a fall detection algorithm based on pattern recognition and human posture analysis

ISCAS OpenIR

	a fall detection algorithm based on pattern recognition and human posture analysis
	Cheng Huang; Luo Haiyong; Zhao Fang
	2012
会议名称	IET International Conference on Communication Technology and Application, ICCTA 2011
会议录名称	IET Conference Publications
页码	853-857
会议日期	October 14, 2011 - October 16, 2011
会议地点	Beijing, China
收录类别	EI
ISBN	9781849194709
部门归属	(1) Software School Beijing University of Posts and Telecommunications Beijing 100876 China; (2) Institute of Computing Technology Chinese Academy of Sciences Beijing 100876 China
摘要	Detecting fall is a particular important task in security monitoring and healthcare applications of sensor networks. However traditional approaches suffer from either a high false positive rate or high false negative rate, especially when the collected sensor data are unbalanced. Therefore, there is a lack of tradeoff between false alarms and misses for many traditional data mining methods to be applied. To solve this problem a novel fall detection algorithm based on pattern recognition and human posture analysis is presented in this paper. It firstly extracts thirty temporal features from the original data traces for different length adaptation of samples, and then exploits Hidden Markov Model (HMM) to filter the noisy character data and reduce the dimension of feature vectors. After that, it performs a closer classification with one-class Support Vector Machine (OCSVM) to filter the high false positive samples, and finally applies posture analysis to counteract the effects of high false negative samples until a satisfying accuracy is achieved. Simulation with real data demonstrates that the proposed algorithm outperforms other existing approaches.; Detecting fall is a particular important task in security monitoring and healthcare applications of sensor networks. However traditional approaches suffer from either a high false positive rate or high false negative rate, especially when the collected sensor data are unbalanced. Therefore, there is a lack of tradeoff between false alarms and misses for many traditional data mining methods to be applied. To solve this problem a novel fall detection algorithm based on pattern recognition and human posture analysis is presented in this paper. It firstly extracts thirty temporal features from the original data traces for different length adaptation of samples, and then exploits Hidden Markov Model (HMM) to filter the noisy character data and reduce the dimension of feature vectors. After that, it performs a closer classification with one-class Support Vector Machine (OCSVM) to filter the high false positive samples, and finally applies posture analysis to counteract the effects of high false negative samples until a satisfying accuracy is achieved. Simulation with real data demonstrates that the proposed algorithm outperforms other existing approaches.
关键词	Algorithms Communication Data Mining Health Care Pattern Recognition Sensor Networks Signal Detection Support Vector Machines
语种	英语
内容类型	会议论文
URI标识	http://ir.iscas.ac.cn/handle/311060/15965
专题	中国科学院软件研究所
推荐引用方式 GB/T 7714	Cheng Huang,Luo Haiyong,Zhao Fang. a fall detection algorithm based on pattern recognition and human posture analysis[C],2012:853-857.