Enabling Usage Pattern-based Logical Status Inference for Mobile Phones

<p>Logical statuses of mobile users, such as isBusy and isAlone, are the key enabler for a plethora of context-aware mobile applications. While on-board hardware sensors (such as motion, proximity, and location sensors) have been extensively studied for logical status inference, continuous usage typically requires formidable energy consumption, which degrades the user experience. In this thesis, we argue that smartphone usage statistics can be used for logical status inference with negligible energy cost. To validate this argument, we present a continuous inference engine that (1) intercepts multiple operating system events, in particular foreground app, notifications, screen states, and connected networks; (2) extracts informative features from OS events; and (3) efficiently</p> <p>infers the logical status of mobile users. The proposed inference engine is implemented</p> <p>for unmodified Android phones, and an evaluation on a four-week trial has shown promising accuracy in identifying four logical statuses of mobile users with over 87% accuracy while the average energy impact on the battery life is less than 0.5%.</p>

Name thesis:degree_name

Master of Science in Computer Science (MS)

Level thesis:degree_level

Thesis

Year dc:date.available

2016

Author dc:creator

• Hammer, Jon C.

Advisor dc:contributor.advisor

• Yan, Tingxin

Contributors dc:contributor

• Gashler, Michael S.
• Gauch, John M.

• Applied sciences
• Logical status inference
• Mobile computing
• Usage statistics
• Graphics and Human Computer Interfaces

Repository record dc:identifier

https://scholarworks.uark.edu/etd/1552

OAI identifier oai:identifier

oai:scholarworks.uark.edu:etd-3091