Activity recognition for Smart City scenarios: Google Play Services vs. MoST facilities

The ever increasing diffusion of smartphones today equipped with several physical and virtual sensors allow to directly collect information about surrounding physical and logical context that range from monitoring current social pulse of individuals and entire communities to detecting user current physical activity. Enabling those advanced sensing capabilities requires complex signal processing, machine learning, and resource management algorithms that are often beyond the skills of many mobile app developers. This paper describes the relevance of these facilities for mobile crowdsensing applications in Smart City scenarios and presents our solution for activity detection, comparing it with the reference implementations provided by Google as part of the Google Play Services library.

[1]  Fanglin Chen,et al.  Unobtrusive sleep monitoring using smartphones , 2013, 2013 7th International Conference on Pervasive Computing Technologies for Healthcare and Workshops.

[2]  Wazir Zada Khan,et al.  Mobile Phone Sensing Systems: A Survey , 2013, IEEE Communications Surveys & Tutorials.

[3]  Emiliano Miluzzo,et al.  A survey of mobile phone sensing , 2010, IEEE Communications Magazine.

[4]  Fan Ye,et al.  Mobile crowdsensing: current state and future challenges , 2011, IEEE Communications Magazine.

[5]  Reza Curtmola,et al.  Fostering participaction in smart cities: a geo-social crowdsensing platform , 2013, IEEE Communications Magazine.

[6]  Norbert Gyorbíró,et al.  An Activity Recognition System For Mobile Phones , 2009, Mob. Networks Appl..

[7]  Rahim Tafazolli,et al.  A survey on smartphone-based systems for opportunistic user context recognition , 2013, CSUR.

[8]  Aiko M. Hormann,et al.  Programs for Machine Learning. Part I , 1962, Inf. Control..

[9]  Zhigang Liu,et al.  The Jigsaw continuous sensing engine for mobile phone applications , 2010, SenSys '10.

[10]  Antonio Corradi,et al.  MSF: An Efficient Mobile Phone Sensing Framework , 2013, Int. J. Distributed Sens. Networks.

[11]  Ian H. Witten,et al.  The WEKA data mining software: an update , 2009, SKDD.