基于Android智能手机内i传感器的人运动识别-集成技术-中国.PDF

Vol. 3 No. 3 JOURNAL OF INTEGRATION TECHNOLOGY May 2014 Android 1,2 1 2 3 1 ( 510006) 2 ( 518055) 3 ( 510006) ( ) WEKA J48 3 J48 90.7% J48 J48 TP 391 A Physical Activity Recognition Based on Android Smartphone LIU Jinlei1,2 YUAN Qingke1 LI Ye2 LÜ Xue3 1( College of Mechanical and Electrical Engineering, Guangdong University of Technology, Guangzhou 510006, China ) 2( Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518055, China ) 3( Mechanical-Electrical and Information Engineering, Guangzhou Sontan Polytechnic College, Guangzhou 510006, China ) Abstract In this paper, built-in sensors were described to automatically detect human daily activities. In contrast to the previous work, this paper intends to recognize the physical activities when the phone’s orientation and position are varying. The data collected from six positions of seven subjects were investigated and two signals that are insensitive to orientation were chosen for classification. Decision trees (J48), Naive Bayes and sequential minimal optimization (SMO) were Keywords physical activity recognition; built-in sensors; varying position and orientation; J48 decision tree 2014-03-03 ()E-mail ye.li@ 62 1 2 2.1 I9100