本論文主旨在於開發基於性感測器之人體姿態分析系統，透過觀察身體角度的連續變化，應用於阿茲海默式症之徵狀評估。首先，本論文設計了single-task、dual-task、Time Up and Go Test三種動作測驗，並且透過穿戴式慣性感測器配置於受測者的腰部中心、雙腳腳背上，藉此取得受測者的動作訊號。接著，本論文提出一種基於支持向量機之阿茲海默氏症患者動作評估演算法，將擷取的動作訊號進行前處理，並基於Mahony的互補式濾波器計算尤拉角，同時使用梯度轉換擷取動作特徵，依據動作特徵的性質建立九種分類器，透過投票機制給予動作表現評分，藉此評估阿茲海默氏症與正常人在動作表現上的差異以及參考指標，並且結合協同過濾(Collaborative Filtering)的方式建構彈性調整的評估架構。最後經結果顯示，本論文提出的方法在辨認阿茲海默氏症患者與正常人之間在動作表現上可達到82.22%的準確率，並且在加入帕金森氏症患者時也與正常人在動作表上有78.2%的準確率，透過以上實驗結果可以驗證本論文提出方法之有效性。期望本論文提出的系統架構可以有效幫助醫護人員在臨床診斷時作為一個評估工具，將繁瑣的工作自動化減輕臨床診斷時的負擔。

The purpose of the thesis is use inertial sensors to collect the movement signal and calculated the participants’ body angle. Then, the thesis use the Euler angle algorithm for Alzheimer’s disease(AD) subjects to classification. First, the thesis designed a series of dynamic procedures to determine subjects’ balance ability. The dynamic procedures will asked the subjects wore the inertial sensors on waist and toe. Second, the thesis designed the consultation system for Alzheimer's disease based on inertial sensor including signal preprocessing, Euler angle, feature extraction, feature normalization, and support vector machine-based classifier to separate AD patients from healthy people. And then, we design two movement grading mechanism to patient’s behave. One is multiple classifiers voting, and the other is collaborative filtering. Finally, the results showed that the optimal accuracy was closed to 82.22 percent for classifier to separate Alzheimer’s disease patients and healthy participants. We expect the proposed the consultation system for Alzheimer's disease may help the medical care practitioners to reduce the burden.

[1] World Health Organization, “Global Age-friendly Cities: A Guide”, ISBN 978-92 4-154730-7, 2007.

[2] 白明奇。《失智症船歌》。健康世界出版社。2009年。

[3] 《記憶終結者，阿茲海默氏症》，財團法人全民健康基金會 http://www.twhealth.org.tw/index.php?option=com_zoo&task=item&item_id=459&Itemid=21.

[4] B. R. Greene and R. A. Kenny, “Assessment of cognitive decline through quantitative analysis of the Timed Up and Go Test,” IEEE Trans. Biomedical Engineering, vol. 59, no. 4, pp. 988-995, 2012.

[5] Blankevoort CG1, van Heuvelen MJ, Scherder EJ, "Reliability of Six Physical Performance Tests in Older People With Dementia", American Physical Therapy Association, vol. 93, no. 1, pp. 69-78, 2013

[6] K. Berg, S. Wood-Dauphinėe, J. I. Williams, and D. Gayton, “Measuring balance in the elderly: Preliminary development of an instrument,” Physiotherapy Canada, vol. 41, no. 6, pp. 304-311, 1989.

[7] M.Tinetti, T. Williams, and R. Mayewski, “Fall risk index for elderly patients based on number of chronic disabilities,” The American Journal of Medicine, vol. 80, no. 3, pp. 429-434, 1986.

[8] D. Maquet, F. Lekeu, E. Warzee, S. Gillain, V. Wojtasik, E. Salmon, J. Petermans, and J. L. Croisier, “Gait analysis in elderly adult patients with mild cognitive impairment and patients with mild Alzheimer’s disease: simple versus dual task: a preliminary report,” Clinical Physiology and Functional Imaging, vol. 30, no. 1, pp. 51-56, 2010.

[9] P. L. Sheridan, J. Solomont, N. Kowall, and J. M. Hausdorff, “Influence of executive function on locomotor function: Divided attention increases gait variability in Alzheimer's disease,” Journal of the American Geriatrics Society, vol. 51, no. 11, pp. 1633-1637, 2003.

[10] D. M. Gavrila, “The visual analysis of human movement: A survey,” Computer Vision and Image Under-standing, vol. 73, no. 1, pp. 82–98, 1999.

[11] R. Romdhane, E. Mulin, A. Derreumeaux, N. Zouba, J. Piano, L. Lee, I. Leroi, P. Mallea, R. David, M. Thonnat, F. Bremond, and P. H. Robert, “Automatic video monitoring system for assessment of Alzheimer’s disease symptoms,” Journal of Nutrition Health and Aging, vol. 16, no. 3, pp. 213-218, 2012.

[12] M. F. Gago, V. Fernandes, J.Ferreira, H. Silva, L. Rocha, E. Bicho, and N. Sousa, “Postural stability analysis with inertial measurement units in Alzheimer's disease,” Dementia and Geriatric Cognitive Disorders Extra: Dement Geriatr Cogn Disord Extra, vol. 4, no. 1, pp. 22-30, 2014.

[13] Janet M. T. Van Uem, Stefan Walgaard, Erik Ainsworth, Sandra E. Hasmann, Tanja Heger, Susanne Nussbaum, Markus A. Hobert, Encarnación M. Micó-Amigo, Rob C. Van Lummel, Daniela Berg, Walter Maetzler, "Quantitative Timed-Up-and-Go Parameters in Relation to Cognitive Parameters and Health-Related Quality of Life in Mild-to-Moderate Parkinson's Disease," PLOS one, 2016

[14] H. Rouhani, J. Favre, X. Crevoisier, K. Aminian, "Ambulatory measurement of ankle kinetics for clinical applications, " Journal of Biomechanics, vol. 44, pp. 2712-2718, 2011.

[15] I. Tien, S. D.Glaser, R. Bajcsy, D. S.Goodin, M. J. Aminoff, "Results of Using a Wireless Inertial Measuring System to Quantify Gait Motions in Control Subjects," IEEE Trans Biomed, vol.14, pp. 904-915, 2010.

[16] M. F. Gago, V. Fernandes, J.Ferreira, H. Silva, L. Rocha, E. Bicho, and N. Sousa, “Postural stability analysis with inertial measurement units in Alzheimer's disease,” Dementia and Geriatric Cognitive Disorders Extra: Dement Geriatr Cogn Disord Extra, vol. 4, no. 1, pp. 22-30, 2014.

[17] A. Avci, S. Bosch, M. Marin-Perianu, R. Marin-Perianu, and P. J. M. Havinga. "Activity recognition using inertial sensing for healthcare, wellbeing and sports applications: A survey," Architecture of Computing Systems, vol. 10, pp. 167–176, 2010.

[18] A. Krause, D. Siewiorek, A. Smailagic, J. Farringdon, "Unsupervised, dynamic identification of physiological and activity context in wearable computing," Wearable Computers, 2003. Proceedings. Seventh IEEE International Symposium on, pp. 88-97, 2003

[19] U. Maurer, A. Smailagic, D. Siewiorek, M. Deisher, "Activity recognition and monitoring using multiple sensors on different body positions," BSN, vol. 06, pp. 112-116, 2006

[20] D. Karantonis, M. Narayanan, M. Mathie, N. Lovell, B. Celler, "Implementation of a real-time human movement classifier using a triaxial accelerometer for ambulatory monitoring," IEEE Transactions on Information Technology in Biomedicine, vol. 10, no. 1, pp. 156–167, 2006.

[21] G. Bieber and C. Peter, "Using physical activity for user behavior analysis," PETRA, vol. 08, pp. 1-6, 2008.

[22] J. Rueterbories, E. G. Spaich, B. Larsen, O. K. Andersen, "Methods for gait event detection and analysis in ambulatory systems," Medical Engineering & Physics, vol 32, pp. 545-552, 2010.

[23] P. Harrington, “Machine Learning in Action,” Oreilly & Associates Inc, 2012.

[24] J. Lester, T. Choudhury, and G. Borriello, "A Practical Approach to Recognizing Physical Activities," Pervasive Comp, pp. 1–16, 2006

[25] C. Mattman, O. Amft, H. Harms, G. Troster, F. Clemens, "Recognizing upper body postures using textile strain sensors," ISWC, , pp. 29–36, 2007.

[26] U. Maurer, A. Smailagic, D. Siewiorek, M. Deisher, "Activity recognition and monitoring using multiple sensors on different body positions," Proceedings of the International Workshop on Wearable and Implantable Body Sensor Networks, pp. 99–102, 2006.

[27] J. Yang, J. Wang, and Y. Chen, "Using acceleration measurements for activity recognition: An effective learning algorithm for constructing neural classifiers," Pattern Recognition Letters, vol. 29, no. 16, pp. 2213–2220, 2008.

[28] F. Pedregosa et al., “Scikit-learn: Machine Learning in Python ,” Journal of Machine Learning Research, vol. 12, pp. 2825–2830, 2011.

[29] Lounesto, Pertti, “Clifford algebras and spinors. Cambridge: Cambridge University Press ,” ISBN 978-0-521-00551-7, 2001.

[30] R. Mahony, T. Hamel and Jean-Michel Pflimlin, “Nonlinear Complementary Filters on the Special Orthogonal Group,” IEEE Transactions on Automatic Control, vol. 53, pp. 1203-1218, 2008.

[31] J. S. Wang, Y. L. Hsu, and J. N. Liu, “An inertial-measurement-unit-based pen with a trajectory reconstruction algorithm and its applications,” IEEE Trans. Industrial Electronics, vol. 57, no. 10, pp. 3508-3521, 2010.

[32] W. T. Fong, S. K. Ong, and A. Y. C. Nee, “Methods for in-field user calibration of an inertial measurement unit without external equipment,” Measurement Science and Technology, vol. 19, no. 8, pp. 1-11, 2008.

[33] P. Lounesto, “Clifford Algebras and Spinors (Cambridge University Press, Cambridge, England), see Chaps. 11 and 12 of the second edition, 2002.

[34] M. Euston, P. Coote, R. Mahony, J. Kim, T. Hamel, “A Complementary Filter for Attitude Estimation of a Fixed-Wing UAV,” Proceedings of IROS IEEE/RSJ International Conference on Intelligent Robots and Systems, 2008.

[35] V. Vapnik, Statistical Learning Theory, Wiley, New York, 1998.

[36] B. Sarwar, G. Karypis, J. Konstan, J. Riedl. “Item-Based collaborative filtering recommendation algorithms,” In: Proceedings of the 10th International World Wide Web Conference, pp.285~295, 2001.

[37] J. Benesty, J. Chen, Y. Huang, I. Cohen, “Pearson correlation coefficient,” Noise reduction in speech processing, vol. 2. Springer Topics in Signal Processing, p.p. 1–4, 2009.
[38] C. F. Crispim-Junior, V. Joumier, Y. L. Hsu, M. C. Pai, P. C. Chung, A. Dechamps, P. Robert, and F. Bremond, “Alzheimer’s patient activity assessment using different sensors,” Gerontechnology, vol. 11, no. 2, pp. 266-267, 2012.
[39] Chien-WenLin, “Inertial-Sensor-Based Balance Analysis System for Patients with Alzheimer’s Disease, “ 2012.
[40] 白明奇，2001，早期阿茲海默氏症病患之認路能力研究，國立中正大學.