跌倒事件在事故傷害類型中佔有很高的比例，其中除了老人族群容易跌倒之外，職場中之跌倒災害也占了多數，可見跌倒偵測不僅在老人族群需要，在職場安全上也逐漸受到重視。本研究提出並實作一動作感知跌倒偵測系統，使用Arduino開發版，搭配三軸加速器放置於足部，分析人類步伐之特性來當作特徵，利用藍牙無線模組傳送至手持式裝置中，將特徵輸入支持向量機以得到步伐狀態，之後再輸入至步伐分析機制求得步伐動作，接著利用學習人類平時足部步伐資訊之隱藏式馬可夫模型來推論出是否發生跌倒事件。與之前研究較不同為能將以往被視為雜訊之足部訊號分析為步伐動作，作為跌倒偵測之依據，且擺脫以往感測器綁全身影響日常行動之系統，不會影響正常生活機能，外出室內皆可配戴。本系統經過實測各種跌倒動作，其總準確率可達96%，能達到跌倒警示之目的。

Fall events cover a large amount of accidental occurrences. These events usually happen to elderly victims and they are also common in occupational hazards. This proves that fall detection is not only required in the elderly population but also in safety of the working public. This research proposes a motion aware fall detection system that uses the Arduino development board with the triple-axis accelerometer placed on the foot area. The device will use different characteristics of the step motion in humans as features to transfer into handheld devices via Bluetooth module. By learning the usual step motion information of users with the Hidden Markov Model to assess whether or not a fall event has occurred. The main difference of this research from previous ones is that normally the part of the feet signal analysis which is seen as noise can be translated to step motion that can be used as the proof of fall detection. The system also uses a simplified set up without constricting the user with multiple sensors which may affect the quality of the user lifestyle to allow ease of usage in indoor and outdoor environments. After actual testing of the system in different types of fall events, the system shows accuracy up to 96% to offer fall detection warning function.

[1] 鍾其祥、白璐、吳秉勳、賴建丞、簡戊鑑 (2010 , 03)。〈臺灣地區跌倒墜落死亡長期趨勢分析〉。中華職業醫學雜誌，17(3)，頁151-162。
[2] 柯運儒 (2013,2)。〈101年度高雄市職業災害統計分析及預防對策〉。高市勞工月刊，24期，頁5。
[3] T. Huan-Wen, C. Mei-Yung, and C. Mei-Yung, “Design of fall detection system with floor pressure and infrared image,” International Conference on System Science and Engineering, pp. 131-135, 2010.
[4] A. K. Bourke, J. V. O’Brien, G. M. Lyons, “Evaluation of a threshold-based tri-axial accelerometer fall detection algorithm,” Gait & Posture, Volume: 26, pp. 194-199, 2007.
[5] Dai, J., Bai, X., Yang, Z., Shen, Z. & Xuan, D., “PerFallD: A pervasive fall detection system using mobile phones,” IEEE International Conference on Pervasive Computing and Communications Workshops(PERCOM Workshops), pp292-297, 2010.
[6] F. Sposaro and G. Tyson, “iFall: An Android Application for Fall Monitoring and Response”, 31st Annual International Conference of the IEEE EMBS, pp. 6119-6122, 2009.
[7] M. N. Nyan, F. E. H. Tay, A. W. Y. Tan, and K. H. W. Seah“Distinguishing Fall Activities from Normal Activities by Angular Rate Characteristics and High-Speed Camera Characterization,” Medical Engineering and Physics, Volume: 28, Issue: 8, pp.842-849, 2006.
[8] 許宏駿，「以個人數位助理(PDA)為基礎之可穿戴式跌倒即時監測系統」，逢甲大學自動控制研究所碩士論文，2004。
[9] 江瑞正，「自適性多感測裝置偕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，2009。
[10] 林琨傑，「基於多感測器下老人跌倒的3D重建系統之設計與實作」，成功大學工程科學研究所碩士論文，2010。
[11] Chieh-Ling Huang, E-Liang Chen, and Pau-Choo Chung, "Fall detection using modular neural networks with back-projected optical flow." Biomedical Engineering: Applications. Basis and Communications Volume: 19, Issue: 6, pp. 415-424, 2007.
[12] S.Y. Chang, C.F. Lai, H.C. Chao, J.H. Park, Y.M. Huang, "An Environmental-Adaptive Fall Detection System on Mobile Device", JOURNAL OF MEDICAL SYSTEMS, Volume: 35, Issue: 5, Special Issue: SI, pp. 1299-1312, Oct. 2011.
[13] C.F. Lai, S.Y. Chang, H.C. Chao and Y.M. Huang*, "Detection of Cognitive Injured Body Region Using Multiple Triaxial Accelerometers for Elderly Falling", IEEE Sensor Journal, Volume: 11, Issue: 3, pp. 763-770, Mar. 2011.
[14]C.F. Lai, Y.M. Huang, J.H. Park and H.C. Chao, "Adaptive Body Posture Analysis Using Collaborative Multi-Sensors for Elderly Falling Detection", IEEE Intelligent Systems, Volume: 25, Issue:2, pp.20-30, Mar. 2010.
[15] C.F. Lai, Y.M. Huang, J.H. Park and H.C. Chao, "Adaptive Body Posture Analysis for Elderly-Falling Detection with Multi Sensors", IEEE Intelligent Systems, Volume: 25, Issue: 2, pp. 20-30, Mar. 2010.
[16] T. Degen, H. Jaeckel, M. Rufer, S. Wyss, “SPEEDY: a fall detector in a wrist watch,” in Proc. Seventh IEEE Int. Symp. on Wearable Computers (ISWC'03), New-York, Oct. 2003, pp. 184-187
[17] “加速度感測器製造技術與原理”,”STMicroelectronic MPD APM Group”, 2007.
[18] "Sonic Nirvana:MEMS Accelerometers as Acoustic Pickups in Musical Instruments",http://www.sensorsmag.com/sensors/article/articleDetail.jsp?id=605887, Retrieved on July 2013.
[19] ”Analog Devices ADXL345 - Three-Axis Digital Accelerometer”,” http://pdf1.alldatasheet.com/datasheet-pdf/view/254714/AD/ADXL345.html”, Retrieved on July 2013.
[20] “微控制器基本內部單元架構” , “http://www.mikroe.com/chapters/view/65/”, Retrieved on July 2013.
[21] ”Summary”,” http://arduino.cc/en/Main/ArduinoBoardFio”, Retrieved on July 2013.
[22] ”藍牙介紹” , ”http://www.bluetooth.com/Pages/Fast-Facts.aspx” Retrieved on July 2013.
[23] ”Bluetooth Bee” , ”http://www.seeedstudio.com/wiki/Bluetooth_Bee” Retrieved on July 2013.
[24] ”Android Application Activity”,” http://developer.android.com/training/basics/activity-lifecycle/starting.html” Retrieved on July 2013.
[25] 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, pp. 1367-1370, 2007.
[26] “人類行走的規律” , ”http://jpkj.tjee.cn/dhydgl/jiexi_5_1_3.asp”, Retrieved on July 2013.
[27] M. Aizerman, E. Braverman, and L. Rozonoer , “Theoretical foundations of the potential function method in pattern recognition learning”, Automation and Remote Control 25: 821-837
[28] J Eisner, ” An interactive spreadsheet for teaching the forward-backward algorithm.” In Proceedings of the ACL Workshop on Effective Tools and Methodologies for Teaching NLP and CL, pp. 10-18, 2002.
[29] A.J. Viterbi, “Error Bounds for Convolutional Codes and an Asymptotically Optimum Decoding Algorithm,” IEEE Transactions on Information Theory, Volume: 13, Issue: 2, pp. 260-269, April 1967.
[30] L. E. Baum, T. Petrie, G. Soules, and N. Weiss, "A maximization technique occurring in the statistical analysis of probabilistic functions of Markov chains", Ann. Math. Statist., Volume: 41, Issue: 1, pp. 164-171, 1970.