拜醫療科技進步所賜，人們的壽命逐漸延長，導致老年人口的比例急速成長，隨著第二次世界大戰後的嬰兒潮以及生育率的下降，現今全球各國人口結構趨於老化，造成社會醫療成本增加。銀髮族隨著年齡增長，罹患失能或失智相關病症之機率大增，造成銀髮族行動遲緩、肌肉骨骼老化與智能退化等，因而需要求助專業的醫療機構，透過一系列肢體復健與智能化復健，以恢復身體機能與減緩老化。
本論文將實現一套基於動作辨識之人機互動(Human Computer Interaction, HCI)實境，應用於銀髮族身心復建輔助。系統實作個人區域感測網路(Personal Area Sensor Network, PASN)，利用從節點(Slave Sensor Node, SSN)與主節點(Master Sensor Node, SSN)分別配帶於胸前與腳踝，藉由感測節點感測人體上、下半身活動姿態之相關數據，透過姿態辨識演算法辨識銀髮族常見的姿態動作。本系統在後端部分亦提出一套適合銀髮族的人機互動介面，當後端接收到主節點回傳的動作判斷資料，動作辨識的結果會以遊戲的方式以呈現。經實際測試結果，本系統之姿態判別準確率超過90%。因此本系統為銀髮族復健提供合適的解決方案，透過富含實用性與娛樂性之身心復健課程，以輔助銀髮族的肢體與智能化復健。

Due to rising life expectancies as a result of advancements in medical science and the continuing aging of the baby boomers born in the middle of the last century, the elderly populations of many countries around the world have increased significantly in recent years. As the age is progressively increased, the elderly are prone to extremity injuries and dementia, and to functional disorders of the body. However, they are often unable to take care of themselves, and therefore have little choice but to turn to professional healthcare providers.
This thesis develops a movement recognition based Human-Computer Interaction (HCI) reality which can be used as a physical and psychological rehabilitation tool to assist with the body and brain training of elderly individuals. The proposed HCI reality is implemented using a Personal Area Sensor Network (PASN), in which a Slave Sensor Node (SSN) and a Master Sensor Node (MSN) are attached to the subject’s chest and foot, respectively, and each of them consists of a data acquisition board and a sensor component. The SSN and MSN perform an initial pre-processing of the signals produced by the equipped sensor component to cooperatively recognize various motions of elderly individuals. Furthermore, a human-computer interaction interface is developed to immediately display the recognition results in a graph manner once the MSN broadcasts the recognition information to the backend server. The experimental results show that the proposed movement recognition based HCI reality has a classification accuracy of approximately 90% when applied to the recognition of various elderly actions, thereby providing a solution for professional healthcare providers to offer a new public health paradigm of physical and psychological rehabilitation for elderly individuals.

[1] 經建會人力規劃處，中華民國臺灣97 年至145 年人口推計及分析，台灣經建專論，Vol. 7，No. 6，PP. 36-69，8月，2009。
[2] 經建會人力規劃處，我國長期照護需求推估及服務供給現況，台灣經建專論，Vol. 7，No. 10，PP. 54-71，10月，2009。
[3] 賴薇如、逢愛君、江為國、張林煌、陳懷恩，網路電話與系統應用，維科圖書有限公司，2007。
[4] Francesco, Buccolieri, Cosimo Distante and Alessandro Leone, “Human Posture Recognition Using Active Contours and Radial Basis Function Neural Network,” IEEE conference on Advanced Video and Signal Based Surveillance, pp. 213-218, Sept. 2005.
[5] Leonid Sigal and Michael J. Black, “HumanEva: Synchronized Video and Motion Capture Dataset for Evaluation of Articulated Human Motion,”Technical Report CS-06-08, Sept. 2006.
[6] Koichi Sagawa, Hikaru Inooka and Yutaka Satoh, "Non-restricted measurement of walking distance," IEEE International Conference on Systems, Man and Cybernetics, Vol. 3, pp. 1847-1852, Oct. 2000.
[7] Makoto Tanigawa, Henk Luinge, Linda Schipper, and Per Slycke, “Drift-Free Dynamic Height Sensor using MEMS IMU Aided by MEMS Pressure Sensor,” Workshop on Positioning, Navigation and Communication, pp. 191-196, March, 2008.
[8] Huiru Zheng, Norman Black and Nigel Harris, "Position-sensing technologies for movement analysis in stroke rehabilitation," Medical and Biological Engineering and Computing, Vol. 43, No.4, pp. 413-420, Aug. 2005.
[9] Dinesh Bhatia, Leonardo Estevez, and Shekar Rao,"Energy Efficient Contextual Sensing for Elderly Care," IEEE Annual International Conference of the IEEE Conference on Engineering in Medicine and Biology Society, pp.4052-4055, Aug. 2007.
[10] Sasiwan Paiyarom, Poj Tungamchit, Rachaporn Keinprasit and Prakasith Kayasith " Activity monitoring system using Dynamic Time Warping for the elderly and disabled people," International Conference on Computer, Control and Communication, pp. 1-4, Feb. 2009.
[11] Dean M. Karantonis, Michael R. Narayanan, Merryn Mathie, Nigel H. Lovell and and Branko G. 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, pp. 156-167, Jan, 2006.
[12] Do-Un Jeong, Se-Jin Kim, and Wan-Young Chung, "Classification of Posture and Movement Using a 3-axis Accelerometer," International Conference on Convergence Information Technology, pp. 837-844, Nov. 2007.
[13] Gaetano Anania, Alessandro Tognetti, Nicola Carbonaro, Mario Tesconi, Fabrizio Cutolo, and Giuseppe Zupone and Danilo De Rossi, "Development of a novel algorithm for human fall detection using wearable sensors," IEEE SENSORS Conference, pp.1336-1339, Oct. 2008.
[14] Juan C. Alvarez, Rafael C. González,Diego Alvarez, Antonio M. López and Javier Rodríguez-Uría, "Multisensor Approach to Walking Distance Estimation with Foot Inertial Sensing," IEEE Annual International Conference of the IEEE Conference on Engineering in Medicine and Biology Society, pp. 5719-5722, Aug. 2007.
[15] Koichi Sagawa, Hikaru Inooka and Yutaka Satoh, "Non-restricted measurement of walking distance," IEEE International Conference on Systems, Man, and Cybernetics, Vol. 3, pp. 1847-1852, Oct. 2000.
[16] Mathie, Merryn Joy, "Monitoring and Interpreting Human Movement Patterns Using a Triaxial Accelerometer," Ph.D. thesis, Univ. New South Wales, Sydney, Australia, 2003.
[17] Yoon Sang Kim, Byung Seok Soh and Sang-Goog Lee "A New Wearable Input Device: SCURRY," IEEE Transactions on Industrial Electronics, Vol. 52, No. 6, Dec. 2005.
[18] Shinobu Tanaka, Kosuke Motoi, Mamamichi Nogawa and Ken-ichi Yamakoshi, "A New Portable Device for Ambulatory Monitoring of Human Posture and Walking Velocity Using Miniature Accelerometers and Gyroscope, " IEEE Annual International Conference of the IEEE Conference on Engineering in Medicine and Biology Society, Vol.1, pp. 2283-2286, Sept. 2004
[19] IEEE Standards 802.15.4™, "Wireless LAN medium access control(MAC) andphysical layer (PHY) specifications for low-rate wireless personal area network(LR-WPANs)," The Institute of Electrical and Electronics Engineers, Inc.,2006
[20] Yeoh, Wee-Soon, Pek, Isaac, Yong, Yi-Han, Chen, Xiang, Waluyo and Agustinus Borgy, “Ambulatory Monitoring of Human Posture and Walking Speed Using Wearable Accelerometer Sensors”, IEEE Annual International Conference of the IEEE Conference on Engineering in Medicine and Biology Society, pp. 5184-5187, Aug. 2008
[21] Sudeep Sarkar, P. Jonathon Phillips, Zongyi Liu, Isidro Robledo Vega, Patrick Grother and Kevin W. Bowyer, “The HumanID Gait Challenge Problem: Data Sets, Performance, and Analysis,” IEEE Trans. Pattern Analysis and Machine Intelligence, Vol. 27, No. 2, pp. 162-177, Feb. 2005.
[22] The Bluetooth Special Interest Group, “Bluetooth Specification Version 1.1,” http://www.bluetooth.com, Feb. 2001.
[23] Oren Eliezer and Dan Michael “Adaptive frequency hopping for FHSS system,” IEEE 802.15-01/169, March 2001
[24] Pravin Bhagwat, “Bluetooth: Technology for Short-Range Wireless Apps,” IEEE Internet Computing 5(3), 2001
[25] Manish Kalia, Sumit Garg, Rejeev Shorey, “Scattnet Structure and Inter- Piconet Communication in Bluetooth system,” IEEE National Conference on Communications, 2000
[26] Standard for part 15.4: Wireless MAC and PHY Specifications for Low-Rate WPAN, IEEE,New York, NY (Oct 2003).
[27] ZigBee Alliance, ZigBee Specification v1.0 (Dec 14th 2004).
[28] Paul Booth,“An introduction to human-computer interaction,”East Sussex,BN32FA, U.K. Lawrence Erlbaum Research, July 1990.
[29] Hui-Tang Lin, Yao-Jung Hsieh, Ming-Che Chen, Wang-Rong Chang, "ActionView: a movement-analysis ambulatory monitor in elderly homecare systems,” IEEE International Symposium on Circuits and Systems, pp. 3098-3101, May 2009
[30] IEEE Standard 802.11-1999.
[31] Simon, D., Optimal State Estimation: Kalman, H Infinity, and Nonlinear Approaches. Hoboken, New Jersey, John Wiley & sons Inc.2007
[32] Maria Isabel Ribeiro, "Kalman and Extended Kalman Filters: Concept, Derivation and Properties," Institute for Systems and Robotics, Feb. 2004.
[33] Sun Shu-Li and Deng Zi-Li, “Multi-sensor optimal information fusion Kalman filter,” Automatica, vol. 40, No. 6, pp.1017-1023, Jun. 2004
[34] Steve Nasiri, David Sachs, Michael Maia，運動處理方案，電子工程專輯，10月，2009
[35] Nunzio Abbate, Adriano Basile, Carmen Brigante and Alessandro Faulisi, “Development of a MEMS based wearable motion capture system”, IEEE Conference on Human System Interactions, PP. 255-259, May 2009
[36] M. Romanovas, L. Klingbeil, M. Trachtler and Y. Manoli, “Efficient orientation estimation algorithm for low cost inertial and magnetic sensor systems”, IEEE/SP Workshop on Statistical Signal Processing, pp.586-589, Sept. 2009.
[37] Liang Xue, Weizheng Yuan, Honglong Chang and Chengyu Jiang, “MEMS-based Multi-sensor Integrated Attitude Estimation Technology For MAV Applications”, IEEE International Conference on Nano/Micro Engineered and Molecular Systems, pp.1031-1035, Jan. 2009.
[38] Chin-Der Wann and ian-Hau Gao, “Sensor Motion Tracking by IMM-Based Extended Kalman Filters”, International Conference on Innovative Computing, Information and Control, pp.1377 – 1380, Dec. 2009