计算机工程与应用2016，Vol.52Issue(23)：1-5,49,6.DOI:10.3778/j.issn.1002-8331.1606-0084
基于智能手机传感器数据的人类行为识别研究
Human activity recognition with smartphone sensor data
摘要
Abstract
Recognition of human activity from the smartphone of sensory data has many important applications in many fields, such as healthcare services, intelligent environments and cyber security. Classification accuracy of most existed methods is not enough in many applications, especially for healthcare services. In order to improve accuracy, the paper proposes a Random Forest(RF)approach to recognize human activities and choose Sparse Local Preserving Projection (SpLPP)as the method of feature reduction. Firstly, the optimal feature subsets are determined by LPP. Secondly, the results of activity recognition are classified by RF ensemble classifier. Compared with other methods, the method uses the significantly less number of features, and the over-all accuracy has been increased.关键词
人类行为识别/随机森林/稀疏局部保持投影/智能手机Key words
human activity recognition/random forest/sparse locality preserving projections/smartphone分类
信息技术与安全科学引用本文复制引用
朱响斌,邱慧玲..基于智能手机传感器数据的人类行为识别研究[J].计算机工程与应用,2016,52(23):1-5,49,6.基金项目
国家自然科学基金（No.61402418，No.61170108，No.61503342）；教育部人文社科研究项目（No.12YJCZH142，No.15YJC-ZH125）；浙江省公益技术研究社会发展项目（No.2016C33168）；浙江省自然科学基金（No.LY13F020017，No.LY15F020013， No.LQ13F020007，No.LY16F030002，No.LQ16F020002）；信息网络安全公安部重点实验室一般项目资助（No.C15610）；上海市信息安全综合管理技术研究重点实验室开放基金（No.AGK2013003）。 （）
