臺灣博碩士論文加值系統

乳癌患者在手術完畢後，必須要進行一系列的復健動作，然而病患在家中自行進行復健動作的過程中，常常因為疼痛，或種種因素而使得整個復健動作流程不完整或中斷。本研究透過動作辨識來紀錄病患每天在家中的復健情形將會對醫生在門診時能更快速的了解病人復健狀況，給予病人更有效的復健療程。

本篇論文主要採用人體在進行復健動作過程中的加速度作為訊號來源，利用機器學習(Machine Learning)的方法，針對八種基本的乳癌復健動作進行辨識。本文探討了加速度訊號的重要特徵值，並以隱藏式馬可夫模型(Hidden Markov Model)為理論基礎進行一系列的實驗來驗證其辨識的準確率。實驗結果指出，在使用平均值、能量、頻譜亂度、相關係數當特徵值時所得到的模型可達到98%的準確性。

Rehabilitation exercises after breast cancer surgery can help
prevent post-operation complications. This thesis adopts activity recognition technique to identify and record patients'' rehabilitative exercises. This information helps doctors monitor the patients'' conditions in follow-up visits.

This thesis presents a activity recognition system based on
continuous hidden Markov models. Accelerometers are used to capture the upper body movements when patients do rehabilitation. Four different representative features, mean, energy, entropy, and correlation, are extracted from signals. The recognition rate of exercises is about 98%. The performance of the recognizer is also evaluated in both user dependent and user independent cases.

Acknowledgments ii
Abstract iii
List of Figures viii
Chapter 1 Introduction 1
1.1 Motivation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1
1.2 Problem Definition . . . . . . . . . . . . . . . . . . . . . . . . . . . 3
Chapter 2 RelatedWork 5
2.1 Detection of Ambulatory Mode . . . . . . . . . . . . . . . . . . . . . 6
2.2 ADL Recognition . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7
2.3 Gesture Recognition . . . . . . . . . . . . . . . . . . . . . . . . . . 8
Chapter 3 Experiment Design 9
3.1 Overview . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9
3.2 Accelerometers . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9
3.2.1 Hardware . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10
3.2.2 Placement . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10
3.3 Target Rehabilitation Exercises . . . . . . . . . . . . . . . . . . . . . 14
3.4 Proposed Solution . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14
3.5 Feature Extraction . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15
3.6 Recognition Algorithm . . . . . . . . . . . . . . . . . . . . . . . . . 21
Chapter 4 Experiment and Evaluation 25
4.1 Data Collection . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 25
4.2 Experiment Results . . . . . . . . . . . . . . . . . . . . . . . . . . . 26
Chapter 5 Conclusion 33
Bibliography 35
Appendix A The Breast Cancer Rehabilitation Exercise 37

[1] L. Bao and S. Intille. Activity recognition from user-annotated acceleration data. In
Proceedings of the 2nd International Conference on Pervasive Computing (Pervasive
2004), pages 1–17, 2004.
[2] G. S. Chambers, S. Venkatesh, G. West, and H. Bui. Hierarchical recognition of intentional
human gestures for sports video annotation. In Proceedings of the 16th International
Conference on Pattern Recognition (ICPR 2002), pages 1082–1085, 2002.
[3] G. S. Chambers, S. Venkatesh, G. West, and H. Bui. Segmentation of intentional human
gestures for sports video annotation. In Proceedings of the 10th International Multimedia
Modeling Conference (MMM 2004), pages 124–129, 2004.
[4] E. Farella, M. O’Modhrain, L. Benini, and B. Ricc`o. Gesture signature for ambient
intelligence applications: A feasibility study. In Proceedings of the 4th International
Conference on Pervasive Computing (Pervasive 2006), pages 288–304, 2006.
[5] E. A. Heinz, K. S. Kunze, M. Gruber, D. Bannach, and P. Lukowicz. Using wearable
sensors for real-time recognition tasks in games of martial arts - an initial experiment.
In Proceedings of the 2nd IEEE symposium on Computational Intelligence and Games
(CIG 2006), pages 98–102, 2006.
[6] N. Kern, G. Tr‥oster, B. Schiele, H. Junker, and P. Lukowicz. Wearable sensing to an-notate meeting recordings. In Proceedings of the 6th IEEE International Symposium on
Wearable Computers (ISWC 2002), pages 186–196, 2002.
[7] A. Krause, M. Ihmig, E. Rankin, D. Leong, S. Gupta, D. Siewiorek, A. Smailagic, M.
Deisher, and U. Sengupta. Trading off prediction accuracy and power consumption for
context-aware wearable computing. In Proceedings of the 9th IEEE International Symposium
on Wearable Computers (ISWC 2005), pages 20–26, 2005.
[8] K. Kunze, M. Barry, E. A. Heinz, P. Lukowicz, D. Majoe, and J. Gutknecht. Towards
recognizing tai chi - an initial experiment. In Proceedings of the 3rd International Forum
on Applied Wearable Computing, 2006.
[9] S. Lee and K. Mase. Activity and location recognition using wearable sensors. Pervasive
Computing, IEEE, 1(3):24–32, 2002.
[10] J. M‥antyj‥arvi, J. Himberg, and T. Sepp‥anen. Recognizing human motion with multiple
acceleration sensors. In Proceedings of the IEEE International Conference on Systems,
Man, and Cybernetics, pages 747–752, 2001.
[11] J. K. Perng, B. Fisher, S. Hollar, and K. S. J. Pister. Acceleration sensing glove (asg). In
Proceedings of the 3th IEEE International Symposium on Wearable Computers (ISWC
1999), pages 178–180, 1999.
[12] L. R. Rabiner. A tutorial on hidden markov models and selected applications in speech
recognition. Proceedings of the IEEE, 77(2):257–286, 1989.
[13] C. Randell and H. Muller. Context awareness by analysing accelerometer data. In Proceedings
of the 4th IEEE International Symposium onWearable Computers (ISWC 2000),
pages 175–176, 2000.
[14] K. Van Laerhoven and O. Cakmakci. What shall we teach our pants? In Proceedings
of the 4th IEEE International Symposium on Wearable Computers (ISWC 2000), pages
77–83, 2000.