为解决人体运动模式识别中姿态分类问题，详细研究了人体姿态识别的特征选择.通过统计三轴加速度传感器的x轴、y轴、z轴等信号，获得标准差、偏度和峰度等117种特征.将Fisher score、relief-F和Chi square 3种算法与层次分类方法相结合选择出特征子集，采用支持向量机对动作进行分类.实验表明，利用3种特征选择算法所选择出的特征集有助于较高精度地识别站立、坐和躺3种静态动作以及走、上楼、下楼3种动态动作，且有利于后续进行低复杂度在线识别方法研究.
In order to solve the problem of activity classification in human motion pattern recognition, the feature selection of human activity recognition is studied in detail. By taking signal statistics on the x-axis, y-axis and z-axis, 117 features such as standard deviation, skewness and kurtosis are obtained. The three algorithms of Fisher score, Relief-F and Chi square are combined with the hierarchical classification method to select the feature subset, and the action classification is conducted by using the support vector machine (SVM). Experiments showed that the feature set selected by the three feature selection algorithms helps to identify three static movements of standing, sitting and lying and three dynamic movements of walking, going upstairs and downstairs with high precision, which is conducive to the subsequent research on low complexity online identification method.
[1] Franchino P, Anana V R, Deepak K. Wearable movement sensors for rehabilitation:a focused review of technological and clinical advances[J]. Innovations Influencing Physical Medicine and Rehabilitation, 2018, 10(9):220-232.
[2] Clayton R P, Danilo R P, Silke A T W, Christian H, Victor H C A, Joao P P. A survey on computer-assisted Parkinson's disease diagnosis[J]. Artificial Intelligence in Medicine, 2019, 95(4):48-63.
[3] Morales J, Akopian D. Physical activity recognition by smartphones a survey[J]. Biocybernetics and Biomedical Engineering, 2017, 37(4):388-400.
[4] 莫悠,钟若飞,张振鑫. 移动与定点扫描结合的室内点云数据获取方法[J]. 应用科学学报,2018, 36(5):756-764. Mo Y, Zhong R F, Zhang Z X. Acquisition of indoor laser point clouds based on mobile and terrestrial scanning[J]. Journal of Applied Sciences, 2018, 36(5):756-764. (in Chinese)
[5] Kumari P, Mathew L, Syal P. Increasing trend of wearables and multimodal interface for human activity monitoring:a review[J]. Biosensors and Bioelectronics, 2017, 90:298-307.
[6] 赵晓东,刘作军,陈玲玲,杨鹏. 下肢假肢穿戴者跑动步态识别方法[J]. 浙江大学学报(工学版),2018, 52(10):1980-1988. Zhao X D, Liu Z J, Chen L L, Yang P. Approach of running gait recognition for lower limb amputees[J]. Journal of Zhejiang University (Engineering Science), 2018, 52(10):1980-1988. (in Chinese)
[7] 王永雄,陈晗,尹钟,喻洪流,孟巧玲. 基于惯导信息的人体动作和路况识别[J]. 生物医学工程学杂志,2018, 35(4):621-630. Wang Y X, Chen H, Yin Z, Yu H L, Meng Q L. Human action and road condition recognition based on the inertial information[J]. Journal of Biomedical Engineering, 2018, 35(4):621-630. (in Chinese)
[8] 孙子文,李松,孙晓雯. 基于D-S证据理论的人体跌倒检测方法[J]. 计算机工程与科学,2018, 40(5):829-835. Sun Z W, Li S, Sun X W. A human fall detection method based on D-S evidence theory[J]. Computer Engineering & Science, 2018, 40(5):829-835. (in Chinese)
[9] 蔡雅薇,谭晓阳. 弱监督任意姿态人体检测[J]. 计算机科学与探索,2017, 11(4):587-598. Cai Y W, Tan X Y. Weakly supervised human body detection under arbitrary poses[J]. Journal of Frontiers of Computer Science and Technology, 2017, 11(4):587-598. (in Chinese)
[10] Thanh H. N, Ty P P, Cuong Q N, Thanh T N. A SVM algorithm for investigation of tri-accelerometer based falling data[J]. American Journal of Signal Processing, 2016, 6(2):56-65.
[11] Kaori F. On-body smartphone localization with an accelerometer[J]. Information, 2016, 21(7):1-23.
[12] Jorge-Lr O, Luca O, Albert S, Xavier P, Davide A. Transition-aware human activity recognition using smartphones[J]. Neurocomputing, 2016, 171:754-767.
[13] Sztyler T, Stuckenschmidt H, Petrich W. Position-aware activity recognition with wearable devices[J]. Pervasive and Mobile Computing, 2017, 38:281-295.
[14] Morales J, Akopian D. Physical activity recognition by smartphones, a survey[J]. Biocybernetics and Biomedical Engineering, 2017, 37(3):388-400.
[15] San S R, Montero J M, Barrac R, Fernandof, Manuel P. Feature extraction from smartphone inertial signals for human activity segmentation[J]. Signal Processing, 2016, 120:359-372.
[16] Adil M K, Ali T, Asadm K, Teemu L. Activity recognition on smartphones via sensor-fusion and KDA-based SVMs[J]. International Journal of Distributed Sensor Networks, 2014, 503291:1-14.
[17] 熊邦书,刘雨,莫燕,黄建萍,李新民. 基于SVM的直升机飞行状态识别[J]. 应用科学学报,2016, 34(7):469-474. Xiong B S, Liu Y, Mo Y, Huang J P, Li X M. Recognition of helicopter flight condition based on support vector machine[J]. Journal of Applied Sciences, 2016, 34(7):469-474. (in Chinese)
[18] Wang Z L, Wu D H, Chen J M, Ghoneim A, Hossain M A. A triaxle accelerometer-based human activity recognition via EEMD-based features and game-theory-based feature selection[J]. IEEE Sensors Journal, 2016, 16(9):3198-3207.
