Publication Type

Conference Proceeding Article

Version

Postprint

Publication Date

6-2014

Abstract

The rich context provided by smartphones has enabled many new context-aware applications. However, these applications still need to provide their own mechanisms to interpret low-level sensing data and generate high-level user states. In this paper, we propose the idea of building a personal analytics (PA) layer that will use inputs from multiple lower layer sources, such as sensor data (accelerometers, gyroscopes, etc.), phone data (call logs, application activity, etc.), and online sources (Twitter, Facebook posts, etc.) to generate high-level user contextual states (such as emotions, preferences, and engagements). Developers can then use the PA layer to easily build a new set of interesting and compelling applications. We describe several scenarios enabled by this new layer and present a proposed software architecture. We end with a description of some of the key research challenges that need to be solved to achieve this goal.

Keywords

Human centric contexts, Personal analytics

Discipline

Software Engineering

Research Areas

Software and Cyber-Physical Systems

Publication

WPA'14: Proceedings of the 2014 ACM Workshop on Physical Analytics: June 16, 2014, Bretton Woods, NH

First Page

25

Last Page

29

ISBN

9781450328258

Identifier

10.1145/2611264.2611267

Publisher

ACM

City or Country

New York

Creative Commons License

Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.

Additional URL

http://dx.doi.org/10.1145/2611264.2611267

Share

COinS