簡易檢索 / 詳目顯示

回結果列表
研究生： 葉紹威
Yeh, Shao-Wei
論文名稱： 手指外骨骼復健輔具之使用者 意圖智慧預兆與診斷
Diagnosis and Prediction of User Intention for Finger Exoskeleton Rehabilitation Assistive Device
指導教授： 張禎元
Chang, Jen-Yuan
口試委員: 曹哲之
Tsao, Che-Chih
宋震國
Sung, Cheng-Kuo
學位類別： 碩士
Master
系所名稱： 工學院 - 動力機械工程學系
Department of Power Mechanical Engineering
論文出版年： 2017
畢業學年度： 105
語文別： 中文
論文頁數： 88
中文關鍵詞： 復健 、外骨骼 、類神經網路
外文關鍵詞： rehabilitation, exoskeleton, neural-network
相關次數： 點閱：1  下載：0 
分享至:
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報

    • 隨著科技的快速發展，人口高齡化情形越趨嚴重，其中衍生出的身體機能逐漸喪失的狀況，讓復健醫療產業的需求急遽的上升。在此塊產業中，過往需要病患與復健師一對一的指導以及協助，執行復健的流程以及動作，許多需要復健的病患，往往無法在最需要的時刻接受的復健師的診斷，造成病況加劇等現象發生。
    在本論文研究中，針對復健用的外骨骼自動復健輔具作了深入的研究，而於手指末梢之復健外骨骼輔具，觀察到了過往的被動式復健所遇到的醫療上的問題，雖解決了復健師與病患之供給問題，但無法切確的提高病患復健的動機以及潛在康復的效率。依此基礎上，本研究提出了一主動式復健之使用者意圖預測，並期望依此加強未來病患復健之康復效率。
    於本研究中，首先架構了一外骨骼實驗平台，依此蒐集使用者的做動數據，使用了力量感測器記錄下外骨骼鋼線的驅動張力，並依此當作使用者意圖判斷的依據。藉由實驗平台記錄下使用者於機台上的意圖後，運用了人工智慧類神經網路，使用蒐集之數據做訓練以及預測，並在比較四種類神經網路訓練方法後，對使用者意圖之判斷達成了0.9上下的判斷成功率。

    With the rapid growth and technology improvement, the aging of the population is getting more and more serious. The demand of rehabilitation rapidly increase along with the aging population, which caused the lack of human resource in this industry.
    The purpose of the study was to improve the efficiency of finger exoskeleton rehabilitation assistive device. The active rehabilitation methodology was proposed after several literature review. Artificial intelligence neural network was used to predict the intention of user and the process and result will be discussed in the following section.
    The results revealed that success rate of user’s intention reach 0.94976 via Levenberg-Marquardt Backpropagation training method. The study findings may serve as a guide for further research on diagnosis and prediction for user intention.

    第一章 緒論 1 1.1 前言 1 1.2 復健產業的研究背景概況 3 1.2.1 復健外骨骼的發展 5 1.2.2 主動式復健回饋 9 1.3 研究流程與方法 11 第二章 人工智慧類神經網路 13 2.1 前言 13 2.2 文獻回顧 15 2.3 類神經網路的訓練學習 20 第三章 實驗架設 23 3.1 前言 23 3.2 平台架設 24 3.2.1 機構設計&架設 24 3.2.2 馬達選用 26 3.2.3 感測器-Load Cell 力量單元感測器 27 3.2.4 控制核心 29 3.2.5 程式架構 30 第四章 類神經網路訓練 35 4.1 前言 35 4.2 網路模型定義 36 4.3 神經網路架構選擇 38 4.4 類神經網路訓練演算模型 40 4.4.1 Levenberg-Marquardt Backpropagation (LMB) 40 4.4.2 Gradient Descent Backpropagation (GDB) 41 4.4.3 Powell-Beale Conjugate Gradient Backpropagation (PBCGB) 41 4.4.4 BFGS Quasi-Newton Backpropagation (BFGS QNB) 42 第五章 實驗結果與分析 44 5.1 機台重複性驗證 44 5.2 健康手實驗 46 5.2.1 受試者A 48 5.2.2 受試者B 55 5.2.3 受試者C 62 5.3 類神經網路訓練結果 69 5.3.1 訓練資料 69 5.3.2 使用四種不同的訓練方式所得到的最佳成果 69 5.4 平台建置以及受試者量測結論 82 5.5 類神經網路訓練結論 82 第六章 總結 84 6.1 各章結論 84 6.2 本文貢獻 84 6.3 未來展望 85 第七章 參考文獻 86

    1. Kazerooni, H. and R. Steger, The Berkeley Lower Extremity Exoskeleton, in Journal of Dynamic Systems, Measurement, and Control. 2005. p. 12.
    2. Inc., C., CYBERDYNE LETS HAL CYBORGS TAKE A STROLL THROUGH TOKYO. 2009.
    3. Festo. human-machine interaction. 2012; Available from: http://www.festo.com/cms/en_corp/12713.htm.
    4. Awareness, C.f.D. Disability statistics. 2013 [cited 2013; Available from: http://www.disabilitycanhappen.org/chances_disability/disability_stats.asp.
    5. Heller, A., et al., Arm function after stroke: measurement and recovery over the first three months. Journal of Neurology, Neurosurgery, and Psychiatry, 1987. 50: p. 714-719.
    6. Nakayama, H., et al., Recovery of upper extremity function in stroke patients: the Copenhagen Stroke Study. Archives of Physical Medicine and Rehabilitation, 1994. 75(4): p. 394-398.
    7. Sunderland, A., et al., Arm function after stroke. An evaluation of grip strength as a measure of recovery and a prognostic indicator. Journal of Neurology, Neurosurgery, and Psychiatry, 1989. 52(11): p. 1267-1272.
    8. Wade, D.T., et al., The hemiplegic arm after stroke: measurement and recovery. Journal of Neurology, Neurosurgery, and Psychiatry, 1983. 46(6): p. 521-524.
    9. Harwin, W.S., J.L. Patton, and V.R. Edgerton, Challenges and Opportunities for Robot-Mediated Neurorehabilitation. Proceedings of the IEEE, 2006. 94(9): p. 1717-1726.
    10. Patton, J.L. and F.A. Mussa-Ivaldi, Robot-Assisted Adaptive Training: Custom Force Fields for Teaching Movement Patterns. 2004, IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING. p. 636-646.
    11. Mark, V.W. and E. Taub, Constraint-induced movement therapy for chronic stroke hemiparesis and other disabilities. Restorative Neurology and Neuroscience, 2004. 22(3-5): p. 317-336.
    12. Taub, E., et al., Technique to improve chronic motor deficit after stroke. Archives of Physical Medicine and Rehabilitation, 1993. 74(4): p. 347-354.
    13. Harwin, W.S., T. Rahman, and R.A. Foulds, A review of design issues in rehabilitation robotics with reference to North American research. IEEE TRANSACTION ON REHABILTATION ENGINEERING, 1995. 3(1): p. 3-13.
    14. Neuhaus, P.D., et al., Design and evaluation of Mina: A robotic orthosis for paraplegics, in IEEE International Conference on Rehabilitation Robotics 2011: Switzerland,.
    15. Esquenazi, A., et al., The ReWalk Powered Exoskeleton to Restore Ambulatory Function to Individuals with Thoracic-Level Motor-Complete Spinal Cord Injury. American Journal of Physical Medicine & Rehabilitation, 2012. 91(11): p. 911-921.
    16. Zeilig, G. and H. Weingarden, Safety and tolerance of the ReWalk™ exoskeleton suit for ambulation by people with complete spinal cord injury: A pilot study. The Journal of Spinal Cord Medicine 2013. 35(2): p. 96-101.
    17. Kazerooni, H., Exoskeleton for Human Power Augmentation, in IEEE/RSJ International Conference on Intelligent Robot and Systems. 2005: Alberta Canada.
    18. 清大研發穿戴式機器人輔具　助中風患者獲新生. 2016; Available from: http://www.appledaily.com.tw/realtimenews/article/new/20161223/1019529/.
    19. Colombo, R., et al., Design strategies to improve patient motivation during robot-aided rehabilitation, in Journal of NeuroEngineering and Rehabilitation. 2007.
    20. Hogan, N., et al., Motions or muscles? Some behavioral factors underlying robotic assistance of motor recovery. Journal of Rehabilitation Research & Development, 2006. 43(5): p. 605-618.
    21. Banala, S.K., et al., Robot Assisted Gait Training With Active Leg Exoskeleton (ALEX), in IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING. 2009. p. 2-8.
    22. Misha Tsodyks, K. Pawelzik, and H. Markram, Neural Networks with Dynamic Synapses. Neural Computation, 2006. 10(4): p. 821-835.
    23. Hussain, M., Review of the applications of neural networks in chemical process control — simulation and online implementation. Artificial Intelligence in Engineering, 1999. 13(1): p. 55-68.
    24. Ljung, L., System Identification. 1999.
    25. Macmurray, J.C. and D.M. Himmelblau, Modeling and control of a packed distillation column using artificial neural networks. Computers & Chemical Engineering, 1995. 19(10): p. 1077-1088.
    26. Villiers, J.d. and E. Barnard, Backpropagation Neural Nets with One and Two Hidden Layers IEEE TRANSACTIONS ON NEURAL NETWORKS, 1992. 4(1): p. 136-141.
    27. Pu, S.-W. and J.-Y. Chang, Rehabilitation system with stiffness measurement 2016: US.
    28. Pu, S.-W., Research and Development of Human Finger Stiffness Measurement System through Mechatronic Integration of Hand Wearable Robotic Device, in Power Mechanical Engineering Department. 2014, National Tsing Hua University.
    29. SANGER, T.D., Optimal Unsupervised Learning in a Single-Layer Linear Feedforward Neural Network Neural Networks, 1989. 2: p. 459-473.

    QR CODE