Human Activity Recognition Using Smartphone Sensor Data Via Deep Neural Networks

CORC > 重庆绿色智能技术研究院 > 中国科学院重庆绿色智能技术研究院 > 高性能计算应用研究中心

	Human Activity Recognition Using Smartphone Sensor Data Via Deep Neural Networks
	Chen, Yuwen; Zhong, Kunhua
	2015
会议日期	DEC 26-27, 2015
会议地点	Sanya, PEOPLES R CHINA
页码	348-353
通讯作者	Chen, YW (reprint author), Chinese Acad Sci, Chongqing Inst Green & Intelligent Technol, Beijing, Peoples R China.
英文摘要	Human activity recognition on smartphones is a relatively new area. Smartphones are equipped with a variety of sensors. Fusing the data of these sensors could enable applications to recognize a large number of activities. Realizing this goal is challenging, however. In this paper, we captured 3-axial linear acceleration and 3-axial gyroscope data, from which 561 features are generated in both time and frequency domain. Then the deep neural networks approach is employed to recognize 6 activities, comparing with other different learning methods, ie. Decision Trees methods, support vector machine and Naive Bayes methods. Experiment results show that the classification rate of deep neural network reaches 0.98, which has the highest accuracy.
会议录	2015 INTERNATIONAL CONFERENCE ON COMPUTATIONAL SCIENCE AND ENGINEERING APPLICATIONS (CSEA 2015)
语种	英语
WOS记录号	WOS:000380291000059
内容类型	会议论文
源URL	[http://119.78.100.138/handle/2HOD01W0/385]
专题	高性能计算应用研究中心
作者单位	(1) Chinese Acad Sci, Chongqing Inst Green & Intelligent Technol, Beijing, Peoples R China
推荐引用方式 GB/T 7714	Chen, Yuwen,Zhong, Kunhua. Human Activity Recognition Using Smartphone Sensor Data Via Deep Neural Networks[C]. 见:. Sanya, PEOPLES R CHINA. DEC 26-27, 2015.