瞭解人們如何維持穩定度為預防及預測跌倒可能性的重要關鍵。過去研究將姿態穩定性作為區分跌倒者與非跌倒者的評估及決策因素。然而，對於非跌倒者是如何維持活動之穩定性仍然不清楚。因此，本研究採用具有經濟效益及可辨識人體活動之加速規，作為主要評估動態姿態穩定性之設備。本研究實驗分為兩部分：首先藉由實驗進行以獲得加速規數據之最佳特徵值，而實驗二則為建立姿態穩定性指標。本研究由第一次實驗中之結果顯示，平均值、標準差、最大值、最小值以及能量，作為特徵值為最適當的。然而，多尺度熵(MSE) 所得之結果優於上述之傳統特徵值。最後，使用MSE中的IMF3，可將穩定性指標區分為穩定性步行、非穩定性步走及跌倒

Understand how humans maintain stability is the key to prevent and predict the likelihood of falls. Past studies evaluated and determined the postural stability to distinguish non-fallers from fallers. However, how stable the movement of non-fallers remain unclear. This study used accelerometers as the main device to evaluate the dynamic postural stability because of its economic benefit and its ability to recognize human physical activity. Two sets of experiments were conducted: first experiment was done to obtain the optimum feature to evaluate acceleration data, while the second experiment was done to develop the postural stability index. The optimum features obtained from the first experiment are mean, standard deviation, maximum, minimum, and energy. However, the multiscale entropy (MSE) performed better than the traditional features mentioned above. The stability index to distinguish balanced walking, unbalanced walking, and falling is developed using the MSE value of IMF3 divided by the total MSE value of all IMFs.

1. Akhavian, R., Behzadan, A.H. (2015). Construction equipment activity recognition for simulation input modeling using mobile sensors and machine learning classifiers. Advanced Engineering Informatics, 29, 867-877.
2. Al-Shanoon, A.A.S., Ahmad, S.A., Hassan, M.K. (2015). Slip detection with accelerometer and tactile sensors in a robotic hand model. IOP Conference Series: Materials Science and Engineering, 99, 012001.
3. Asokan, A., Pothen, A.J. (2016). ARMatron – A wearable gesture recognition glove for control of robotic devices in disaster management and human rehabilitation. International Conference on Robotics and Automation for Humanitarian Applications, Tamilnadu, India, 18-20 December.
4. Aung, M., Thies, S., Kenney, L., Howard, D., Selles, R., Findlow, A., Goulermas, J. (2013). Automated detection of instantaneous gait events using time frequency analysis and manifold embedding. IEEE Transactions of Neural System Rehabilitation Engineering, 21, 908–916.
5. Babic, J., Karcnik, T., Bajd, T. (2001). Stability analysis of four point walking. Gait and Posture, 14, 56-60.
6. Bachmann, H., Anmann, W. (1987). Vibrations in structures induced by man and machines. International Association for Bridge and Structural Engineering, IABSE – AIPC – IVBH, Zurich, Switzerland.
7. Bachmann, H. (1995). Vibration problems in structures, practical guidelines, 1st edition. Basel, Switzerland: Birkhauser Verlag.
8. Baltich, J., von Tscharner, V., Zandiyeh, P., Nigg, B.M. (2014). Quantification and reliability of center of pressure movement during balance tasks of varying difficulty. Gait and Posture, 40, 327–332.
9. Bao, L., Intille, S.S. (2004). Activity recognition from user-annotated acceleration data. Proceedings of the Second International Conference on Pervasive Computing, 23, 1-17.
10. Benocci, M., Bachlin, M., Farella, E., Roggen, D., Benini, L., Troster, G. (2010). Wearable assistant for load monitoring: Recognition of on-Body load placement from gait alterations. Proceedings of the Fourth International Conference on Pervasive Computing Technologies for Healthcare, Munich, Germany, 22-25 March. doi:10.4108/ICST. PERVASIVEHEALTH2010.8894.
11. Bloem, B.R. (1992). Postural instability in Parkinson’s disease. Clinical Neurology and Neurosurgery, 94 (Suppl.), S41–S45.
12. Brownlee, J. (2016). K-Nearest neighbors for machine learning. Retrieved June 15, 2016, from https://machinelearningmastery.com/k-nearest-neighbors-for-machine-learning/
13. Bourke, A.K., Culhanne, K.M., O’brien, J.V., Lyons, G.M. (2007). Evaluation of a threshold-based tri-axial accelerometer fall detection algorithm. Gait and Posture, 26, 194-199.
14. Cech, D.J., Martin, S.T. (2002). Functional movement development across the lifespan. Philadelphia, PA: Elsevier.
15. Chen, C., Grennan, K., Badner, J., Zhang, D., Gershon, E., Jin, L.; et al. (2011). Removing match effects in analysis of expression microarray data: An evaluation of six batch adjustment methods. PLoS ONE, 6(2), e17238.
16. Cleland, I., Kikhia, B., Nugent, C., Boytsov, A., Hallberg, J., Synnes, K., McClean, S., Finlay, D. (2013). Optimal placement of accelerometers for the detection of everyday activities. Sensors, 13, 9183-91200.
17. Costa, M. Goldberger, A.L., Peng, C.K. (2002). Multiscale entropy analysis of complex physiologic time series. Physical Review Letters, 89, 06812.
18. Costa, M. Goldberger, A.L., Peng, C.K. (2005). Multiscale entropy analysis of biological signals. Physical Review A, E71, 021906.
19. Cortes, C., Vapnik, V. (1995). Support-vector networks. Machine Learning, 20(3), 273–297.
20. Cui, X., Peng, C.K., Costa, M.D., Weiss, A., Goldberger, A.L., Hausdorff, J.M. (2014). Development of a new approach to quantifying stepping stability using ensemble empirical mode decomposition. Gait and Posture, 39, 495-500.
21. Curtze, C., Hof, A.L., Postema, K., Queen, B. (2010). Over rough and smooth: Amputee gait on an irregular surface. Gait and Posture, 33, 292-296.
22. Dai, J., Bai, X., Yang, Z., Shen, Z., Xuan, D. (2010). Mobile phone-based pervasive fall detection. Personal and Ubiquitous Computing, 14, 633-43.
23. Dargie, W. (2009). Analysis of time and frequency domain features of accelerometer measurements. Proceedings of 18th International Conference on Computer Communications and Networks, 3-6 August, 1-6. doi:10.1109/ICCCN.2009.5235366.
24. Dernbach,S., Das, B., Khrisnan, N.C., Thomas, B.L., Cook, D.J. (2012). Simple and complex activity recognition through smart phones. Proceedings of the 8th International Conference on Intelligent Environments, Guanajuato, Mexico, 26-29 June, 214-221.
25. Dimeas, F., Aspragathos, N. (2016). Online stability in human-robot cooperation with admittance control. IEEE Transactions on Haptics, 9(2), 267-278.
26. Dingwell, J.B., Cusumano, J.P. (2010). Re-interpreting detrended fluctuation analyses of stride-to-stride of variability in human walking. Gait and Posture, 32(3), 348-353.
27. Dobkin, B.H., Xu, X., Batalin, M., Thomas, S., Kaiser, W. (2011). Reliability and validity of bilateral ankle accelerometer algorithms for activity recognition and walking speed after stroke. Stroke, 42, 2246-2250.
28. Doheny, E.P., Walsh, C., Foran, T., Green, B.R., Fan, C.W., Cunningham, C., Kenny, R.A. (2013). Falls classification using tri-axial accelerometers during the five-times-sit-to-stand test. Gait and Posture, 38, 1021-1025.
29. Figo, D., Diniz, P.C., Ferreira, D.R., Cardoso, J.M. (2010). Preprocessing techniques for context recognition from acceleration data. Personal and Ubiquitous Computing, 14, 645-662.
30. Fino, P.C., Mojdehi, A.R., Adjerid, K., Habibi, M., Lockhart, T.E., Ross, S.D. (2016). Comparing postural stability entropy analyses to differentiate fallers and non-fallers. Annals of Biomedical Engineering, 44, 1636–1645.
31. Fletcher, P.C., Hirdes, J.P. (2004). Restriction in activity associated with fear of falling among community-based seniors using home care services. Age and Ageing, 33, 273–279.
32. Gao, J., Hu, J., Buckley, T., White, K., Hass, C. (2011). Shannon and Renyi entropies to classify effects of mild traumatic brain injury on postural sway. PLoS ONE, 6, e24446.
33. Gjoreski, M., Gjoreski, H., Lustrek, M., Gams, M. (2016). How accurately can your wrist device recognize daily activities and detect falls? Sensors, 16(6), 800. doi. 10.3390/s16060800.
34. Greene, B.R., Doheny, E.P., Walsh, C., Cunningham, C., Crosby, L., Keeny, R.A. (2012). Evaluation of falls risk in community-dwelling older adults using body-worn sensors. Gerontology, 58, 472-280.
35. Griffin, M. J., (1990). Handbook of Human Vibration. London, UK: Academic Press.
36. Gupta, P., Bhardwaj, D.D., Jain, R.V. (2017). Gesture controlled mobile robotic arm vehicle using accelerometer. International Research Journal of Engineering and Technology, 4(4), 1245-1247.
37. Hasan, S.S., Robin, D.W., Szurkus, D.C., Ashmead, D.H., Peterson, S.W., Shiavi, R.G. (1996). Simultaneous measurement of body center of pressure and center of gravity during upright stance. Part I: Methods. Gait and Posture, 4(1), 1-10.
38. Hasmann, S.E., Berg, D., Hobert, M.A., Weiss, D., Lindemann, U., Streffer, J., et al. (2014). Instrumented functional reach test differentiates individuals at high risk for Parkinson's disease from controls. Frontiers in Aging Neuroscience, 6, 286.
39. Hausdorff, J.M., Peng, C.K., Ladin, Z., Wei, J.Y., Goldberger, A.L. (1995). Is walking a random walk? Evidence for long-range correlations in stride interval of human gait. Journal of Applied Physiology, 78(1), 349-358.
40. Hertel, J., Miller, J., Denegar, C.R. (2000). Intratester and interested reliability during the star excursion balance tests. Journal of Sports and Rehabilitation, 9, 104-116.
41. Hof, A.F., Gazendam, M.G.J., Sinke, W.E. (2005). The condition for dynamic stability. Journal of Biomechanics, 38(1), 1-8.
42. Hof, A.F. (2008). The ‘extrapolated center of mass’ concept suggests a simple control of balance in walking. Human Movement Science, 27, 112-125.
43. Huang, N.E., Shen, Z., Long, S.R., Wu, M.C., Shih, E.H., Zheng, Q., Tung, C.C., Liu, H.H. (1998). The empirical mode decomposition method and the Hilbert spectrum for non-stationary time series analysis. 1998. Proceedings of the Royal Society of London, 454A, 903-995.
44. Huang, N.E., Wu, Z., Long, S.R., Arnold, K., Chen, X., Blank, K. (2009). On instantaneous frequency. Advances in Adaptive Data Analysis, 1(2), 177-229.
45. Jiang, B.C., Yang, W.H., Shieh, J.S., Fan, J.S.Z., Peng, C.K. (2013). Entropy-based method for COP data analysis. Theoretical Issues in Ergonomic Science, 14(3), 227-246.
46. Kohavi, R. (1995). The power of decision tables. In: Lavrac N., Wrobel S. (eds) Machine Learning: ECML-95. ECML 1995. Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence), Vol 912. Springer, Berlin, Heidelberg.
47. Lake, D.E., Richman, J.S., Griffin, M.P., Moorman, J.R. (2002). Sample entropy analysis of neonatal heart rate variability. American Journal of Physiology. Regulatory, Integrative and Comparative Physiology, 282, R789–R797.
48. Lara, O.D., Labrador, M.A. (2013). A survey on human activity recognition using wearable sensors. IEEE Communications Surveys and Tutorials, 15(3), 1192-1209.
49. Li, B., Boccanfuso, L., Wang, Q., Barney, E., Ahn, Y.A., Foster, C., Chawarska, K., et al. (2016). Human robot activity classification based on accelerometer and gyroscope. 25th IEEE International Symposium on Robot and Human Interactive Communication, New York, USA, 26-31 August, 423-424.
50. Lombriser, C., Bharatula, N.B., Roggen, D., Trosser, G. (2007). On-body activity recognition in a dynamic sensor network. Proceedings of Second International Body Area Networks Conference, 17-22, Florence, Italy.
51. Lu, H., Liu, H. (2000). Decision tables: Scalable classification exploring RDBMS capabilities. Proceedings of the 26th International Conference on Very Large Data Bases, San Francisco, CA, USA, 10-14 September, 373-384.
52. Lyons, G., Culhane, K., Hilton, D., Grace, P., Lyons, D. (2005). A description of an accelerometer-based mobility monitoring technique. Medical Engineering and Physics, 27, 497–504.
53. Maekawa, T., Yanagisawa, Y., Kishino, Y., Ishiguro,K., Kamei,K,, Sakurai, Y., Okadome, T. (2010). Object-based activity recognition with heterogeneous sensors on wrist. Pervasive, 246-264.
54. Mahmood, M.S., Celik-Butler, Z., Butler, D.P. (2017). Wafer-level packaged flexible and bendable MEMS accelerometer for robotics and prosthetics. Sensors and Applications Symposium, Glasboro, NJ, USA, 13-15 March.
55. MATLAB R2015a. (2015). Natick, Massachusetts: The MathWorks Inc.
56. Matsumoto, Y., Nishioka, T., Shiojiri, H., Matsuzaki, K. (1978). Dynamic design of foot-bridges. Proceedings of International Association for Bridge and Structural Engineering, 17(78), 1-15.
57. McAndrew Young, P.M., Wilken, J.M., Dingwell, J.B. (2012). Dynamic margins of stability during walking in destabilizing environments. Journal of Biomechanics, 45(6), 1053-1059.
58. Ministry of Health and Welfare, Republic of China (2017). Taiwan patient safety reporting system. Retrieved June 20, 2017, from http://www.patientsafety.mohw.gov.tw/Content/Messagess/Contents.aspx?SiteID=2&MmmID=621316242156723353
59. Moe-Nilssen, R., Helbostad, J.L. (2004). Estimation of gait cycle characteristics by trunk accelerometry. Journal of Biomechanics, 37, 121-126.
60. Naqvi, M.N.Z., Kumar, D.A., Chauhan, A., Sahni, K. (2012). Step counting using smartphone-based accelerometer. International Journal on Computer Science and Engineering, 4, 675–81.
61. National Statistics, Republic of China. (2017). General situation of population. Retrieved June 20, 2017, from https://eng.stat.gov.tw/ct.asp?xItem=41871&ctNode=2265&mp=5
62. Pachi, A., Ji, T. (2005). Frequency and velocity of people walking. The Structural Engineer, 83(3), 36–40.
63. Pai, Y.C., Patton, J. (1997). Center of mass velocity-position predictions for balance control. Journal of Biomechanics, 30, 347-354.
64. Parseval, M.A. (1799). Parseval des Chênes, Marc Antoine Mémoire sur les séries et sur l’Intégration complète d’une équation aux différences partielles linéaire du second ordre, à coefficients constants presented before the Académie Sciences Paris on April 5 1799. Mémoires présentés a l’Institut des Sciences, Lettres et Arts, par divers savants, et les dans ses assemblees. Sciences, Mathématiques et Physiques Savant étrangers, 1806, 1, 638-648.
65. Peters, S.C., Iagnemma, K. (2006). An analysis on rollover stability measurement for high-speed mobile robots. Proceedings of the IEEE International Conference on Robotics and Automation, 15-19 May, Orlando, Florida, USA, 3711-3716.
66. Pincus, S.M. (1991). Approximate entropy as a measure of system complexity. Proceedings of the National Academy of Sciences, 88, 2297–2301.
67. Pirttikangas, S., Fujinami, K., Seppanen, T. (2006). Feature selection and activity recognition from wearable sensors. Proceedings of the Third International Symposium on Ubiquitous Computing Systems, 4239, 516-527.
68. Ravi, N., Dandekar, N.I., Mysore, P., Littman, M.L. (2005). Activity recognition from accelerometer data, AAAI Press, 5, 1541-1546.
69. Rayleigh, J.W.S. (1889). On the character of the complete radiation at a given temperature. Philosophical Magazine, 27, 460-469.
70. Rogers, M.J.B., Hrovat, K., McPherson, K., Moskowitz, M.E., Reckart, T. (1997). Accelerometer data analysis and presentation techniques. National Aeronautics and Space Administration. NASA Technical Reports, 19970034695, 1-48.
71. Saxena, R. (2017). How the naïve Bayes classifier works in machine learning. Retrieved June 20, 2017, from http://dataaspirant.com/2017/02/06/naive-bayes-classifier-machine-learning/
72. Schutte, K.H., Aeles, J., Op De Beek, T., van der Zwaard, B.C., Venter, R., Vanwanseele, B. (2016). Surface effects on dynamic stability and loading during outdoor running using wireless trunk accelerometry. Gait and Posture, 48, 220-225.
73. Setia, A., Mittal, S., Nigam, P., Singh, S., Gangwar, S. (2015). Hand gesture recognition based robot using accelerometer sensor. International Journal of Advanced Research in Electrical, Electronics and Instrumentation Engineering, 4(5), 4470-4476.
74. Shannon, C.E. (1948). A mathematical theory of communication. The Bell System Technical Journal, 27, 379–423.
75. Shumway-Cook, A., Woollacott, M. (2000). Attentional demands and postural control: The effect of sensory context. Journal of Gerontology, 55A (1), M10-M16.
76. Singh, A.K., Sing, J. (2015). 3-Axis hand gesture control robot using accelerometer. International Journal of Engineering Technology, Management and Applied Sciences, 13(5), 270-272.
77. Sokolova, M., Lapalme, G. (2009). A systematic analysis of performance measures for classification tasks. Journal of Information Processing and Management: an International Journal, 45(4), 427-437.
78. Song, Y.Y. Lu, Y. (2015). Decision tree methods: Applications for classification and prediction. Shanghai Arch Psychiatry, 27(2), 130–135.
79. Sporaso, F., Tyson, G. (2009). iFall: an Android application for fall monitoring and response. In: He, B., Kim, Y., editors. Proceedings of the Annual International Conference at IEEE Engineering in Medicine and Biology Society. Minneapolis, USA: IEEE.
80. Srivastava, T. (2014). Introduction to k-Nearest neighbors: Simplified. Retrieved January 10, 2017, from https://www.analyticsvidhya.com/blog/2014/10/introduction-k-neighbours-algorithm-clustering/
81. Stikic, M., Huynh, T., van Laerhovern, K., Schiele, B. (2008). ADL recognition based on the combination of RFID and accelerometer sensing. Proceedings of the Second International Conference on Pervasive Computing Technologies for Healthcare, Tampere, Finland, January 30 – February 1, 258-263.
82. Strogatz, S. H., Abrams, D. M., McRobie, A., Eckhardt, B., Ott, E. (2005). Crowd synchrony on the Millennium Bridge. Nature, 438, 43–44.
83. Terry, K., Gade, V.K., Allen, J., Forrest, G.F., Barrance, P., Edwards, W.T. (2011). Cross-correlations of center of mass and center of pressure displacements reveal multiple balance strategies in response to sinusoidal platform perturbations. Journal of Biomechanics, 44, 2066-2076.
84. Wang, T., Zhang, M., Yu, Q., Zhang, H. (2012). Comparing the applications of EMD and EEMD on time-frequency analysis of seismic signal. Journal of Applied Geophysics, 83, 29 – 34.
85. Wayne, P.M., Gow, B.J., Costa, M.D., Peng, C.K., Lipsitz, L.A., Hausdorff, J.M., Davis, R.B., Walsh, J.N., Lough, M.; Novak, V., et al. (2014). Complexity-based measures inform effects of Tai Chi training on standing postural control: Cross-sectional and randomized trial studies. PLoS ONE, 9, e114731.
86. Weka 3.8.1. (2016). Hamilton, New Zealand: The University of Waikato.
87. Wheeler, J.E. (1982). Prediction and control of pedestrian-induced vibration in foot-bridges. Journal of Structural Division, 108, 2045-2065.
88. Winter, D.A. (1995). Human balance and posture during standing and walking. Gait and Posture, 3, 193-214.
89. Wu, Z., Huang, N.E. (2005). Ensemble empirical mode decomposition: A noise-assisted data analysis method. COLA Technical Reports 193, Central for Ocean-Land-Atmosphere Study, Calverton, Maryland, USA.
90. Yang, W.H. (2010). Data mining on physiological signal – integrate dissimilarity approach and signal reconstruction for complexity analysis. (Unpublished doctoral dissertation). Yuan Ze University, Chungli, Taiwan.
91. Yoshida, T. Mizuno, F., Hayasaka, T., Tsubota, K., Wada, S., Yamaguchi, T. (2005). A wearable computer system for a detection and prevention of elderly users from falling. In: Magjarevic R.R., Nagel, J.H, editors. Proceedings of the 12th International Conference on Biomedical Engineering, Singapore: Springer.
92. Yoshizawa, M., Takasaki, W., Ohmura, R. (2013). Parameter exploration for response time reduction in accelerometer-based activity recognition. Proceedings of the 2013 ACM Conference on Pervasive and Ubiquitous Computing, 653-664.
93. Zhang, J., Sun, L., Peng, P., Zhang, X., Li, J. (2013). Simulation analysis of passive adaptive robot’s tip-over stability. Robotics and Biomimetics, Shenzhen, China, 12-14 December, 1936-1940.