高技术通讯2017，Vol.27Issue(3)：228-236,9.DOI:10.3772/j.issn.1002-0470.2017.03.005
半监督极限学习机用于Android手机活动识别的研究
Study of applying semi-supervised extreme learning machines to activity recognition using Android phones
摘要
Abstract
Based on the analysis of the existing techniques for activity recognition using Android phones, the semi-supervised(SS) learning capable of raising the recognition accuracy and speed based on unlabeled samples was combined with the extreme learning machine (ELM) reflecting the effective learning mechanism of pattern classification regression to give a SS-ELM method to solve the activity recognition on the Android mobile platform to solve the difficult problem of extrapolating human activity from incomplete,inadequate mobile sensor data.Furthermore, based on combining principal component analysis (PCA), a new method,called the SS-ELM, was proposed. The experimental results show that the novel method is feasible and its recognition accuracy can reach 95%, better than that of the recently proposed method of mixture-of-experts.关键词
活动识别/半监督极限学习机(SS-ELM)/传感器/加速度计/Android手机Key words
activity recognition/semi-supervised extreme learning machine (SS-ELM)/sensor/accelerometer/Android phone引用本文复制引用
王金甲,田佩佩..半监督极限学习机用于Android手机活动识别的研究[J].高技术通讯,2017,27(3):228-236,9.基金项目
国家自然科学基金(61273019,61473339),河北自然科学基金(F2013203368),河北省青年拔尖人才支持计划([2013]17),河北省博士后专项(B2014010005)和中国博士后科学基金(2014M561202)资助项目. （61273019,61473339）
