基于SVM的人体运动分析与防跌倒检测技术
|
摘要
随着人们对健康监测关注度的日益增长和智能手机的普及,文中提出了一种基于SVM的人体运动分析方法,并基于该方法和Android平台设计了一种防跌倒系统。通过采集智能手机内置传感器的数据,并对原始数据进行滤波去噪、加窗分割、时频特征提取及特征降维等处理,使用SVM分析与识别不同的行为。该防跌倒系统,在检测到用户处于跌倒状态时会发出求救信息。实验与测试结果表明,所提出的方法能获得97. 5%的敏感性和98. 3%的特异性,对跌倒行为具有较高的识别精度。
Focusing on growing concern on health monitoring and the popularity of smartphones,a human movement analysis method based on SVM is proposed and a fall prevention Android platform system based on this method is designed. By collecting the data through built-in sensors of smartphones,and processing the original data,such as filtering and denoising,window segmentation,time-frequency feature extraction and feature dimensionality reduction,and using SVM to analyze and identify different behaviors. The fall prevention system sends a distress message when it detects that the user is in a falling state. Experiments and test results show that the proposed method can obtain sensitivity of 97. 5% and specificity of 98. 3%,has high recognition accuracy for falls.
Focusing on growing concern on health monitoring and the popularity of smartphones,a human movement analysis method based on SVM is proposed and a fall prevention Android platform system based on this method is designed. By collecting the data through built-in sensors of smartphones,and processing the original data,such as filtering and denoising,window segmentation,time-frequency feature extraction and feature dimensionality reduction,and using SVM to analyze and identify different behaviors. The fall prevention system sends a distress message when it detects that the user is in a falling state. Experiments and test results show that the proposed method can obtain sensitivity of 97. 5% and specificity of 98. 3%,has high recognition accuracy for falls.
引文
[1]孙荣霞,马少卿,王硕南,等.一种适用于单片机的老人跌倒检测算法研究[J].现代电子技术,2017,40(22):14-18.
[2]Wang L. Recognition of human activities using continuous autoencoders with wearable sensors[J]. Sensors,2016,16(2):189-195.
[3]zdemir Ahmet Turan. An analysis on sensor locations of the human body for wearable Fall Detection Devices:Principles and Practice:[J]. Sensors,2016,16(8):1161-1168.
[4]Liu L,Peng Y,Wang S,et al. Complex activity recognition using time series pattern dictionary learned from ubiquitous sensors[J]. Information Sciences,2016,340-341(C):41-57.
[5]焦金辉,勾灿,孙玉国.基于安卓的物体姿态与位置信息远程监测系统[J].电子科技,2017,30(8):113-116.
[6]Wu D,Wang Z,Chen Y,et al. Mixed-kernel based weighted extreme learning machine for inertial sensor based human activity recognition with imbalanced dataset[J]. Neurocomputing,2016,19(10):35-49.
[7]Rawashdeh S A,Rafeldt D A,Uhl T L. Wearable IMU for shoulder injury prevention in overhead sports[J]. Sensors,2016,16(11):1847-1852.
[8]白勇,孙晓雯,秦防,等.基于SVD特征降维和支持向量机的跌倒检测算法[J].计算机应用与软件,2017,34(1):247-251.
[9]李政.一种基于三轴加速度的跌倒检测方法[J].电子科技,2015,28(3):11-14.
[10]蔡靖,樊毅尧,董子健,等.基于穿戴式平台的老人摔倒监测系统设计[J].传感器与微系统,2017,36(7):130-133.
[11]程一风,李达,张翔晨.基于Android手机多传感器的老人跌倒检测技术研究与实现[J].电子设计工程,2016,24(14):181-183.
[12]Chang K M,Chun Y T,Chen S H,et al. The evaluation of physical stillness with wearable chest and arm accelerometer during chan ding practice[J]. Sensors,2016,16(7):1126-1135.
[13]Choudhury T,Borriello G,Consolvo S,et al. The mobile sensing platform:an embedded activity recognition system[J]. IEEE Pervasive Computing,2008,7(2):32-41.
[14]Altun K,Barshan B,Tun9el O. Comparative study on classifying human activities with miniature inertial and magnetic sensors[J]. Pattern Recognition,2010,43(10):3605-3620.
[15]Albinali F,Intille S,Haskell W,et al. Using wearable activity type detection to improve physical activity energy expenditure estimation[C]. ACM,2010:311-320.
[16]Preece S J,Goulermas J Y,Kenney L P,et al. Activity identification using body-mounted sensors-a review of classification techniques[J]. Physiological Measurement,2009,30(4):31-35.
[17]Findling R D,Muaaz M,Hintze D,et al. ShakeUnlock:securely transfer authentication states between mobile devices[J]. IEEE Transactions on Mobile Computing,2017,16(4):1163-1175.
[18]陈鹏,涂亚庆,童俊平,等.可穿戴式跌倒检测智能系统设计[J].传感器与微系统,2017,36(2):114-116.
[19]孙朋,夏飞,张浩,等.改进混合高斯模型在人体跌倒检测中的应用[J].计算机工程与应用,2017,53(20):173-179.
[20]孙子文,孙晓雯.基于加速度传感器的人体跌倒检测方法[J].计算机工程与科学,2017,39(2):330-335.
[21]King R C,Villeneuve E,White R J,et al. Application of data fusion techniques and technologies for wearable health monitoring[J]. Medical Engineering&Physics,2017(42):1-12.
[22]赵子傧.仿人跑步机器人稳定性研究[J].电子科技,2017,30(11):89-92.
[23]Kondo Y,Salibian-Barrera M,Zamar R. RSKC:an R package for A robust and sparse k-means clustering algorithm[J]. Journal of Statistical Software,2016,72(5):59-66.
[2]Wang L. Recognition of human activities using continuous autoencoders with wearable sensors[J]. Sensors,2016,16(2):189-195.
[3]zdemir Ahmet Turan. An analysis on sensor locations of the human body for wearable Fall Detection Devices:Principles and Practice:[J]. Sensors,2016,16(8):1161-1168.
[4]Liu L,Peng Y,Wang S,et al. Complex activity recognition using time series pattern dictionary learned from ubiquitous sensors[J]. Information Sciences,2016,340-341(C):41-57.
[5]焦金辉,勾灿,孙玉国.基于安卓的物体姿态与位置信息远程监测系统[J].电子科技,2017,30(8):113-116.
[6]Wu D,Wang Z,Chen Y,et al. Mixed-kernel based weighted extreme learning machine for inertial sensor based human activity recognition with imbalanced dataset[J]. Neurocomputing,2016,19(10):35-49.
[7]Rawashdeh S A,Rafeldt D A,Uhl T L. Wearable IMU for shoulder injury prevention in overhead sports[J]. Sensors,2016,16(11):1847-1852.
[8]白勇,孙晓雯,秦防,等.基于SVD特征降维和支持向量机的跌倒检测算法[J].计算机应用与软件,2017,34(1):247-251.
[9]李政.一种基于三轴加速度的跌倒检测方法[J].电子科技,2015,28(3):11-14.
[10]蔡靖,樊毅尧,董子健,等.基于穿戴式平台的老人摔倒监测系统设计[J].传感器与微系统,2017,36(7):130-133.
[11]程一风,李达,张翔晨.基于Android手机多传感器的老人跌倒检测技术研究与实现[J].电子设计工程,2016,24(14):181-183.
[12]Chang K M,Chun Y T,Chen S H,et al. The evaluation of physical stillness with wearable chest and arm accelerometer during chan ding practice[J]. Sensors,2016,16(7):1126-1135.
[13]Choudhury T,Borriello G,Consolvo S,et al. The mobile sensing platform:an embedded activity recognition system[J]. IEEE Pervasive Computing,2008,7(2):32-41.
[14]Altun K,Barshan B,Tun9el O. Comparative study on classifying human activities with miniature inertial and magnetic sensors[J]. Pattern Recognition,2010,43(10):3605-3620.
[15]Albinali F,Intille S,Haskell W,et al. Using wearable activity type detection to improve physical activity energy expenditure estimation[C]. ACM,2010:311-320.
[16]Preece S J,Goulermas J Y,Kenney L P,et al. Activity identification using body-mounted sensors-a review of classification techniques[J]. Physiological Measurement,2009,30(4):31-35.
[17]Findling R D,Muaaz M,Hintze D,et al. ShakeUnlock:securely transfer authentication states between mobile devices[J]. IEEE Transactions on Mobile Computing,2017,16(4):1163-1175.
[18]陈鹏,涂亚庆,童俊平,等.可穿戴式跌倒检测智能系统设计[J].传感器与微系统,2017,36(2):114-116.
[19]孙朋,夏飞,张浩,等.改进混合高斯模型在人体跌倒检测中的应用[J].计算机工程与应用,2017,53(20):173-179.
[20]孙子文,孙晓雯.基于加速度传感器的人体跌倒检测方法[J].计算机工程与科学,2017,39(2):330-335.
[21]King R C,Villeneuve E,White R J,et al. Application of data fusion techniques and technologies for wearable health monitoring[J]. Medical Engineering&Physics,2017(42):1-12.
[22]赵子傧.仿人跑步机器人稳定性研究[J].电子科技,2017,30(11):89-92.
[23]Kondo Y,Salibian-Barrera M,Zamar R. RSKC:an R package for A robust and sparse k-means clustering algorithm[J]. Journal of Statistical Software,2016,72(5):59-66.