手机加速度计的行人行进状态识别Pedestrian movement status identification based on mobile phone attitude sensor
刘清华;郭英;郎爱坤;冯茗扬;孙建立;
摘要(Abstract)：
针对行人在行进过程中会出现后退而导致对行人航位轨迹的错误判断问题,该文以手机内加速度传感器信号为数据依据,以识别行人正常前进中的后退状态为研究目标,研究三轴信号的均值、方差、轴间协方差等时域特征,采用经验模态分解、最大相关最小冗余、最小二乘支持向量机等方法,识别行人实时的前进或后退。研究结果表明:两人将手机置于不同位置,分别采集前进中出现不同后退步数的实验数据,以一组为建模数据,识别其他情况的运动状态,其识别平均成功率达96.00%,具有较大的理论参考价值。
关键词(KeyWords)： 经验模态分解;最大相关最小冗余;最小二乘支持向量机;行人行进状态
基金项目(Foundation):
作者(Author): 刘清华;郭英;郎爱坤;冯茗扬;孙建立;
Email:
DOI: 10.16251/j.cnki.1009-2307.2020.06.002
参考文献(References)：
- [1] 刘经南,高柯夫.智能时代测绘与位置服务领域的挑战与机遇[J].武汉大学学报(信息科学版),2017,42(11):1506-1517.(LIU Jingnan,GAO Kefu.Challenges and opportunities for mapping and surveying location based service in the age of intelligence[J].Geomatics and Information Science of Wuhan University,2017,42(11):1506-1517.)
- [2] HARLE R.A survey of indoor inertial positioning systems for pedestrians[J].IEEE Communications Survey & Tutorials,2013,15(3):1281-1293.
- [3] LUGADE V,FORTUNE E,MORROW M,et al.Validity of using tri-axial accelerometers to measure human movement[J].Medical Engineering & Physics,2014,36(2):169-176.
- [4] ZHANG M,SAWCHUK A.A feature selection-based framework for human activity recognition using wearable multimodal sensors[C]//Proceedings of the 6th International Conference on Body Area Networks.[S.l.]:[s.n.],2011:92-98.
- [5] 路永乐,张欣,龚爽,等.基于MEMS惯性传感器的人体多运动模式识别[J].中国惯性技术学报,2016,24(5):589-594.(LU Yongle,ZHANG Xin,GONG Shuang,et al.Recognition of multiple human motion patterns based on MEMS inertial sensors[J].Journal of Chinese Inertial Technology,2016,24(5):589-594.)
- [6] FARZIN D,BENOIT M STEOHANE R,et al.Gait and foot clearance parameters obtained using shoe-worn inertial sensors in a large-population sample of older adults[J].Sensors,2014,14(1):443-457.
- [7] 郭英,刘清华,姬现磊,等.基于手机加速度计的行人步态分析[J].中国惯性技术学报,2017,25(6):708-712.(GUO Ying,LIU Qinghua,JI Xianlei,et al.Pedestrian gait analysis based on mobile phone accelerometer[J].Journal of Chinese Inertial Technology,2017,25(6):708-712.)
- [8] VAPNIK V.The nature of statistical learning theory[M].[S.l.]:Springer,2000:169-170.
- [9] HUYNH T,SCHIELE B.Analyzing features for activity recognition[J/OL].[2019-03-04].https://core.ac.uk/display/20790851.
- [10] 武哲,杨绍普,刘永强.基于多元经验模态分解的旋转机械早期故障诊断方法[J].仪器仪表学报,2016,37(2):241-248.(WU Zhe,YANG Shaopu,LIU Yongqiang.Rotating machinery early fault diagnosis method based on multivariate empirical mode decomposition[J].Chinese Journal of Scientific Instrument,2016,37(2):241-248.)
- [11] MICHAEL B,REDMOND S J,LOVELL N H.Tracking the evolution of smartphone sensing for monitoring human movement[J].Sensors,2015,15(8):18901-18933.
- [12] DUAN L Z,LIU S F,LU Q.Study on the determination of moving step length in moving method of mean[J].Journal of Beijing University of Technology,2004,30(3):378-381.