A mobile platform for real-time human activity recognition

Author

Lara, Óscar D. ; Labrador, Miguel A.

Author_Institution

Dept. of Comput. Sci. & Eng., Univ. of South Florida, Tampa, FL, USA

fYear

2012

Firstpage

667

Lastpage

671

Abstract

Context-aware applications have been the focus of extensive research yet their implementation in mobile devices usually becomes challenging due to restrictions in regards to processing power and energy. In this paper, we propose a mobile platform to provide real-time human activity recognition. Our system features (1) an efficient library, MECLA, for the mobile evaluation of classification algorithms; and (2) a mobile application for real-time human activity recognition running within a Body Area Network. The evaluation indicates that the system can be implemented in real scenarios meeting accuracy, response time, and energy consumption requirements.

Keywords

behavioural sciences computing; body area networks; mobile computing; pattern classification; MECLA; body area network; classification algorithm; context aware application; energy consumption requirement; energy processing; mobile devices; mobile evaluation of classifier; mobile platform; power processing; real-time human activity recognition; response time; Acceleration; Accuracy; Feature extraction; Mobile communication; Mobile handsets; Sensors; Time factors; Body Area Networks; Human-centric sensing; Machine learning; Mobile applications;

fLanguage

English

Publisher

ieee

Conference_Titel

Consumer Communications and Networking Conference (CCNC), 2012 IEEE

Conference_Location

Las Vegas, NV

Print_ISBN

978-1-4577-2070-3

Type

conf

DOI

10.1109/CCNC.2012.6181018

Filename

6181018