本研究主要利用多個三軸加速度感測器協同偵測身體行為模式與意外跌倒事件的發生，用分佈在身體各個部份的感測器提供的資訊配合無線傳輸裝置傳回電腦分析判斷，再利用自我學習機制自動調整辨識條件以符合個人化需求，其目標是為了識別目前身體的行為狀態，並在跌倒意外發生時發出警告，在跌倒意外發生後，還能提供意外事件發生當時身體的姿態、重要部位是否受到撞擊等等，提供更多的資訊給予醫療人員做更精準的判斷。因為受到地心引力的影響，物體都會存在一個向地表的重力加速度g，這是一個永遠存在而且是不太會有變化相當具有參考價值的參數，人類的姿勢受到重力影響下，身體中的每個肢體受力方向皆有所不同，例如坐的時候腿部與軀幹受重力的方向都會不同，在運動行為中每個肢體因為施力不同所受到的加速度也有所不同，我們便利用這些特性來進行多個三軸加速度感測器協同偵測之研究；從研究結果顯示出我們提出的方式可以達到相當高的正確率，而自適性機制讓我們可以依照個人習慣不同來調整判斷條件，在跌到意外發生時還可以提供相關訊息給予醫療人員做急救之參考。

This study explored the collaborative detection of body behavior modes and accidental falling incidents by using multiple tri-axis acceleration sensors. Information is provided by sensors distributed over the body that transmit positions, by radio transmission devices to a computer, in order to analyze and recognize current body behavior status, which create a warning when a falling accident happens. After a falling accident occurs, more information of the sudden incident, such as body posture and impact of crucial position, can be provided to medical personnel for more accurate diagnosis. As affected by gravity, every object has a gravitational acceleration, g, toward the ground. This is a permanent and often fixed parameter with remarkable reference value. Under gravity, direction of force on each limb of the body varies. For example, when sitting, the legs and body are subjected to gravity of various directions. Each limb bears different accelerations due to different forces of motion behaviors. These characteristics are utilized to study the collaborative detection of multiple tri-axis acceleration sensors. When a falling accident occurs, injury of the first position impacted is usually the maximal, especially with head or spinal cord injuries. Thus, it is important to detect body posture of the fall and crucial position impact to provide relevant data to medical personnel for rescue and treatment. However, this topic is seldom discussed. Past studies have suggested that, using single tri-axis acceleration sensors have limitations of information deficiency, and fail to provide correct information of falling posture and impact position. Therefore, this study proposed a method that can provide enough data to recognize falling information. To identify a behavior incident or detect a falling incident, using multiple sensors can provide various conditions to judge the incident collaboratively.

[1] " 九十八年第四週內政統計通報(97 年底人口結構分析)," http://www.moi.gov.tw/stat/, 1.January.2009.
[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] H. Foroughi, A. Naseri, A. Saberi, and H. S. Yazdi, "An eigenspace-based approach for human fall detection using Integrated Time Motion Image and Neural Network," in Signal Processing, 2008. ICSP 2008. 9th International Conference on, 2008, pp. 1499-1503.
[4] D. M. Karantonis, M. R. Narayanan, M. Mathie, N. H. Lovell, and B. G. Celler, "Implementation of a real-time human movement classifier using a triaxial accelerometer for ambulatory monitoring," Information Technology in Biomedicine, IEEE Transactions on, vol. 10, pp. 156-167, 2006.
[5] M. Kangas, A. Konttila, P. Lindgren, I. Winblad, and T. Jamsa, "Comparison of low-complexity fall detection algorithms for body attached accelerometers," Gait Posture, vol. 28, pp. 285-91, Aug 2008.
[6] N. Noury, A. Fleury, P. Rumeau, A. K. Bourke, G. O. Laighin, V. Rialle, and J. E. Lundy, "Fall detection--principles and methods," Conf Proc IEEE Eng Med Biol Soc, vol. 2007, pp. 1663-6, 2007.
[7] 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.
[8] Z. Tong, W. Jue, L. Ping , and H. Jing, "Fall Detection by Embedding an Accelerometer in Cellphone and Using KFD Algorithm," IJCSNS - International Journal of Computer Science and Network Security, vol. 6, pp. 277-284, Oct 2006.
[9] P. H. Veltink, HansB J. Bussmann, W. de Vries, WimL J. Martens, and
R. C. Van Lummel, "Detection of static and dynamic activities using uniaxial accelerometers," Rehabilitation Engineering, IEEE Transactions on, vol. 4, pp. 375-385, 1996.
[10] " 維基百科 Wii," http://zh.wikipedia.org/w/index.php?title=Wii&variant=zh-tw, 1.July.2009.
[11] "加速度感測器製造技術與原理", "STMicroelectronics MPD APM
Group," 2007.
[12] "Sonic Nirvana: MEMS Accelerometers as Acoustic Pickups in Musical Instruments," http://www.sensorsmag.com/sensors/article/articleDetail.jsp?id=60558 7, 1.July.2009.
[13] " 電子時報：MEMS 微機電感測器的多元化應用," http://www.digitimes.com.tw/tw/dt/n/shwnws.asp?CnlID=7&id=00000 85077_A7H6I5LQDG8LUZZ6AADWJ&ct=1&OneNewsPage=1&PA GE=4, 1.July.2009.
[14] IEEE, "IEEE Std 802.15.4™-2003,IEEE Standard for Information technology—Telecommunications and information exchange between systems—Local and metropolitan area networks—Specific requirements Part 15.4: Wireless Medium AccessControl (MAC) and Physical Layer (PHY) Specifications for Low-Rate Wireless Personal Area Networks (LR-WPANs)."
[15] "Freescale ZSTAR3 Reference Design Manual," http://www.freescale.com/webapp/sps/site/prod_summary.jsp?code=R D3172MMA7456L, 1.July.2009.
[16] "Simple Media Access Controller (SMAC) User's Guide," http://www.freescale.com/files/rf_if/doc/user_guide/SMACRM.pdf?fsr ch=1, 1.July.2009.
[17] "AN3461, Tilt Sensing Using Linear Accelerometers " http://www.freescale.com/files/sensors/doc/app_note/AN3461.pdf?WT _TYPE=Application%20Notes&WT_VENDOR=FREESCALE&WT_ FILE_FORMAT=pdf&WT_ASSET=Documentation, 1.July.2009.
[18] M. Kangas, A. Konttila, I. Winblad, and T. Jamsa, "Determination of simple thresholds for accelerometry-based parameters for fall detection," in Engineering in Medicine and Biology Society, 2007. EMBS 2007. 29th Annual International Conference of the IEEE, 2007, pp. 1367-1370.
[19] M. J. Mathie, N. H. Lovell, A. C. F. Coster, and B. G. Celler, "Determining activity using a triaxial accelerometer," in [Engineering in Medicine and Biology, 2002. 24th Annual Conference and the Annual Fall Meeting of the Biomedical Engineering Society] EMBS/BMES Conference, 2002. Proceedings of the Second Joint, 2002, pp. 2481-2482 vol.3.
[20] 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.
[21] A. K. Bourke, J. V. O'Brien, and G. M. Lyons, "Evaluation of a threshold-based tri-axial accelerometer fall detection algorithm," Gait Posture, vol. 26, pp. 194-9, Jul 2007.
[22] L. Suhuai and H. Qingmao, "A dynamic motion pattern analysis approach to fall detection," in Biomedical Circuits and Systems, 2004 IEEE International Workshop on, 2004, pp. 1-5-8a.
[23] 張斐章 張麗秋, "類神經網路," 東華出版社, 2003, pp. 269-196.