研究生: |
廖書賢 Shu-Hsien Liao |
---|---|
論文名稱: |
透過分類演算法建構動作分析與風險評估系統 Building a Rapid Motion Analysis and Risk Assessment System by Adopting Classification Algorithm |
指導教授: |
林久翔
Chiuhsiang Joe Lin |
口試委員: |
江行全
Bernard C. Jiang 梁曉帆 Sheau-Farn Liang |
學位類別: |
碩士 Master |
系所名稱: |
管理學院 - 工業管理系 Department of Industrial Management |
論文出版年: | 2018 |
畢業學年度: | 106 |
語文別: | 中文 |
論文頁數: | 82 |
中文關鍵詞: | 光學影像擷取系統 、穿戴式動作捕捉系統 、分類式演算法 、隨機森林演算法 、倒傳遞類神經網路 |
外文關鍵詞: | Optitrack Motion Capture System, XSENS, Classification Algorithm, Random Forest, Back Propagation Neural Network |
相關次數: | 點閱:264 下載:2 |
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 |
台灣每年的職業災害案例卻逐漸上升,其中有關不當動作導致職災比例也逐年升高,因此發展一套快速動作分析風險評估系統能為讓勞工們降低因為不當動作導致的肌肉骨骼傷害,而本研究透過光學影像擷取系統(Optitrack Motion Capture System, OMCS)和穿戴式動作捕捉系統(Xsens)設計了三組實驗,分別是基礎動作實驗、抬舉作業實驗和前推作業實驗,將OMCS收集到的座標資料分為連續型的角度和離散型的RULA分數輸入到演算法中進行學習建模,在把Xsens的資料透過此模型得到預測值跟實際值做比較,雖然有些誤差以呈現學習失效的結果,但還是有很多結果是在可接受範圍甚至是表現非常優異的,本研究透過演算法結合Xsens和OMCS這兩種系統是能建立出一套快速動作分析系統的。
Cases of occupational injury are increasing in recent years in Taiwan, and proportion of bad postures of occupational injury increase simultaneously. Therefore developing a rapid motion analyze and risk assessment system can mitigate WMSDs from bad postures of workers. This study designed basic movement, lifting work and pushing work three types of experiments by adopting both OMCS and Xsens. This study transformed data of OMCS into two types, continuous data and discrete data, getting predicted values by inputting both types of data in classification algorithm to comparing with actual value. Though there are a little unacceptable errors, however, some of the results performed very well. According to those better results, combining Xsens, OMCS and classification algorithm can build a rapid motion analyze system indeed.
Alwasel, A., Abdel-Rahman, E. M., Haas, C. T., & Lee, S. (2017). Experience, productivity, and musculoskeletal injury among masonry workers. Journal of Construction Engineering and management, 143(6), 05017003.
Alwasel, A., Sabet, A., Nahangi, M., Haas, C. T., & Abdel-Rahman, E. (2017). Identifying poses of safe and productive masons using machine learning. Automation in Construction, 84, 345-355.
Battini, D., Persona, A., & Sgarbossa, F. (2014). Innovative real-time system to integrate ergonomic evaluations into warehouse design and management. Computers & Industrial Engineering, 77, 1-10.
Breiman, L. (2001). Random forests. Machine learning, 45(1), 5-32.
Chen, F.-C. (1989). Back-propagation neural network for nonlinear self-tuning adaptive control. Paper presented at the Intelligent Control, 1989. Proceedings., IEEE International Symposium on.
Dempsey, P. G., McGorry, R. W., & Maynard, W. S. (2005). A survey of tools and methods used by certified professional ergonomists. Applied Ergonomics, 36(4), 489-503.
Goh, A. T. (1995). Back-propagation neural networks for modeling complex systems. Artificial Intelligence in Engineering, 9(3), 143-151.
Hecht-Nielsen, R. (1992). Theory of the backpropagation neural network Neural networks for perception (pp. 65-93): Elsevier.
Jung, E. S., & Park, S. (1994). Prediction of human reach posture using a neural network for ergonomic man models. Computers & Industrial Engineering, 27(1-4), 369-372.
Kim, S., & Nussbaum, M. A. (2013). Performance evaluation of a wearable inertial motion capture system for capturing physical exposures during manual material handling tasks. Ergonomics, 56(2), 314-326.
Leardini, A., Benedetti, M., Berti, L., Bettinelli, D., Nativo, R., & Giannini, S. (2007). Rear-foot, mid-foot and fore-foot motion during the stance phase of gait. Gait & posture, 25(3), 453-462.
Leardini, A., Biagi, F., Merlo, A., Belvedere, C., & Benedetti, M. G. (2011). Multi-segment trunk kinematics during locomotion and elementary exercises. Clinical Biomechanics, 26(6), 562-571.
Leardini, A., Sawacha, Z., Paolini, G., Ingrosso, S., Nativo, R., & Benedetti, M. G. (2007). A new anatomically based protocol for gait analysis in children. Gait & posture, 26(4), 560-571.
Liaw, A., & Wiener, M. (2002). Classification and regression by randomForest. R news, 2(3), 18-22.
Lin, H.-F., Hsu, C.-H., & Wang, M.-J. J. (2007). An application of data mining technique in engineering to facilitate production management of garments. Paper presented at the proceedings of the 11th WSEAS international conference on computers, Agios Nikolaos, Crete Island, Greece.
McAtamney, L., & Corlett, E. N. (1993). RULA: a survey method for the investigation of work-related upper limb disorders. Applied Ergonomics, 24(2), 91-99.
Pal, M. (2005). Random forest classifier for remote sensing classification. International Journal of Remote Sensing, 26(1), 217-222.
Portinaro, N., Leardini, A., Panou, A., Monzani, V., & Caravaggi, P. (2014). Modifying the Rizzoli foot model to improve the diagnosis of pes-planus: application to kinematics of feet in teenagers. Journal of foot and ankle research, 7(1), 57.
Robertson, G., Caldwell, G., Hamill, J., Kamen, G., & Whittlesey, S. (2013). Research methods in biomechanics, 2E: Human Kinetics.
Roetenberg, D., Luinge, H., & Slycke, P. (2009). Xsens MVN: full 6DOF human motion tracking using miniature inertial sensors. Xsens Motion Technologies BV, Tech. Rep, 1.
Rumelhart, D. E., & McClelland, J. L. (1986). Parallel distributed processing: explorations in the microstructure of cognition. volume 1. foundations.
Tee, K. S., Low, E., Saim, H., Zakaria, W. N. W., Khialdin, S. B. M., Isa, H., . . . Soon, C. F. (2017). A study on the ergonomic assessment in the workplace. Paper presented at the AIP Conference Proceedings.
Wang, D., Dai, F., & Ning, X. (2015). Risk assessment of work-related musculoskeletal disorders in construction: State-of-the-art review. Journal of Construction Engineering and management, 141(6), 04015008.
Werbos, P. (1974). Beyond Regression:" New Tools for Prediction and Analysis in the Behavioral Sciences. Ph. D. dissertation, Harvard University.
XSENS. (2016). XSENS Motion Tracker Wireless Awinda User Manual.
勞動部. (2018). 勞動統計月報.