Multiple Classifier Based Walking Pattern Recognizing Algorithm Using Acceleration Signals

LI Yue-xiang; LIU Yan; YUAN Tao; WANG Wen-jian

您当前的位置：

首页 >

文章列表页 >

Multiple Classifier Based Walking Pattern Recognizing Algorithm Using Acceleration Signals

更新时间：2025-07-16

- Multiple Classifier Based Walking Pattern Recognizing Algorithm Using Acceleration Signals
- Acta Electronica Sinica Vol. 37, Issue 8, Pages: 1794-1798(2009)
- 作者机构：
  
  1. 山西大学计算机与信息技术学院,山西,太原,030006
  2. 清华大学自动化系,北京,100084
  3. 山西大学计算机与信息技术学院山西太原,030006
  4. 清华大学自动化系北京,100084
- 作者简介：
- 基金信息：
- DOI：
  CLC： TP391.4
- Published：2009
- 稿件说明：
移动端阅览
LI Yue-xiang, LIU Yan, YUAN Tao, et al. Multiple Classifier Based Walking Pattern Recognizing Algorithm Using Acceleration Signals[J]. Acta Electronica Sinica, 2009, 37(8): 1794-1798.
DOI：

LI Yue-xiang, LIU Yan, YUAN Tao, et al. Multiple Classifier Based Walking Pattern Recognizing Algorithm Using Acceleration Signals[J]. Acta Electronica Sinica, 2009, 37(8): 1794-1798. DOI：

摘要

研究了一种基于多级分类模型的非特定人走路模式识别算法

实现了对水平行走和上、下楼梯三种运动状态的识别.将装有微型加速度传感器的无线数据采集装置固定于人体后腰部

获取运动时的三维步态加速度信号.采用离散小波变换提取与运动相关频带的时频特征

并结合步频以及垂直方向和前进方向加速度信号之间的互相关性

经过特征融合设计了多级分类识别算法.通过对10个人共360组数据的测试结果表明:在步频范围扩大到1~3Hz时

识别率达到了96.1%

且对测试对象的依赖性小.

Abstract

This paper presented the multiple classifier based walking pattern recognition algorithm

which could identify three walking patterns:horizontal walking

up and down staircase walking.Three-dimensional accelerations during walking were acquired from the wireless accelerometer device fixed on the back waist.The discrete wavelet transformation was applied for time-frequency analysis.The time-frequency features associated with the main frequency band of the motion

walking cadence and the correlation between the vertical and forward acceleration signals were combined to design a multiple classifier.A set of 360 gait samples involving 10 people were used for test

giving an overall recognition accuracy for 96.1% when the walking cadence range was within 1~3Hz

and this algorithm was less dependent on individuals.

关键词

Keywords

references

Views

1136

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

A Rapid and Effective Method for Shot Boundary Detection

Clutter Reduction Based on Polarization Imaging Technology and Image Fusion Theory

Wavelet Coefficients Generalized Gaussian Distribution Image Retrieval Algorithm Based on Shape

Related Author

WEN Cheng-lin

LUO Zhi-zeng

LI Zhong-ning

FENG Song-he

XU De

GENG Yu-liang

ZHAO Yong-qiang

PAN Quan

Related Institution

Department of MathematicsHenan UniversityKaifeng 475001China

Department of Mathematics,Henan University

Robotics Research Institute,Hangzhou Dianzi University

Institute of Computer Science and Engineering,Beijing Jiaotong University

College of Automatization,Northwest Ploytechnic University,Xian,Shannxi

⁰