采用运动传感器的人体运动识别深度模型

滕千礼 1; A.ESMAEILI KELISHOMI 1; 2; 蔡忠闽 1; 2

doi:10.7652/xjtuxb201808010

您当前的位置：

首页 >

文章列表页 >

采用运动传感器的人体运动识别深度模型

更新时间：2025-07-09

- 采用运动传感器的人体运动识别深度模型
- A Deep Learning Model for Human Activity Recognition Using Motion Sensor Data
- 西安交通大学学报 2018年52卷第8期页码：60-66+145
- 作者机构：
  
  1. 西安交通大学智能网络与网络安全教育部重点实验室,西安,710049
  2. 西安交通大学电子与信息工程学院,西安,710049
- 作者简介：
- 基金信息：
  
  : 2017-12-15。作者简介: 滕千礼(1994—),男,硕士生;蔡忠闽(通信作者),男,教授,博士生导师。基金项目: 国家自然科学基金资助项目(61772415)
- DOI：10.7652/xjtuxb201808010
  中图分类号： TP301.6;TP391.4
- 网络首发：2018-08-10，
  
  纸质出版：2018
- 稿件说明：
移动端阅览
滕千礼 1, A.ESMAEILI KELISHOMI 1, 2, 等. 采用运动传感器的人体运动识别深度模型[J]. 西安交通大学学报, 2018,52(8):60-66+145.

A Deep Learning Model for Human Activity Recognition Using Motion Sensor Data[J]. 2018, 52(8): 60-66+145.
滕千礼 1, A.ESMAEILI KELISHOMI 1, 2, 等. 采用运动传感器的人体运动识别深度模型[J]. 西安交通大学学报, 2018,52(8):60-66+145. DOI： 10.7652/xjtuxb201808010.

A Deep Learning Model for Human Activity Recognition Using Motion Sensor Data[J]. 2018, 52(8): 60-66+145. DOI： 10.7652/xjtuxb201808010.

摘要

针对传统机器学习方法在采用运动传感器数据的人体运动识别领域中识别效果严重依赖人工特征且准确率受限的问题

提出一种改进的卷积网络与双层长短期记忆网络的深层混合(VGG-LSTM)模型以实现特征自提取并进行运动识别。该模型结合传感器数据层状、时序的结构特点

将多维传感器数据类比于图像的RGB矩阵进行适应性处理; 由一维串联卷积网络与双层长短期记忆网络复合而成。实验结果表明

在开源的人体运动识别(HAR)数据集和无线传感器信息控掘(WISDM)数据集上采用该模型的人体运动识别方法的平均准确率分别达到了97.17%和96.53%

该模型可以有效避免复杂的特征工程

在人体运动识别问题中具有很好的准确性和适应性。

Abstract

An improved deep hybrid HAR model(VGG-LSTM)is proposed to solve the problem that the performances of traditional machine learning methods for human activity recognition(HAR)using motion sensor data are heavily dependent on artificial features

and their accuracies are limited. The model combines a convolutional neural network and a long-short-term-memory network to automatically extract features and to effectively recognize different activities. The proposed method combines multiple modified 1D-convolutional neural networks and two layers of long-short-term-memory networks by comparing the stratified and time-series structure of sensor data with RGB matrix of image. Experiments show that the model achieves average accuracies of 97.17% on the benchmark dataset HAR and 96.53% on the dataset WISDM

and that it effectively avoids complex feature engineering and has a good accuracy in the human activity recognition.

关键词

Keywords

references

AGGARWAL J K. Human activity recognition: a grand challenge [C]∥Proceedings of the International Symposium on Signals, Circuits and Systems. Piscataway, NJ, USA: IEEE, 2007: 1.

VEPAKOMMA P, DE D, DAS S K, et al. A-Wristocracy: deep learning on wrist-worn sensing for recognition of user complex activities [C]∥Proceedings of the International Conference on Wearable and Implantable Body Sensor Networks. Piscataway, NJ, USA: IEEE, 2016: 1-6.

翁汉良, 战荫伟. 基于视觉的多特征手势识别 [J]. 计算机工程与科学, 2012, 34(2): 123-127.

WENG Hanliang, ZHAN Mengwei. Vision-based hand gesture recognition with multiple cues [J]. Computer Engineering and Science, 2012, 34(2): 123-127.

WANG A, CHEN G, YANG J, et al. A comparative study on human activity recognition using inertial sensors in a smartphone [J]. IEEE Sensors Journal, 2016, 16(11): 4566-4578.

卢先领, 王洪斌, 王莹莹, 等. 一种基于加速度传感器的人体跌倒识别方法 [J]. 计算机应用研究, 2013, 30(4): 1109-1111.

LU Xianling, WANG Hongbin, WANG Yingying, et al. Human falling detection based on accelerometer [J]. Application Research of Computers, 2013, 30(4): 1109-1111.

BULLING A, BLANKE U, SCHIELE B. A tutorial on human activity recognition using body-worn inertial sensors [J]. ACM Computing Surveys, 2014, 46(3): 1-33.

ANGUITA D, GHIO A, ONETO L, et al. Training computationally efficient smartphone—based human activity recognition models [C]∥ Proceedings of the 2013 Artificial Neural Networks and Machine Learning. Berlin, Germany: Springer, 2013: 426-433.

BANOS O, TOTH M A, DAMAS M, et al. Dealing with the effects of sensor displacement in wearable activity recognition [J]. Sensors, 2014, 14(6): 9995-10023.

KRIZHEVSKY A, SUTSKEVER I, HINTON G E. ImageNet classification with deep convolutional neural networks [C] ∥Proceedings of the 2012 International Conference on Neural Information Processing Systems. New York, USA: ACM, 2012: 1097-1105.

RONAO C A, CHO S B. Human activity recognition with smartphone sensors using deep learning neural networks [J]. Expert Systems with Applications, 2016, 59(C): 235-244.

ORDONEZ F J, ROGGEN D. Deep convolutional and LSTM recurrent neural networks for multimodal wearable activity recognition [J]. Sensors, 2016, 16(1): 115.

SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition [EB/OL].(2015-04-10)[2017-11-12]. http:∥arxiv.org/pdf/1409.1556v6.pdf.

GOODFELLOW I, YOSHUA B, AARON C. Deep learning [M]. 1st ed. Cambridge, MA, USA: MIT Press, 2015: 294-295.

LECUN Y, BOTTOU L, BENGIO Y, et al. Gradient-based learning applied to document recognition [J]. Proceedings of the IEEE, 2001, 86(11): 2278-2324.

KINGMA D P, BA J. Adam: a method for stochastic optimization [EB/OL].(2015-07-23)[2017-11-12]. http:∥arxiv.org/pdf/1412.6980v8.pdf.

SRIVASTAVA N, HINTON G, KRIZHEVSKY A, et al. Dropout: a simple way to prevent neural networks from overfitting [J]. Journal of Machine Learning Research, 2014, 15(1): 1929-1958.

ANGUITA D, GHIO A, ONETO L, et al. Human activity recognition on smartphones using a multiclass hardware-friendly support vector machine [C]∥ Proceedings of the 4th International Conference on Ambient Assisted Living and Home Care. Berlin, Germany: Springer, 2012: 216-223.

ABADI M, AGARWAL A, BARHAM P, et al. TensorFlow: large-scale machine learning on heterogeneous distributed systems [EB/OL].(2016-03-14)[2017-11-21]. http: ∥arxiv.org/pdf/1603.04467v1. pdf.

KWAPISZ J R, WEISS G M, MOORE S A. Activity recognition using cell phone accelerometers [J]. ACM SIGKDD Explorations Newsletter, 2011, 12(2): 74-82.

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

结构-语义-残差协同的图像压缩框架：面向隐私保护与高保真重建

不同板叠材料热声热机能量转换过程数值模拟研究

扇贝仿生密封腔室内超临界二氧化碳泄漏流湍动能耗散机理研究

EBSILON软件在热电联产系统优化中的应用综述

超临界二氧化碳向心透平轮背间隙内风阻损失及流动特性研究