臺灣博碩士論文加值系統

透過生物感測元件在醫療領域的應用，人體動作分析與行為感知技術已成為醫療與健康照護之發展趨勢。為了提供學生良好的體育學習環境，台灣各大學對於身障生以及因意外傷害致行動不便的學生皆有加開特殊體育課程，訂定訓練計畫以提供正確有效的運動方式與內容，並檢視其訓練成效。本研究核心為一即時腹直肌訓練測量評估系統之研製，利用無線感測技術，針對腹直肌訓練器材佈建感測元件，收集學生在訓練中肌肉施力的詳細數據，透過程式開發工具做整理和分析，即時反映給同學供檢視訓練動作是否正確，而老師除了在現場指導同學動作外，亦可根據量化資料，檢測和分析學生的腹直肌訓練成效。
本研究目標為:(1)運用無線感測技術，測量與收集訓練詳細數據(2)訓練數據正確性分析，即時回饋(3)結合資料探勘，進行決策樹分析。本研究的技術核心，除依據體育老師所訂定之動作標準予以系統化，使訓練狀況達到自動化監測功能外，著重在即時性測量運動狀態下的腹直肌施力狀況，評估人體的運動姿勢狀態與施力正確度，並結合資料庫以追蹤每位受訓者各階段訓練紀錄，設計出客觀的腹直肌訓練測量系統，再利用圖型的使用者介面設計，使測量系統具有能夠自我診斷功能與友善的人機介面，根據所收集到的使用者復健數據，進行資料探勘，以決策樹演算法分析影響復健成效之關鍵因子，回饋供體育老師規劃訓練課程與未來受訓者使用。

Through the application of biological sensor in the medical field, human motion analysis and behavior-aware technology has become the development trend of medical and health care. In order to provide students with a good sports learning environment for accident and disabilities college students in Taiwan universities, arranged special sport lessons, set an effective training program to provide the correct movement pattern and content, and view their training effectiveness.
The core of this research is to develop a real-time rectus training evaluated system The key elements of this study are threefold: (1) Use wireless sensor technology, to measure and collect detailed training data. (2) Analyze training data, real-time feedback (3) Data mining, decision tree analysis. Focusing on the real-time measurement of the rectus abdominis training, design graphical user interface, so that training can be self- diagnostic. Based on the collected training data, use decision tree algorithm to analyze the impact the effectiveness of training key factors. Contribute to the future training.

目錄
第一章 緒論 1
1.1研究背景 1
1.2研究動機與目的 3
1.3論文架構 6
第二章 相關研究 7
2.1校園常見腹部及背部運動傷害 7
2.1.1脊椎側彎治療 9
2.1.2椎間盤突出治療 9
2.2復健訓練簡介 10
2.3腹直肌訓練(RAMT) 14
2.4資料探勘 15
2.5決策樹演算法 19
2.5.1常見的決策樹演算法 20
2.5.2 C4.5決策樹演算法之定義 23
第三章 研究方法 29
3.1研究流程 30
3.2系統架構 30
3.3腹直肌無線感測 32
3.4動作分析 34
3.4.1姿勢追蹤 34
3.4.1.1姿勢追蹤─背部 35
3.4.1.2姿勢追蹤─臀部 35
3.4.1.3姿勢追蹤─判斷 36
3.4.2肌力追蹤 37
3.4.2.1訓練動作肌力分析 37
3.4.2.2肌力追蹤─腹直肌 39
3.4.2.3肌力追蹤─手臂 39
3.4.2.4肌力正確性判斷與分數計算 40
3.4.3下壓角度追蹤 41
3.4.4肌耐力追蹤 42
3.5知識探勘 43
3.5.1知識探勘介紹 43
3.5.2復健成效檢測方法 45
3.5.3復健分析目標 46
3.5.4復健分析流程 47
3.5.5復健原始資料 48
3.5.6選擇復健關鍵因子 49
3.5.7資料預處理與轉換 50
3.5.8復健成效決策樹分析 51
第四章 實作結果與分析 53
4.1腹直肌無線感測 54
4.1.1腹直肌無線感測模組架構 54
4.1.2腹直肌無線感測模組實體畫面 55
4.1.3行動裝置即時回饋畫面 57
4.2動作分析 58
4.2.1姿勢追蹤狀況─背部 58
4.2.2姿勢追蹤狀況─臀部 60
4.2.3肌力追蹤狀況 63
4.2.4下壓角度追蹤狀況 68
4.2.5肌耐力追蹤狀況 68
4.3知識探勘 70
4.3.1復健詳細數據實例 71
4.3.2復健成效檢測實例 71
4.3.3決策樹模型分析與探討 72
第五章 結論與未來方向 76
5.1結論 76
5.2未來方向 77
參考文獻 78
附錄一 羅蘭-摩里斯腹背部生活障礙問卷─RMDQ 81
附錄二 歐式腹背部生活障礙量表─ODI 84
附錄三 英文論文 88

圖目錄
圖1.1美國加州柏克萊大學所研發的智慧灰塵(smart dust) 2
圖2.1 ICF概述 11
圖2.2 ICF各要素間的交互作用 11
圖2.3腹直肌圖示 14
圖2.4腹直肌訓練動作圖解 15
圖2.5決策樹模組 20
圖2.6訊息熵值變化 26
圖2.7性別屬性作為決策樹節點 28
圖2.8購買房車決策樹模組 28
圖3.1系統架構圖 31
圖3.2腹直肌訓練示意圖 33
圖3.3訓練器材之壓力感測器佈建圖 34
圖3.4使用者之肌電感測器佈建圖 37
圖3.5預期正確施力之肌電訊號圖 38
圖3.6施力不合標準之肌電訊號圖 38
圖3.7腹直肌肌電感測器佈建圖 39
圖3.8肱二頭肌肌電感測器佈建圖 39
圖3.9角加速度計佈建圖 41
圖3.10知識探勘流程 43
圖3.11復健分類群組示意圖 46
圖3.12復健分析流程圖 48
圖3.13決策樹分析流程 52
圖4.1研究流程圖 53
圖4.2腹直肌無線感測模組架構圖 54
圖4.3微控制器與藍芽模組實體畫面 55
圖4.4壓力感測器實體畫面 56
圖4.5肌電感測器與角加速度計實體畫面 56
圖4.6行動裝置即時回饋畫面 57
圖4.7背部姿勢正確壓力訊號圖表 59
圖4.8背部姿勢錯誤-上背部離開器材 59
圖4.9背部姿勢錯誤-下背部離開器材 60
圖4.10臀部姿勢正確壓力訊號圖表 61
圖4.11臀部姿勢錯誤-重心偏右 62
圖4.12臀部姿勢錯誤-重心偏左 63
圖4.13體育老師示範肌力正確圖表 64
圖4.14同學訓練肌力正確圖表 65
圖4.15肌力運用錯誤-腹直肌力不足 66
圖4.16肌力運用錯誤-使用手臂肌力 66
圖4.17同學常見訓練狀況-運用腹直肌力也借助手臂肌力 67
圖4.18腹直肌訓練下壓角度紀錄 68
圖4.19肌耐力紀錄-階段性達成訓練目標 69
圖4.20肌耐力紀錄-不穩定的訓練表現 69
圖4.21全部同學肌耐力紀錄 70
圖4.22決策樹模型─所有因子 73
圖4.23決策樹模型─控制訓練重量 73
圖4.24決策樹模型─控制訓練重量與肌力分數 74

表目錄
表2.1常見腹部及背部運動傷害一覽表 8
表2.2常見復健治療方法 13
表2.3常見決策樹演算法之比較 21
表2.4觀察家庭是否購買房車的相關資料 25
表3.1姿勢正確性判斷 36
表3.2肌力正確性判斷 40
表3.3原廠角度計算公式 42
表3.4適應體育腰背部受傷學生資料 49
表3.5復健關鍵因子 50
表3.6資料預處理與轉換後範例 51
表4.1腹直肌無線感測模組硬體規格 55
表4.2適應體育腰背部受傷學生訓練數據 71
表4.3適應體育腰背部受傷學生復健成效檢測 71
表4.4決策樹分析資料 72
表4.5決策樹特徵分析規則 75

[1]"Technology Review," http://www.technologyreview.com, 2014.
[2]"Smart Dust," http://robotics.eecs.berkeley.edu/~pister/SmartDust/, 2001.
[3]"Market Research," http://www.linkedin.com/company/transparency-market-research, 2013.
[4]N. Hogan, H.J. Krebs, B. Rohrer, J.J. Palazzolo, L. Dipietro, S.E. Fasoli, J. Stein, R. Hughes, W.R. Frontera, D. Lynch and B.T. Volpe "Motions or muscles? Some behavioral factors undel-Iying robotic ass istance of motor recovery, " Journal of Rehabilitation Research & Development, vol. 43, no. 5, pp. 605-618, August 2006.
[5]C.G. Burgar, P.S. Lum, P.C. Shor and H.F. Machiel Van der Loos, "Development of robots for rehabilitation therapy: the Palo Alto VA/Stanford experience," Journal of Rehabilitation Research & Development, vol. 37, no. 6, pp. 663-673, November 2000.
[6]松本守雄, 高橋洋平 and 小倉洋二, "Genome wide association study for adolescent idiopathic scoliosis," 整形・災害外科, vol. 57, no. 3, pp. 295-299, March 2014.
[7]Yosuke Oishi, Masaaki Murase and Yoshiyuki Okada, "Clinical Results of Operations for Degenerative Lumbar Scoliosis with Lumbar Spinal Stenosis with at Least Three Years Follow-up Including an Analysis of Poor Outcome Patients," 日本脊椎脊髄病學會 英文原著號, vol. 5, no. 2, pp. 98-105, February 2014.
[8]World Health Organization, " International Classification of Functioning, Disability and Health, " World Health Organization, 2001.
[9]"中華民國復健醫學發展協會," http://www.rmdaroc.org.
[10]Daisuke Tomita and Kaegemoto Yuasa, "Muscle activity levels during daily physical activity : Muscular activity while walking with baggage,"中京大學體育學論叢, vol. 45, no.1, pp. 29-34, 2003.
[11]"山姆伯伯工作坊," http://www.unclesam.cc/blog/,2014.
[12]Daisuke Tomita and Kaegemoto Yuasa, "Characteristic of isometric contraction from muscle activity levels,"中京大學體育學論叢, vol. 45, no.1, pp. 23-27, 2003.
[13]Tohru Handa, Hiroto Kato, Shin Hasegawa, Junichi Okada and Kiyotada Kato, "Electromyographic investigation of the upper and lower rectus abdominis, external abdominal oblique, and rectus femoris muscles in seven traditional abdominal exercises," 日本體育學會體育學研究, vol. 54, no. 1, pp. 43-54, June 2009.
[14]Hidenori Akaha, Keiichi Mochizuki, Masato Takahashi, Shinsei Osaki and Taro Tanaka, "Analysis of the Trunk Muscle Activities While Raising the Hand in All Fours using EMG and Manual Muscle Testing," The Journal of Japanese Physical Therapy Association, vol. 30, no. 7, pp.407-414, 2003.
[15]"Prector力量健身設備使用手冊," Precor - Premium Home and Commercial Fitness Equipment, 2010.
[16]M. J. A. Berry and G. Linoff, "Data Mining Techniques: for Marking, Sales, and Customer Support," New York: John Wiley & Sons Inc, 1997.
[17]尹相志, "Microsoft SQL Server 2005資料採礦聖經," 學貫出版社, 2007.
[18]"決策樹," http://www.twwiki.com/wiki/決策樹.
[19]Jocelyne Fayn, "A Classification Tree Approach for Cardiac Ischemia Detection Using Spatiotemporal Information From Three Standard ECG Leads," IEEE Transactions on Biomedical Engineering, vol. 58, no. 1, pp. 95-102, January 2011.
[20]Junghwan Cho, Xiaopeng Li, Zhiyong Gu, and Pradeep U. Kurup, "Recognition of Explosive Precursors Using Nanowire Sensor Array and Decision Tree Learning," IEEE Sensors Journal, vol. 12, no. 7, pp.2384-2391, July 2012.
[21]Guleng Sheri and David Corne, "Learning-Assisted Evolutionary Search for Scalable Function Optimization: LEM(ID3)," IEEE Congress on Evolutionary Computation, pp.1-8, July 2010.
[22]Leszek Rutkowski, Lena Pietruczuk, Piotr Duda, and Maciej Jaworski, "Decision Trees for Mining Data Streams Based on the McDiarmid’s Bound," IEEE Transactions on Knowledge and Data Engineering, vol. 25, no. 6, pp.1272-1279, June 2013.
[23]Timo Horeis and Bernhard Sick, "Collaborative Knowledge Discovery & Data Mining: From Knowledge to Experience," Proceedings of the 2007 IEEE Symposium on Computational Intelligence and Data Mining(CIDM 2007), pp.421-428, 2007.
[24]C4.5 Decision Tree Implementation, "http://www.otnira.com/2013/03/25/c4-5/," 2013.