臺灣博碩士論文加值系統

人們的手指佔據生活的很大一個部分，在生活當中許多動作都需要手指的介入才可以達成。但是在許多產業，尤其是工業當中，許多人都因為機器操作不慎或臨時的機器故障造成手指受到一定程度的傷害，甚至進而需要開刀，本研究目的為透過自製的Arduino數據收集手套，進行正常人與患者之資料收集，並透由分析與機器學習的方式，知悉患者目前手部靈活度狀況與改善情形，可以更適時且數據化的調整患者的復健模式，以達到最佳的復健效果。本研究運用綜觀、時序以及變異係數的分析方式解決不同數據收集手套間由於感測器的個體差異，產生數值差異進而導致無法分析的困境，除此之外，本研究還將類分子神經網路的轉換函數加入了訓練機制，使得各個類別能夠以學習的方式找到最佳解，改善類分子神經網路需要不斷嘗試轉換函數之缺點，使其泛化能力更佳，得以更輕易地運用在各個領域之上。

The use of fingers occupies a large part of people's lives, and many movements in life require the intervention of fingers to achieve. But in many industries, especially in industry, many people have suffered some degree of injury to their fingers due to careless operation of machines or temporary machine failure, and even require surgery. The purpose of this study is to collect data from normal people and patients through a self-made Arduino data collection glove, and to know the current hand mobility status and improvement situation through analysis and machine learning, so that the rehabilitation of patients can be adjusted in timelier and data-oriented manner to achieve the best rehabilitation effect. This study uses the analysis methods of overview, time series and coefficient of variation to solve the dilemma that the analysis cannot be performed due to the individual differences of sensors among different data collection gloves. In addition to the application of Artificial NeuroMolecular System, this study also incorporates a training mechanism for the conversion function, so that each class can find the best solution in learning, improving the shortcomings of Artificial NeuroMolecular System that require constant attempts to convert the function, making them more generalizable and easier to apply to various fields.

摘要 i
Abstract ii
目錄 iii
表目錄 iv
圖目錄 v
第一章　緒論 1
1.1 研究背景及動機 1
1.2 研究目的 2
第二章　文獻探討 3
2.1 手部動作與手指 3
2.2 手指復健相關研究 4
2.3 手部資料收集手套 4
2.4 類分子神經網路 5
第三章　研究方法 8
3.1 研究架構 8
3.2 實驗設備與裝置 8
3.3 資料收集流程 11
3.4 資料分析流程 12
第四章　實驗結果 13
4.1 多個患者資料分析 13
4.1.1 右手 13
4.1.2 左手 14
4.2 單一患者分析 17
4.3 機器學習 - 完成動作當下 19
4.3.1 特徵值設計 19
4.3.2 實驗結果 19
4.4 機器學習 - 以執行動作過程之數值學習 21
4.4.1 特徵值設計 21
4.4.2 實驗結果 22
第五章　結論 23
參考文獻 24
附錄 26
附錄一、右手塑膠手套 26

勞動部職業安全衛生署. (2021). 109年勞動檢查統計年報重點摘要摺頁. Retrieved from https://www.osha.gov.tw/1106/1164/1165/1168/35136/
Chen, J.-C. (1998). Problem solving with a perpetual evolutionary learning architecture. Applied Intelligence, 8(1), 53-71.
Chen, J.-C., & Conrad, M. (1994a). Learning synergy in a multilevel neuronal architecture. BioSystems, 32(2), 111-142.
Chen, J.-C., & Conrad, M. (1994b). A multilevel neuromolecular architecture that uses the extradimensional bypass principle to facilitate evolutionary learning. Physica D: Nonlinear Phenomena, 75(1-3), 417-437.
Cohney, B. C. (1979). Some psychological aspects of hand injuries. In The War Injuries of the Upper Extremity (Vol. 16, pp. 4-6): Karger Publishers.
Fahn, C.-S., & Sun, H. (2005). Development of a data glove with reducing sensors based on magnetic induction. IEEE Transactions on Industrial Electronics, 52(2), 585-594.
Fang, B., Lv, Q., Shan, J., Sun, F., Liu, H., Guo, D., & Zhao, Y. (2019). Dynamic gesture recognition using inertial sensors-based data gloves. Paper presented at the 2019 IEEE 4th International Conference on Advanced Robotics and Mechatronics (ICARM).
Feix, T., Romero, J., Schmiedmayer, H.-B., Dollar, A. M., & Kragic, D. (2015). The grasp taxonomy of human grasp types. IEEE Transactions on human-machine systems, 46(1), 66-77.
Halawani, S. M., & Zaitun, A. (2012). An avatar based translation system from Arabic speech to Arabic sign language for deaf people. International Journal of Information Science and Education, 2(1), 13-20.
Hioki, M., Kawasaki, H., Sakaeda, H., Nishimoto, Y., & Mouri, T. (2010). Finger rehabilitation system using multi-fingered haptic interface robot controlled by surface electromyogram. Paper presented at the 2010 3rd IEEE RAS & EMBS International Conference on Biomedical Robotics and Biomechatronics.
Hoda, M., Hafidh, B., & El Saddik, A. (2015). Haptic glove for finger rehabilitation. Paper presented at the 2015 IEEE International Conference on Multimedia & Expo Workshops (ICMEW).
Jordan, M. I., & Mitchell, T. M. (2015). Machine learning: Trends, perspectives, and prospects. Science, 349(6245), 255-260.
Kim, D. H., Lee, S. W., & Park, H.-S. (2016). Improving kinematic accuracy of soft wearable data gloves by optimizing sensor locations. Sensors, 16(6), 766.
Klapheke, M. M. (1999). Transplantation of the human hand: psychiatric considerations. Bulletin of the Menninger Clinic, 63(2), 159.
Kononenko, I. (2001). Machine learning for medical diagnosis: history, state of the art and perspective. Artificial Intelligence in medicine, 23(1), 89-109.
Mohamaddan, S., & Komeda, T. (2010). Wire-driven mechanism for finger rehabilitation device. Paper presented at the 2010 IEEE International Conference on Mechatronics and Automation.
Polygerinos, P., Lyne, S., Wang, Z., Nicolini, L. F., Mosadegh, B., Whitesides, G. M., & Walsh, C. J. (2013). Towards a soft pneumatic glove for hand rehabilitation. Paper presented at the 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems.
Ray, S. (2019). A quick review of machine learning algorithms. Paper presented at the 2019 International conference on machine learning, big data, cloud and parallel computing (COMITCon).
Sadek, M. I., Mikhael, M. N., & Mansour, H. A. (2017). A new approach for designing a smart glove for Arabic Sign Language Recognition system based on the statistical analysis of the Sign Language. Paper presented at the 2017 34th National Radio Science Conference (NRSC).
Saengsri, S., Niennattrakul, V., & Ratanamahatana, C. A. (2012). TFRS: Thai finger-spelling sign language recognition system. Paper presented at the 2012 second international conference on digital information and communication technology and it's applications (DICTAP).
Sayeed, S., Besar, R., & Kamel, N. S. (2006). Dynamic signature verification using sensor based data glove. Paper presented at the 2006 8th international Conference on Signal Processing.
Shaheen, H., & Mehmood, T. (2018). Talking gloves: Low-cost gesture recognition system for sign language translation. Paper presented at the 2018 IEEE Region Ten Symposium (Tensymp).
Shen, Y., Ong, S., & Nee, A. (2009). Hand rehabilitation based on augmented reality. Paper presented at the Proceedings of the 3rd International Convention on Rehabilitation Engineering & Assistive Technology.