構分為二個部分，第一部分為跌倒意外的偵測，人體運動依據個人習慣會呈現群聚性。以加速度感測器資訊求得人體部位的運動軌跡，利用此群聚的特性，以減法聚類法對此軌跡點作群聚處理，來判斷跌倒意外的發生，第二部分為重現老人跌倒過程的姿態，包含建立人體骨架的資料結構、以及如何使用運動學公式來計算人體骨架的運動。

This study explored the reconstruction of elder’s fall-down gesture. Detecting fall-down by placing accelerometers、gyroscopes and RF(Radio frequency) module on the body. When fall-down is detected, using kinematics formula to compute the motion of human skeleton and to reconstruct elder’s fall-down gesture.
Thie study is divided into two parts, The first is detection for fall-down accidents. The human motion will present clustering according to personal habit. Calculate the kinematic locus of body with acceleration sensors. According to the characteristic of clustering, Detecting fall-down accidients by clustering kinematic locus of body by subtractive clustering method.The second is reconstruction of elder’s fall-down gesture, including creating data structure of human skeleton and computing human motion with kinematics formula.

[1] A Sixsmith and N Johnson., "Smart sensor to detect the falls of the elderly". IEEE Pervasive Computing, 3(2):42–47,April-June (2004).
[2] N. Thome, S. Miguet, and S. Ambellouis, "A Real-Time, Multiview Fall Detection System: A LHMM-Based Approach", Circuits and Systems for Video Technology, IEEE Transactions on, vol. 18, pp. 1522-1532, 2008.
[3] W. Chia-Chi, C. Chin-Yen, L. Po-Yen, C. Yi-Chieh, I. T. Kuo, H. Chih-Ning, and C. Chia-Tai, "Development of a Fall Detecting System for the Elderly Residents", in Bioinformatics and Biomedical Engineering, 2008. ICBBE 2008. The 2nd International Conference on, 2008, pp. 1359-1362.
[4] 江瑞正 "自適性多感測裝置協同偵測身體姿態之方法", 國立成功大學工程科學研究所碩士論文, June 2009
[5] "IPhone", http://en.wikipedia.org/wiki/IPhone , Retrieved on July 2010
[6] "Wiimote", http://en.wikipedia.org/wiki/Wiimote, Retrieved on July 2010
[7] "加速度感測器製造技術與原理", "STMicroelectronics MPD APM Group," 2007.
[8] "Sonic Nirvana: MEMS Accelerometers as Acoustic Pickups in Musical Instruments,"http://www.sensorsmag.com/sensors/article/articleDetail.jsp?id=605587, Retrieved on July 2010
[9] "Freescale ZSTAR3 Reference Design Manual," http://www.freescale.com/webapp/sps/site/prod_summary.jsp?code=RD3172MMA7456L , Retrieved on July 2010
[10] "Euler_angles", http://en.wikipedia.org/wiki/Euler_angles, Retrieved on July 2010

[11] "eZ430-RF2500 Development Tool User's Guide", http://focus.ti.com/lit/ug/slau227e/slau227e.pdf Retrieved on July 2010
[12] "Introduction to SimpliciTI", http://focus.ti.com/lit/ml/swru130b/swru130b.pdf Retrieved on July 2010
[13] B. G. Mertzios and G. K. Grigoriadis, "Fast implementation of forward robot kinematics of position with distributed arithmetic architecture," IEEE Trans. Syst., Man, Cybern., to be published.
[14] S. R. BUSS, "Introduction to inverse kinematics with Jacobian transpose, pseudoinverse, and damped least squares methods.", Typeset manuscript, available from http://math.ucsd.edu/~sbuss/ResearchWeb , July 2010.
[15] "Jacobian matrix and determinant", http://en.wikipedia.org/wiki/Jacobian_matrix_and_determinant, Retrieved on July 2010
[16] 張斐章 張麗秋, "類神經網路," 東華出版社, 2003, pp. 269-196.
[17] F. R. Allen, E. Ambikairajah, N. H. Lovell, and B. G. Celler, "Classification of a known sequence of motions and postures from accelerometry data using adapted Gaussian mixture models," Physiol Meas, vol. 27, pp. 935-51, Oct 2006.
[18] Stephen L. Chiu Rockwell Science Center , "Extracting Fuzzy Rules from Data for Function Approximation and Pattern Classification", Chapter 9 in Fuzzy Information Engineering: A Guided Tour of Applications,ed. D. Dubois, H. Prade, and R. Yager, John Wiley & Sons, 1997.
[19] "Human_skeleton", http://en.wikipedia.org/wiki/Human_skeleton Retrieved on July 2010