本文藉由觀察一般日常生活中健康人下肢活動方式，提出動作意向偵測之演算法，並且結合主動式輔具輔助脊椎受損病患完成一般日常動作，藉此讓病患重新獲得下半身行動能力。同時，系統藉由輔具感測器訊號並且配合兩組類神經網路建立出偵測異常動作之演算法以達成預防跌倒之警示功能。整套主動式輔具主要利用慣性單元以監測上半身之行動，同時配合放置於腳底和拐杖之薄型壓力感測片偵測使用者的身體重量轉移。感測器之訊號同時會送入已訓練好的類神經網路做判斷與分類。藉此方式，系統便會分離不正常行為出來並且判斷該狀況為危險動作來達到預防跌倒偵測之效果。因此，操作主動式輔具之訊號來源可分成兩類：一.動作意向偵測之結果、二.預防跌倒偵測之結果。最後整合成具備人性、合理且安全之演算法。

[1]新竹脊髓損傷協會網站
[2]H. A. Quintero, R. J. Farris, and M. Goldfarb, “Control and Implementation of a Powered Lower Limb Orthesis to Aid Walking in Paraplegic Individuals,” Rehabilitation Robotics(ICORR) IEEE International Conference, pp.1-6, June 29- July 1, 2011.
[3]黃獻永, 動力下肢輔具之上下樓梯步態分析與控制, 碩士論文,台灣新竹國立清華大學動力機械工程學系, 2012.
[4]T. Hayashi, H. Kawamoto, and Y. Sankai, “Control method of robotic suit HAL working as operator's muscle using biological and dynamical information,” IEEE/RSJ IROS, pp. 3063-3068, 2005.
[5]K. Susuki, Y. Kawamura, T. Hayashi, T. Sakurai, Y. Hasegawa, and Y. Sankai, “Intention-Based Walking Support for Paraplegia Patient with Robot Suit HAL,” Systems, Man and Cybernetics, IEEE International Conference, Vol. 3, pp.2707-2713, 2005.
[6]D. A. Winter, “Human balance and posture control during standing and walking,” Gait and Posture, Vol. 3, No. 4, pp. 193-214, 1995.

[7]N. Noury, A. Fleury, P. Rumeau, A. K. Bourke, G. Ó Laighin, V. Rialle, and J. E. Lundy, “Fall detection Principles and Methods,” International Conference of the IEEE EMBS, pp.1663-1666, 2007.
[8]N. Jia, “Detecting Human Falls with a 3-Axis Digital Accelerometer,” Application Note from Analog Dialogue Analog Device, 2009.
[9]http://www.ncku.edu.tw/~nursedp/hygiene/hygiene_12_02.htm 拐杖使用之步態
[10]H. A. Quintero, R. J. Farris, and M. Goldfarb, “A Method for the Autonomous Control of Lower Limb Exoskeletons for Persons with Paraplegia,” ASME Journal of Medical Devices, Vol.6, Issue 4, 041003(6 pages), 2012.
[11]Chung-Yi Chen, Toward the Study of the Thigh EMG for the Motion Recognition, Master thesis, Department of Power Mechanical Engineering, National TsingHua University, Hsinchu, Taiwan, 2008.
[12]Q. Li, J. A. Stankovic, M. Hanson, A. Barth, and J. Lach, “Accurate, Fast Fall Detection Using Gyroscopes and Accelerometer Derived Posture Information,” 6th Int.Workshop on Wearable and Implantable Body Sensor Networks, Berkeley, pp. 138-143, 2009.
[13]陳協慶, 陳嘉玲, 科技輔具研發-跌倒偵測與警報裝置, 行政院國家科學委員會專題研究計畫成果報告, 2001.

[14]J. Rose, Clinical Gait Analysis Biomechanics & Etiology of Common Walking Disorders, Teaching Material, Department of Orthopaedic Surgery, Stanford University School of Medicine, 2009.
[15]羅華強, 類神經網路—MATLAB的運用, ISBN 986-412-240-1, 2005.07.20.
[16] Simon Haykin, Neural Networks, ISBN 0-13-908385-5, 1999.
[17] http://www.drfoot.com.tw/knowledge.aspx. 足部醫學
[18] http://researcher.nsc.gov.tw/public/jeewm/Data/841716522971.pdf :高齡者動作分析實驗－動作分析、步行時動態足底壓力分析
[19]Cheng-Chih Hsu, On the Design and Implementation of wearable Hybrid Assisted Lower Limb Orthosis, Master thesis, Department of Power Mechanical Engineering, National Tsing Hua University, Hsinchu, Taiwan, 2010.
[20]ADXL335Z data sheet, Analog Device Inc., 2009.
[21]C. J. Fisher, “Using an Accelerometer for Inclination Sensing,” Application Note from Analog Dialogue Analog Device, AN-1057, 2010.
[22]J. R. Gage, “An overview of normal walking,” Instructional Course Lectures, 39,pp.291-303, 1990.
[23]C. A. Downey, Observational Gait Analysis Handbook, Professional Staff Association of Rancho Los Amigos Medical Center, 1989.
[24]J. Perry, “Pathological gait,” Instructional Course Lectures, 39, pp.325-331, 1990.