高技术通讯2017，Vol.27Issue(7)：604-611,8.DOI:10.3772/j.issn.1002-0470.2017.07.003
用于Android手机活动识别的深度重构模型
Deep reconstruction models for activity recognition using Android Phones
摘要
Abstract
The activity recognition using Android phones is studied based on the assumption of the manifold-shaped data, and a deep reconstruction model ( DRM) which can learn the complex nonlinear curved surface structure and geo-metric features of current class samples without a priori assumption of basic geometry is proposed.Firstly, a tem-plate of the DRM is defined, and its parameters are initialized by performing the unsupervised pre-training in a lay-er-wise fashion using Gaussian restricted Boltzmann machines.In the training stage, the initialized DRM template is then separately trained for training the samples of each class and the class-specific DRMs are learnt.In the tes-ting stage, activities are recognized based on the minimum reconstruction error between the learnt class-specific models and the test samples.The experiment performed using the Android mobile phone dataset show that the cor-rect rate of this method for activity recognition is up to 99%.关键词
活动识别/深度重构模型/自动编码器/Android手机/高斯受限玻尔兹曼机(GRBMs)Key words
activity recognition/deep reconstruction model ( DRM)/auto-encoder/Android mobile phone/Gaussian restricted Boltzmann machines ( GRBMs)引用本文复制引用
王金甲,田佩佩..用于Android手机活动识别的深度重构模型[J].高技术通讯,2017,27(7):604-611,8.基金项目
国家自然科学基金(61273019,61473339),河北省自然科学基金(F2013203368),河北省青年拔尖人才支持计划([2013]17),河北省博士后专项资助项目(B2014010005)和中国博士后科学基金面上项目(2014M561202)资助. （61273019,61473339）
