臺灣博碩士論文加值系統

由於機器人技術已日漸成熟。我們希望可以有一個類似管家的機器人，平常不僅
能幫助家裡處理瑣碎的事物，也能扮演家庭保全、看護老年人的功能。論文發展一套人體姿態的辨識系統，希望藉由此系統與機器人結合，讓在家裡服務的機器人能夠同時監控家中老年人的生活，扮演看護角色。

本論文應用無線傳送之加速度訊號發展一套人體姿態辨識系統。此系統包括一三
軸加速度訊號量測、傳輸模組及姿態辨識軟體。其中加速度量測為一三軸加速度計，無線傳輸模組為Zigbee 及12 bit 的ADC 轉換，類比轉成數位訊號輸出。在接收端有Zigbee 序列無線傳輸接收模組，與個人電腦或機器人主電腦溝通。再利用萃取出來的8個特徵，經過比對辨識，完成轉圈、跑步、走路、跳躍、站和坐六種姿態辨識系統。接著，我們也把所萃取出來的特徵加入權重的概念，透過權重和誤差法篩選出重要的特徵，並將權重的概念結合在一起，完成了一套系統，讓辨識率提升了10-12%。

Since the robotics and automation technology is getting matured, we wish to develop a domestic robot which is able to help household chores as well as elderly and infirm people. This thesis aims at developing a human gesture recognition system which can help domestic robots take care of people with disabilities in their daily life. The human gesture recognition system is developed with the application of wireless transmission of acceleration signal. The identification of the extracted characteristics with the training bases helps us complete a system which can recognize six human gestures: rotating, running, walking, jumping, standing and sitting. In our thesis, we use eight characteristics to identify actions at first. Then we add the weight method to raise the recognition rates. Finally we raise about 10-12% by using just four characteristics with weight added on them.

中文摘要. . . . . . . . . . . . . . . . . . . . . . . . . . i
Abstract . . . . . . . . . . . . . . . . . . . . . . . . ii
誌謝. . . . . . . . . . . . . . . . . . . . . . . . . . iii
Contents . . . . . . . . . . . . . . . . . . . . . . . . iv
List of Tables . . . . . . . . . . . . . . . . . . . . . vii
List of Figures . . . . . . . . . . . . . . . . . . . . viii
1 Introduction . . . . . . . . . . . . . . . . . . . . . . 1
1.1 Research Background . . . . . . . . . . . . . . . . . 1
1.2 Motivation and Objective . . . . . . . . . . . . . . . 2
1.3 Contribution . . . . . . . . . . . . . . . . . . . . . 4
1.4 Organization . . . . . . . . . . . . . . . . . . . . . 5
2 Activity Recognition System . . . . . . . . . . . . . . 6
2.1 Activity Recognition Flow Chart . . . . . . . . . . . .6
2.2 Hardware Introduction . . . . . . . . . . . . . . . . 7
2.2.1 Microprocessor-Arduino . . . . . . . . . . . . . . . 7
2.2.2 3-Axis Accelerometer-Hitac48C . . . . . . . . . . . .9
2.2.3 Zigbee Transmission . . . . . . . . . . . . . . . . 10
2.2.4 Experimental Equipment . . . . . . . . . . . . . . 12
3 Data Processing . . . . . . . . . . . . . . . . . . . . 14
3.1 Structure of Activity Recognition System . . . . . . .14
3.2 Receiving Raw Data . . . . . . . . . . . . . . . . . .14
3.3 Window Size (Frame) . . . . . . . . . . . . . . . . . 16
3.4 Using Moving Average for Raw Data Filtering . . . . . 17
3.5 Signal Magnitude Area (SMA) . . . . . . . . . . . . . 18
3.6 Feature Extraction . . . . . . . . . . . . . . . . . .19
3.6.1 Amplitude . . . . . . . . . . . . . . . . . . . . . 19
3.6.2 Mean . . . . . . . . . . . . . . . . . . . . . . . .20
3.6.3 Energy . . . . . . . . . . . . . . . . . . . . . . .20
3.6.4 Variance . . . . . . . . . . . . . . . . . . . . . .21
3.6.5 Standard Deviation . . . . . . . . . . . . . . . . .21
3.6.6 Mean Absolute Deviation . . . . . . . . . . . . . . 22
3.6.7 Root Mean Square (RMS) . . . . . . . . . . . . . . .22
3.6.8 Interquartile Range . . . . . . . . . . . . . . . . 23
3.7 The Strategy of Classification . . . . . . . . . . . .24
3.8 Improving Rates by Weighting . . . . . . . . . . . . .27
3.9 Improving Weight Method . . . . . . . . . . . . . . . 28
4 Experimental Results and Analysis . . . . . . . . . . . 30
5 Conclusions and Future Work . . . . . . . . . . . . . . 38
5.1 Conclusions . . . . . . . . . . . . . . . . . . . . . 38
5.2 Future work . . . . . . . . . . . . . . . . . . . . . 38
References . . . . . . . . . . . . . . . . . . . . . . . .40
個人簡歷. . . . . . . . . . . . . . . . . . . . . . . . . 42

[1] W.-Y. Chung, S. Bhardwaj, A. Purwar, D.-S. Lee, and R. Myllylae, ``A fusion health monitoring using ecg and accelerometer sensors for elderly persons at home,' in Engineering in Medicine and Biology Society (EMBS'07), 29th Annual International Conference of the IEEE, pp. 3818--3821, Aug. 2007.

[2] A. Sixsmith and N. Johnson, ``A smart sensor to detect the falls of the elderly,' IEEE Pervasive Computing, vol. 3, pp. 42--47, April-June 2004.

[3] F. Cavallo, A. Sabatini, and V. Genovese, ``A step toward gps/ins personal navigation systems: real-time assessment of gait by foot inertial sensing,' in IEEE/RSJInternational Conference onIntelligent Robots and Systems(IROS'05), pp. 1187--1191, Aug. 2005.

[4] K. Sagawa, H. Inooka, and Y. Satoh, ``Non-restricted measurement of walking distance,' in IEEE International Conference on Systems, Man, and Cybernetics, vol. 3, pp. 1847--1852, 2000.

[5] S. Shin, C. Park, J. Kim, H. Hong, and J. Lee, ``Adaptive step length estimation algorithm using low-cost mems inertial sensors,' in IEEE Sensors Applications Symposium (SAS'07), pp. 1 --5, Feb. 2007.

[6] M. Mathie, J. Basilakis, and B. Celler, ``A system for monitoring posture and physical activity using accelerometers,' in Engineering in Medicine and Biology Society,the 23rd Annual International Conference of the IEEE, vol. 4, pp. 3654--3657, 2001.

[7] Y.-P. Chen, J.-Y. Yang, S.-N. Liou, G.-Y. Lee, and J.-S. Wang, ``Online classifier construction algorithm for human activity detection using a tri-axial accelerometer,' Applied Mathematics and Computation, vol. 205, no. 2, pp. 849--860, 2008.

[8] D. Karantonis, M. Narayanan, M. Mathie, N. Lovell, and B. Celler, ``Implementation of a real-time human movement classifier using a triaxialaccelerometer for ambulatory monitoring,' IEEE Transactions on Information Technology in Biomedicine, vol. 10, pp. 156--167, Jan. 2006.

[9] M. Mathie, B. Celler, N. Lovell, and A. Coster, ``Classification of basic daily movements using a triaxial accelerometer,' Medical and Biological Engineering and Computing, vol. 42, pp. 679--687, 2004. 10.1007/BF02347551.

[10] D.-U. Jeong, S.-J. Kim, and W.-Y. Chung, ``Classification of posture and movement using a 3-axis accelerometer,' in International Conference on Convergence Information Technology, pp. 837--844, Nov. 2007.

[11] S. Wang, J. Yang, N. Chen, X. Chen, and Q. Zhang, ``Human activity recognition with user-free accelerometers in the sensor networks,' in International Conferenceon Neural Networks and Brain(ICNNB'05), vol. 2, pp. 1212 --1217, Oct. 2005.

[12] S. Lee, H. Park, S. Hong, K. Lee, and Y. Kim, ``A study on the activity classification using a triaxial accelerometer,' in Engineering in Medicine and Biology Society, the 25th Annual International Conference of the IEEE, vol. 3, pp. 2941--2943, sept. 2003.