Study on human gait recognition based on cell phone acceleration sensor

DUAN Xiaohu; JIANG Gang; LIU Canghai

doi:10.13873/J.1000-9787(2021)01-0030-04

Chinese

您当前的位置：

首页 >

文章列表页 >

Study on human gait recognition based on cell phone acceleration sensor

更新时间：2025-09-11

- Study on human gait recognition based on cell phone acceleration sensor
- Vol. 40, Issue 1, Pages: 30-33+38(2021)
- 作者机构：
  
  西南科技大学制造科学与工程学院
- 作者简介：
- 基金信息：
- DOI：10.13873/J.1000-9787(2021)01-0030-04
  CLC： TP212.9
- Published：2021
- 稿件说明：
移动端阅览
[1]段小虎,蒋刚,留沧海.基于手机加速度传感器的人体步态识别研究[J].传感器与微系统,2021,40(01):30-33+38.

DUAN Xiaohu, JIANG Gang, LIU Canghai. Study on human gait recognition based on cell phone acceleration sensor[J]. 2021, 40(1): 30-33+38.
[1]段小虎,蒋刚,留沧海.基于手机加速度传感器的人体步态识别研究[J].传感器与微系统,2021,40(01):30-33+38. DOI： 10.13873/J.1000-9787(2021)01-0030-04.

DUAN Xiaohu, JIANG Gang, LIU Canghai. Study on human gait recognition based on cell phone acceleration sensor[J]. 2021, 40(1): 30-33+38. DOI： 10.13873/J.1000-9787(2021)01-0030-04.

摘要

使用福坦莫大学无线数据挖掘实验室（WISDM）利用手机采集的人体步态数据集

以支持向量机（SVM）、K最近邻（KNN）和随机森林算法实现对人体步态的识别。对加速度的时间序列进行分窗和均值平滑处理。以2 s作为窗口大小

提取三轴加速数据的均值、方差和协方差作为样本特征。采用以上算法对样本的六种类别（步行、慢跑、上楼梯、下楼梯、静坐、站立）进行训练和测试

并进行了准确率、曲线下面积AUC等分析以及实验验证。与其它特征提取方法和深度学习方法相比

提取统计量作为特征方法简单和模型计算量较小。其线性核函数SVM的平均准确率可达81.3%。

Abstract

Human gait dataset of Wireless Data Mining Laboratory of Fordham University（WISDM） collected by mobile phone is used.Realizing the recognition of human gait by support vector machine（SVM）

K nearest neighbour（KNN） and random forest algorithm.The time series of acceleration is processed by windowing and mean smoothing.Taking 2 s as window size

the mean

variance and covariance of triaxial acceleration data are extracted as sample features.The six types of samples（walking

jogging

upstairs

downstairs

sitting

standing） are trained and tested by the above algorithm

and the accuracy

AUC analysis and experimental verification are carried out.Compared with other feature extraction methods and deep learning methods

the method of extracting statistics as feature is simpler and the computational complexity of model is smaller.The average accuracy of linear kernel SVM is 81.3 %.

关键词

Keywords

references

基于CNN与SVM融合的步态识别方法 [J]. 张加加,王修晖. 中国计量大学学报 . 2019(01)

基于多传感器的人体运动模式识别 [J]. 张乾勇,张涛,赵治羽. 传感器与微系统 . 2019(02)

特征融合的多视角步态识别研究 [J]. 王竣,王修晖. 中国计量大学学报 . 2017(02)

基于Kinect的下肢体康复动作评估系统 [J]. 杨文璐,王杰,夏斌,谢宏. 传感器与微系统 . 2017(01)

单人行走运动参数估计方法 [J]. 孙忠胜,王俊,孙进平,张耀天,袁常顺,向洪. 北京航空航天大学学报 . 2016(04)

一种基于三维加速度传感器的人体行为识别方法 [J]. 徐川龙,顾勤龙,姚明海. 计算机系统应用 . 2013(06)

基于可穿戴设备的人体行为识别与状态监测方法研究 [D]. 杨伟笃. 哈尔滨工业大学 2016

基于三维加速度传感器的人体行为识别 [D]. 徐川龙. 浙江工业大学 2013

Recognition of human activities using SVM multi-class classifier [J] . Huimin Qian,Yaobin Mao,Wenbo Xiang,Zhiquan Wang. Pattern Recognition Letters . 2009 (2)

Using acceleration measurements for activity recognition: An effective learning algorithm for constructing neural classifiers [J] . Jhun-Ying Yang,Jeen-Shing Wang,Yen-Ping Chen. Pattern Recognition Letters . 2008 (16)

Support-Vector Networks [J] . Corinna Cortes,Vladimir Vapnik. Machine Learning . 1995 (3)

Views

139

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Structure optimization and simulation analysis of high-range acceleration sensor

Design of wearable fetal movement signal acquisition system

Design of novel dual-axis capacitive acceleration sensor

Fetal movement signal detection method based on multi-acceleration sensor

Theoretical modeling and response analysis of acceleration sensor installation mode

Related Author

HAN Wenman

GUO Tao

LIU Xi-heng

WU Wei

PU Zhi-min

FENG Yu-ting

ZHU Bin-bin

WANG Lu-wen

Related Institution

Micron Nanotechnology Research Center of North University of China

School of Electronic Information, Hangzhou Dianzi University

Institute of Micro-electronics CAD,Hangzhou Dianzi University

cole Nationale Supérieure des Arts et Industries Textiles

School of Internet of Things Engineering,Jiangnan University

⁰