基于核函数的在线序列ELM算法的姿态识别

韩莹; 张浩; 刘健; 陈立平

Chinese

您当前的位置：

首页 >

文章列表页 >

基于核函数的在线序列ELM算法的姿态识别

更新时间：2026-09-04

- 基于核函数的在线序列ELM算法的姿态识别
- Activity Recognition Based on Online Sequential Kernel Extreme Learning Machine
- 微电子学与计算机 2018年35卷第1期页码：91-95
- 作者机构：
  
  1. 中国科学院机构微电子研究所,北京,100029
  2. 北京科技大学计算机与通信工程学院,北京,100029
- 作者简介：
- 基金信息：
  
  国家重大专项 2015ZX03001013-002
- DOI：
  中图分类号：
- 纸质出版：2018
- 稿件说明：
移动端阅览
韩莹, 张浩, 刘健, 陈立平. 基于核函数的在线序列ELM算法的姿态识别[J]. 微电子学与计算机, 2018, 35(1): 91-95.

HAN Ying, ZHANG Hao, LIU Jian, et al. Activity Recognition Based on Online Sequential Kernel Extreme Learning Machine[J]. 2018, 35(1): 91-95.
韩莹, 张浩, 刘健, 陈立平. 基于核函数的在线序列ELM算法的姿态识别[J]. 微电子学与计算机, 2018, 35(1): 91-95. DOI：

HAN Ying, ZHANG Hao, LIU Jian, et al. Activity Recognition Based on Online Sequential Kernel Extreme Learning Machine[J]. 2018, 35(1): 91-95. DOI：

摘要

姿态识别是许多应用的基础(医学、运动、游戏、安全).传统的识别算法采用批学习的方式去训练网络

但是数据量庞大且数据不会一次性获取

这会导致这类算法花费大量的学习时间且网络权重也不能在线更新.对此利用一种基于核函数的在线序列极限学习机OS-KELM (Online Sequential Kernel Extreme Learning Machine)算法实现人体姿态的分类识别.为降低学习难度和提高学习效率

使用了基于Fisher准则和特征聚类的方法进行特征选择.用手机的三轴加速度计和陀螺仪数据识别人走路、下楼、上楼、站立、坐和躺下的姿态

平均识别精度达到91.89%.

Abstract

Activity recognition (AR) is the basis for many applications concerning health care

sports

security and gaming industry. Traditionally

batching learning recognition algorithms is adopted to train network. However

the amount of data is considerable and not all training data arrives instantly

the learning procedure is time-consuming and the network weights cannot be updated online. In this paper

Classification of the human activities is performed with Online Sequential Kernel Extreme Learning Machine (OS-KELM). The method of feature selection based on Fisher criterion and feature clustering has been adopted to reduce difficulty and improve efficiency of learning. A tri-axial accelerometer and gyros data from a users smart phone are used to recognize walking

waling downstairs

walking upstairs

standing

sitting and laying. Experimental results with an average accuracy of 91.89% are achieved.

关键词

Keywords

references

Al Jeroudi Y, Ali M A, Latief M, et al. Online sequential extreme learning machine algorithm based human activity recognition using inertial data[C]//Control Conference (ASCC), 2015 10th Asian. IEEE, 2015: 1-6.

Perez A J, Labrador M A, Barbeau S J. G-sense: a scalable architecture for global sensing and monitoring[J]. IEEE Network, 2010, 24 (4): 57-64. DOI: 57

Anguita D, Ghio A, Oneto L, et al. A public domain dataset for human activity recognition using smartphones[C]//ESANN. Bruges, 2013.

Huang G B, Zhu Q Y, Siew C K. Extreme learning machine: theory and applications[J]. Neurocomputing, 2006, 70(1): 489-501. DOI: 489

Liu Z G, Song Y N, Shang Y. Posture recognition algorithm for theelderly based on BP neural networks[C]// Proceedings of 27th Control and Decision Conference (CCDC). IEEE, 2015: 1447-1449.

Deng W Y, Ong Y S, Tan P S, et al. Online sequential reduced kernel extreme learning machine[J]. Neurocomputing, 2016, 174: 72-84. DOI: 72

Shi X, Xiong Q Y, Lei L N. Fall detection system based on pressure sensor[J]. Chinese Journal of Scientific Instrument, 2010, 31(3): 715-720. DOI: 715

Huang G B, Zhou H, Ding X, et al. Extreme learning machine for regression and multiclass classification[J]. IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 2012, 42(2): 513-529. DOI: 513

王飒, 郑链. 基于Fisher准则和特征聚类的特征选择[J]. 计算机应用, 2007, 27(11): 2812-2813. DOI: 2812

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

超低功耗实时时钟电路的设计

基于区块链的AI生成内容溯源框架设计研究

注意力机制与改进密集卷积引导的信息隐藏模型

基于反向体偏置的高增益稳定性高温运放设计

V型沟槽SiC中子探测器的蒙特卡洛分析