An Extensible Pervasive Platform for Large-Scale Anticipatory Mobile Computing

Anticipatory mobile computing is an emerging research field in pervasive environments. However, building multiple anticipatory applications to proactively support a user on his behalf still involves a disproportionate effort through their interdisciplinary nature and individual complex development from scratch. In this paper, we present architectural concepts and a reference implementation of a distributed platform acting as base frame for various anticipatory mobile applications to provide cooperative personal assistants. We demonstrate that our proof of concept prototype enables fast and time-saving development of various cooperating intelligent assistants through a hierarchical modular approach. We further show that this approach makes energy-efficient mobile applications currently available for iOS and Android possible while the platform is horizontal scalable to growing number of users and assistance use cases. Feedback from end-users and researchers indicates a high user experience for using our apps and developing new assistants. Our proposed open source platform provides the scaffolding for future research in personal collaborative assistance systems which proactively guide and autonomously support users.

[1]  Mirco Musolesi,et al.  Trajectories of depression: unobtrusive monitoring of depressive states by means of smartphone mobility traces analysis , 2015, UbiComp.

[2]  E. Brewer,et al.  CAP twelve years later: How the "rules" have changed , 2012, Computer.

[3]  BJ Fogg,et al.  Creating persuasive technologies: an eight-step design process , 2009, Persuasive '09.

[4]  Mi Zhang,et al.  MyBehavior: automatic personalized health feedback from user behaviors and preferences using smartphones , 2015, UbiComp.

[5]  Francis Heylighen,et al.  Complexity and Information Overload in Society: why increasing efficiency leads to decreasing control , 2002 .

[6]  Benedikt Schmidt,et al.  Fitness tracker or digital personal coach: how to personalize training , 2015, UbiComp/ISWC Adjunct.

[7]  Christian Becker,et al.  A survey of proactive pervasive computing , 2014, UbiComp Adjunct.

[8]  Silvia Santini,et al.  The influence of temporal and spatial features on the performance of next-place prediction algorithms , 2013, UbiComp.

[9]  Max Mühlhäuser,et al.  Labels: quantified self app for human activity sensing , 2015, UbiComp/ISWC Adjunct.

[10]  Ramachandran Ramjee,et al.  PRISM: platform for remote sensing using smartphones , 2010, MobiSys '10.

[11]  Mirco Musolesi,et al.  Anticipatory Mobile Computing , 2013, ACM Comput. Surv..

[12]  James H. Aylor,et al.  Computer for the 21st Century , 1999, Computer.

[13]  J. B. Brooke,et al.  SUS: A 'Quick and Dirty' Usability Scale , 1996 .

[14]  Feng Xu,et al.  ConRec: A Software Framework for Context-Aware Recommendation Based on Dynamic and Personalized Context , 2015, 2015 IEEE 39th Annual Computer Software and Applications Conference.

[15]  Cecilia Mascolo,et al.  Smartphones for Large-Scale Behavior Change Interventions , 2013, IEEE Pervasive Computing.

[16]  Mirco Musolesi,et al.  Anticipatory Mobile Digital Health: Towards Personalised Proactive Therapies and Prevention Strategies , 2015, ArXiv.

[17]  Max Mühlhäuser,et al.  Kraken.me mobile: The energy footprint of mobile tracking , 2014, 6th International Conference on Mobile Computing, Applications and Services.