請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/55950
完整後設資料紀錄
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.advisor | 王富正(Fu-Cheng Wang) | |
dc.contributor.author | You-Chi Li | en |
dc.contributor.author | 李友棋 | zh_TW |
dc.date.accessioned | 2021-06-16T05:11:29Z | - |
dc.date.available | 2025-07-31 | |
dc.date.copyright | 2020-08-11 | |
dc.date.issued | 2020 | |
dc.date.submitted | 2020-08-03 | |
dc.identifier.citation | [1] World Health Organization. (2018). The top 10 causes of death. Available:https://www.who.int/news-room/fact-sheets/detail/the-top-10-causes-of-death [2] Centers-for-Disease-control-and-prevention. (2017). Stroke Facts. Available: https://www.cdc.gov/stroke/facts.htm [3] Go, A. S., Mozaffarian, D., Roger, V. L., Benjamin, E. J., Berry, J. D., Blaha, M. J., ... Fullerton, H. J. (2014). Executive summary: heart disease and stroke statistics—2014 update: a report from the American Heart Association. Circulation, 129(3), pp.399-410. [4] Hsu M. H. (1996).Outcome of Rehabilitation of stroke patients in recent 10 years. Chinese J Rehabil, 24(1), pp.41-49. [5] K. Bobath and B. Bobath. (1984). The neuro-developmental treatment., Management of the motor disorders of children with cerebral palsy. Clinics in Developmental Medicine, 90, pp.6-18. [6] J. S. Vij and N. K. Multani. (2012). Efficacy of neuro-developmental therapy based gait training in correction of gait pattern of post stroke hemiparetic patients, Journal of Exercise Science and Physiotherapy, 8(1), pp. 30-38. [7] E. Mikołajewska. (2013). The value of the NDT-Bobath method in post-stroke gait training, Advances in Clinical and Experimental Medicine, 22(2), pp. 261-272, [8] Lennon, Sheila; Ashburn, Ann; Baxter, David. (2006).Gait outcome following outpatient physiotherapy based on the Bobath concept in people post stroke, Disability and rehabilitation, 28(13-14), pp.873-881. [9] Pohl, Marcus; Mehrholz, Jan; Ritschel, Claudia; Ruckriem, Stefan. (2002). Speed-dependent treadmill training in ambulatory hemiparetic stroke patients, Stroke , 33(2), pp. 553-558. [10] Visintin, Martha; Barbeau, Hugues; Korner-Bitensky, Nicol; E. Mayo Nancy. (1998). A new approach to retrain gait in stroke patients through body weight support and treadmill stimulation, Stroke ,29(6), pp.1122-1128. [11] Hesse, S.; Bertelt C.; Jahnke, M. T.; Schaffrin, A.; Baake, P.; Malezic, M.; Mauritz, K. H. (1995). Treadmill training with partial body weight support compared with physiotherapy in nonambulatory hemiparetic patients, Stroke, 26(6),pp. 976-981. [12] Lakshya Neuro. (2013, Aug, 17) Body Weight Supported Treadmill training for hemiplegic patient (BWSTT). [13] 原煒, '基於神經發展治療及深度學習之自動化步態訓練機研發,' 碩士論文, 機械工程學研究所, 國立臺灣大學,2019. [14] Fu-Cheng Wang, You-Chi Li, Kai-Lin Wu, Po-Yin Chen and Li-Chen Fu. (2020). Online Gait Detection with an Automatic Mobile Trainer Inspired by Neuro-Developmental Treatment, Sensors, 20(12), pp. 1-21 [15] Díaz, Iñaki; Gil, Jorge Juan; Sánchez, Emilio. (2011). Lower-limb robotic rehabilitation: literature review and challenges, Journal of Robotics [16] Colombo, Gery, Joerg, Matthias, Schreier, Reinhard, Dietz, Volker. (2000). Treadmill training of paraplegic patients using a robotic orthosis, Journal of rehabilitation research and development, 37(6), pp.693-700. [17] Schmidt, Henning, Werner, Cordula; Bernhardt, Rolf, Hesse, Stefan, Kruger, Jorg. (2007). Gait rehabilitation machines based on programmable footplates, Journal of neuroengineering and rehabilitation, 4(2). [18] Patton, James; Brown, David A.; Peshkin, Michael; Santos-Munne, Julio J.; Makhlin, Alex; Lewis, Ela; Colgate, Edward; Schwandt, Doug. (2008). KineAssist: design and development of a robotic overground gait and balance therapy device, Topics in stroke rehabilitation, 15(2), pp. 131-139. [19] Schmitt, C.; and Métrailler, P. (2004). The Motion Maker™: a rehabilitation system combining an orthosis with closed-loop electrical muscle stimulation, 8th Vienna International Workshop on Functional Electrical Stimulation. No. LSRO2-CONF-2006-011. [20] A. Roy, H. I. Krebs, and S. L. Patterson. (2007). Measurement of human ankle stiffness using the anklebot, in Proceedings of the 10th IEEE International Conference on Rehabilitation Robotics, The Netherlands , pp. 356–363. [21] G. L. Gama, M. L. Celestino, J. A. Barela, L. Forrester, J. Whitall, and A. M. Barela. (2017). Effects of Gait Training With Body Weight Support on a Treadmill Versus Overground in Individuals With Stroke,' (in English), Archives of Physical Medicine and Rehabilitation, 98(5), pp. 738-745. [22] K. K. R, Future Directions in Gait Analysis, RRDS Gait Analysis in the Science of Rehabilitation, 4, pp. 85-112. [23] Phoenix-Technologies-Inc. VZ4000. Available: http://www.ptiphoenix.com/products/trackers/VZ4000 [24] VICON. VICON products. Available: https://www.vicon.com/ [25] Aminian, K., Najafi, B., Büla, C., Leyvraz, P.F. and Robert, Ph. (2002). Spatio-temporal parameters of gait measured by an ambulatory system using miniature gyroscopes, Journal of Biomechanics, 35 (5), pp. 689-699. [26] Williamson, R. and Andrews, B.J. (2000). Gait event detection for FES using accelerometers and supervised machine learning. IEEE Transactions on Rehabilitation Engineering, 8 (3), pp. 312-319. [27] Hesse, S., Reiter, F., Jahnke, M., Dawson, M., Sarkodie-Gyan, T. and Mauritz, K.H. (1997). Asymmetry of gait initiation in hemiparetic stroke subjects. Archives of Physical Medicine and Rehabilitation, 78 (7), pp. 719-724. [28] Mazilu, S., Hardegger, M., Zhu, Z., Roggen, D., Tröster, G., Plotnik, M. and Hausdorff, J.M. (2012). Online detection of freezing of gait with smartphones and machine learning techniques. 2012 6th International Conference on Pervasive Computing Technologies for Healthcare (PervasiveHealth) and Workshops, pp. 123-130. [29] Rifton. Rifton Pacer Gait Trainers. Available: https://www.rifton.com/ [30] HAION. Certification. Available: http://www.haioncaster.com/ch/certification/ [31] D. Gouwanda and S. M. N. A. Senanayake. (2008), Emerging Trends of Body-Mounted Sensors in Sports and Human Gait Analysis, 21(1), pp.715-718 [32] Lee, Y.-S., Ho, C.-S., Shih, Y., Chang, S.-Y., Róbert, F.J. and Shiang, T.-Y. (2015). Assessment of walking, running, and jumping movement features by using the inertial measurement unit, Gait and Posture, 41 (4), pp. 877-881. [33] APDM, INC. OPAL USER GUIDE Available:https://www.apdm.com/ [34] 漢馬克驅動科技有限公司. 五相步進馬達及驅動器. Available: http://www.hanmark.com.tw/pro_detail.asp?s_no=8 [35] 漢馬克驅動科技有限公司, MAC5518、MAC5528使用說明書. 2011. [36] Transducer. Mini low profile load cell. Available: https://www.transducertechniques.com/mlp-load-cell.aspx [37] Transducer, DIGITAL PANEL MOUNT METER OPERATOR MANUAL. Transducer Techniques, 2013. [38] Transducer. Smart Digital Panel Mount Load Cell Meter. Available: https://www.transducertechniques.com/dpm-3.aspx [39] Arduino. ARDUINO MEGA 2560. Available: https://store.arduino.cc/usa/arduino-mega-2560-rev3 [40] Atmel, Atmel ATmega640/V-1280/V-1281/V-2560/V-2561/V Data Sheet. 2014. [41] Epomedicine. Physical Examination: Gait. Available: http://epomedicine.com/clinical-medicine/physical-examination-gait/ [42] Hsu, K. L., Gupta, H. V., Sorooshian, S. (1995). Artificial neural network modeling of the rainfall‐runoff process. Water resources research, 31(10), pp. 2517-2530. [43] LeCun, Y., Bengio, Y., Hinton, G. (2015). Deep learning, nature, 521, pp. 436-444 [44] Hecht-Nielsen, R. (1992). Theory of the backpropagation neural network. In Neural networks for perception, Academic Press, pp. 65-93 [45] Schuster, M., Paliwal., K.K., Bidirectional recurrent neural networks(1997) ,IEEE Transactions on Signal Processing, 45 (11), pp. 2673-2681. [46] Chung Junyoung, Gulcehre Caglar, Cho KyungHyun, and Bengio Yoshua. Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv preprint arXiv:1412.3555, 2014. [47] Hochreiter, S. and Schmidhuber, J. (1997). Long Short-Term Memory. Neural Computation, 9 (8), pp. 1735-1780 [48] Christopher Olah. Understanding LSTM Networks. Available: https://colah.github.io/posts/2015-08-Understanding-LSTMs/ [49] K. Aminian. (2002). Spatio-temporal parameters of gait measured by an ambulatory system using miniature gyroscopes, Journal of Biomechanics,35 (5), pp.689-699. [50] J. R. Rebula, L. V. Ojeda, P. G. Adamczyk, and A. D. Kuo. (2013), Measurement of foot placement and its variability with inertial sensors, Gait Posture, 38(4), pp. 974-80. [51] X. Yun, J. Calusdian, E. R. Bachmann, and R. B. McGhee.(2012) ,Estimation of Human Foot Motion During Normal Walking Using Inertial and Magnetic Sensor Measurements, IEEE Transactions on Instrumentation and Measurement, 61(7), pp. 2059-2072. [52] J. R. Rebula, L. V. Ojeda, P. G. Adamczyk, and A. D. Kuo. (2013). Measurement of foot placement and its variability with inertial sensors, Gait Posture, 38(4), pp. 974-80. [53] De Boer, P.T., Kroese, D.P., Mannor, S. and Rubinstein, R.Y. (2005). A tutorial on the cross-entropy method. Annals of Operations Research, 13 (1), pp. 19-67. [54] Tieleman, T. and Hinton, G. (2012). Lecture 6.5—RmsProp: Divide the gradient by a running average of its recent magnitude. COURSERA: Neural Networks for Machine Learning. [55] Duchi, J., Hazan, E. and Singer, Y. (2011). Adaptive subgradient methods for online learning and stochastic optimization. Journal of Machine Learning Research, 12 (Jul), pp. 2121-2159. [56] Trojaniello, D., Cereatti, A. and Della Croce, U. (2014). Accuracy, sensitivity and robustness of five different methods for the estimation of gait temporal parameters using a single inertial sensor mounted on the lower trunk. Gait and Posture, 40 (4), pp. 487-492 [57] Kohavi, R. (1995, August). A study of cross-validation and bootstrap for accuracy estimation and model selection. In Ijcai ,14(2), pp. 1137-1145. [58] Li, M., Zhang, T., Chen, Y., Smola, A. J. (2014, August). Efficient mini-batch training for stochastic optimization. In Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining (pp. 661-670). ACM. [59] Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R. (2014). Dropout: a simple way to prevent neural networks from overfitting. The Journal of Machine Learning Research, 15(1), 1929-1958. [60] 台大人體試驗委員會(Institutional Review Board; IRB), Available: https://www.ntuh.gov.tw/NCTRC/training/training.aspx [61] Stewart, J. D. (2008). Foot drop: where, why and what to do?. Practical neurology, 8(3), pp. 158-169. [62] Kerrigan, D. C., Frates, E. P., Rogan, S., Riley, P. O. (2000). Hip hiking and circumduction: quantitative definitions. American journal of physical medicine rehabilitation, 79(3), pp. 247-252. [63] Morris, M. E., Matyas, T. A., Bach, T. M., Goldie, P. A. (1992). Electrogoniometric feedback: its effect on genu recurvatum in stroke. Archives of Physical Medicine and Rehabilitation, 73(12), pp. 1147-1154. [64] Brigham, E. Oran. The fast Fourier transform and its applications. No. 517.443. Prentice Hall, 1988. [65] Chen, George; Patten, Carolynn; Kothari, Dhara H.; Zajac, Felix E. (2005). Gait differences between individuals with post-stroke hemiparesis and non-disabled controls at matched speeds, Gait posture, 22(1), pp. 51-56. [66] Bo Wei Liang., Wen Hua Wu. et al. Pelvic step: The contribution of horizontal pelvis rotation to step length in young healthy adults walking on a treadmill, Gait posture, 39(1), pp.105-110. [67] Khan, Mohd Ehmer; Khan, Farmeena. (2012). A comparative study of white box, black box and grey box testing techniques. International Journal of Advanced Computer Science and Applications (IJACSA); 3(6), pp. 12–15 [68] Doyle, John; Francis, Bruce; Tannenbaum, Allen. Tannenbaum.(1990). Feedback control theory.' Macmillan [69] Zhou, Kemin; Doyle, John Comstock. Essentials of robust control. Prentice Hall International 1998. [70] Glover, Keith; McFarlane, Duncan. (1989). Robust stabilization of normalized coprime factor plant descriptions with H∞-bounded uncertainty, IEEE transactions on Automatic Control, 34(8), pp. 821–830. [71] McFarlane, Duncan; Glover, Keith. (1992). A loop-shaping design procedure using H∞ synthesis, IEEE transactions on Automatic Control, 37(6), pp. 759–769. [72] Wang, Fu-Cheng; Chen, Lien-Sheng; Tsai, Yan-Chen; Hsieh, Chin-Hui; Yen, Jia-Yush. (2014). Robust loop-shaping control for a nano-positioning stage. Journal of Vibration and Control, 20(6), pp. 885-900. [73] D. Mungas. (1991). Iii-office mental status testing: A practical guide, Geriatrics, 46(7). [74] Saebo. The Brunnstrom Stages of Stroke Recovery. Available: https://www.saebo.com/the-stages-of-stroke-recovery/ [75] H. MK, G. KM, and M. MR. (1986). Gait assessment for neurologically impaired patients. Standards for outcome assessment, Physical therapy, 66(10), [76] C. Werner, S. von Frankenberg, T. Treig, M. Konrad, and S. Hesse. (2002). Treadmill Training With Partial Body Weight Support and an Electromechanical Gait Trainer for Restoration of Gait in Subacute Stroke Patients: A Randomized Crossover Study, Stroke, 33(12), pp. 2895-2901. | |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/55950 | - |
dc.description.abstract | 本論文主要針對中風患者行走能力的復健,接續先前開發的移動式神經發展治療(Neuro Developmental Treatment;NDT)步態訓練系統,並透過深度學習的方式發展一套步態偵測系統。治療手法上設計了一套可以提升受測者腰部旋轉幅度的訓練方法,並以臨床實驗驗證其效果。 NDT步態訓練整合了各種支撐、誘發、引導、與抑制等手法,是相當有效的中風復健方式,然而對於治療師而言,傳統的NDT治療方式往往相當耗時、費力,無法給予患者大量的治療復健,而且僅能在特定之空間範圍內進行復健,故本實驗室在過去開發了一套移動式自動化NDT步態訓練機,用來降低治療師的工作負擔並同時增加患者的復健訓練時間,以提升NDT步態訓練之效果。本論文延續移動式NDT步態訓練機架構,開發一套步態偵測系統及一套可以提升腰部旋轉的訓練方式。 首先,本論文提出了一套穿戴式步態偵測系統,運用深度學習即時偵測特定的步態相位,作為系統介入時機點的依據。其次,根據先前研究結果顯示,自動化NDT步態訓練機對增進縱向擺動期對稱性的效果顯著,但是在腰部旋轉角度的表現上則不如治療師之訓練,因此本論文進一步分析治療師之施力手法與腰部轉角之關係,並提出了一套可以增進腰部轉角表現的控制流程,並將其與移動式NDT步態訓練機整合,提升NDT步態訓練系統的性能。本論文運用系統識別的方式來建立數學模型,接著針對此系統模型設計控制器。最後則以擬中風受測者的NDT步態訓練,驗證所提出的訓練方法可以有效提升受測者的訓練效果。 | zh_TW |
dc.description.abstract | This thesis proposes a gait detection method that can identify specific gait features in real-time and develops a training method that can help improve their pelvic rotation during neural development treatment(NDT) rehabilitation. NDT is an effective rehabilitation method for stroke patients, because it can let patients have the feeling on walking with minimal physical intervention. However, it is very labor-intensive and time-consuming for therapists. Consequently, patients usually cannot receive sufficient training because of the shortage of therapist assistance. Therefore, we developed a movable automatic gait trainer to relief therapists’ working load and increase patients’ training time in previous research. This thesis extends the work by proposing an online gait detection algorithm and developing a new training method to improve the user’s pelvic rotation The first contribution of this thesis is the development of a gait detection system. Gait detection and analyses are importance in clinical applications because they can help speeding up diagnosis and applying suitable treatments. In NDT rehabilitation, we need to identify specific gait events to trigger corresponding physical intervention. However, the identification of gait events for stroke patients might be difficult because of the influences of diseases. Therefore, we develop a gait detection system that can correctly identify the gait features in real-time. First, we apply a wearable device to receive subjects’ gait information. Second, we propose a recurrent neural network to build a gait detection system that can automatically extract gait features. Last, we integrate this system with the movable NDT gait trainer to conduct real-time gait detection for triggering rehabilitation intervention. The second contribution of this thesis is the development of an intervention method to improve the user’s pelvic rotation during NDT rehabilitation. Previous studies showed that the NDT trainer was effective in improving the symmetry of swing phases, but the amplitude of pelvic rotation was not improved when comparing with the therapist guiding. Therefore, we propose a new training method to improve the pelvic rotation. First, we record the therapist’s actions and the test subject’s motions during the training. Then we translate the clinical know-how to build an expert dataset and propose an effective method to improve the pelvic rotation. Second, we apply identification techniques to derive the transfer function of the motor systems and design robust controllers to cope with disturbances and noises during gait training. Last, we recruit fourteen subjects to conduct NDT gait training to verify the proposed method. Based on the results, the proposed method is deemed effective in improving of swing phases and the pelvic rotation simultaneously during NDT rehabilitation. | en |
dc.description.provenance | Made available in DSpace on 2021-06-16T05:11:29Z (GMT). No. of bitstreams: 1 U0001-2807202014580300.pdf: 8144404 bytes, checksum: 2d7504872042e049d7018430de210b35 (MD5) Previous issue date: 2020 | en |
dc.description.tableofcontents | 致謝 I 摘要 III ABSTRACT V 目錄 VII 圖目錄 XI 表目錄 XVII 符號 XIX 縮寫 XXIII 第一章 序論 1 1.1 前言 1 1.2 研究動機與方法 2 1.3 文獻回顧 4 1.4 論文架構 7 第二章 移動式自動化NDT步態訓練機 9 2.1 步態訓練機系統架構 9 2.2 步態訓練機硬體架構 10 2.3 穿戴式步態偵測系統之硬體元件 13 2.4 馬達拉繩系統之硬體元件 15 2.4.1 馬達與驅動器 15 2.4.2 拉繩機構設計 17 2.4.3 力量感測器 18 2.4.4 微處理器 20 2.5 安全系統設計 21 第三章 步態偵測系統 23 3.1 研究目的與背景 23 3.2 深度學習與模型架構 24 3.2.1 深度學習介紹 24 3.2.2 遞迴神經網路 26 3.3 步態偵測系統之建立 28 3.3.1 步態偵測系統之架構 28 3.3.2 訓練資料集之蒐集與建立 29 3.3.3 步態偵測模型 31 3.4 模型訓練與測試結果 35 3.4.1 模型訓練 35 3.4.2 模型訓練結果與討論 37 第四章 治療師專家系統 43 4.1 治療師專家系統之轉譯 43 4.2 效能指標介紹與分析 46 4.3 腰部旋轉幅度訓練方法 50 4.4 硬體實現控制流程 55 第五章 馬達控制系統 57 5.1 系統識別方法與介紹 57 5.2 馬達拉繩機構之系統識別 58 5.3 控制器設計 62 5.3.1 PI控制器設計 64 5.3.2 實際訓練測試與比較 69 5.4 強韌控制器設計 71 5.4.1 強韌控制設計理論 71 5.4.2 強韌控制設計 85 5.4.3 實際訓練測試與比較 89 第六章 移動式NDT步態訓練機臨床測試 93 6.1 臨床測試介紹 93 6.1.1 受測者收案條件 93 6.1.2 臨床測試流程 95 6.1.3 受測者基本資料 101 6.2 測試結果分析 103 6.2.1 中風患者NDT步態訓練實驗 103 6.2.2 擬中風自動化NDT訓練實驗 103 第七章 結論與未來展望 107 7.1 結論 107 7.2 未來展望 108 參考文獻 109 附錄A、中風受測者之自動化NDT步態訓練實驗結果 117 附錄B、IRB同意書 121 附錄C、受測者知情同意書 123 附錄D、擬中風自動化NDT訓練實驗結果 125 附錄E、口試委員之問題與回答 135 | |
dc.language.iso | zh-TW | |
dc.title | 基於神經發展治療及深度學習之移動式自動化步態訓練機研發 | zh_TW |
dc.title | The Development of a Movable Automatic Gait Rehabilitation Device based on Neuro-Developmental Treatment and Deep Learning | en |
dc.type | Thesis | |
dc.date.schoolyear | 108-2 | |
dc.description.degree | 碩士 | |
dc.contributor.oralexamcommittee | 顏家鈺(Jia-Yush Yen),蔡明祺(Mi-Ching Tsai),林靜嫻(Chin-Hsien Lin) | |
dc.subject.keyword | 深度學習,神經發展治療,步態訓練,中風,強韌控制,馬達控制, | zh_TW |
dc.subject.keyword | deep learning,recurrent neural network,NDT,gait training,stroke,robust control,motor control, | en |
dc.relation.page | 139 | |
dc.identifier.doi | 10.6342/NTU202001968 | |
dc.rights.note | 有償授權 | |
dc.date.accepted | 2020-08-03 | |
dc.contributor.author-college | 工學院 | zh_TW |
dc.contributor.author-dept | 機械工程學研究所 | zh_TW |
顯示於系所單位: | 機械工程學系 |
文件中的檔案:
檔案 | 大小 | 格式 | |
---|---|---|---|
U0001-2807202014580300.pdf 目前未授權公開取用 | 7.95 MB | Adobe PDF |
系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。