Date of Original Version




Abstract or Description

Context information, including a user’s locations and activities, is indispensable for context-aware applications such as targeted advertising and disaster response. Inferring user context from sensor data is intrinsically challenging due to the semantic gap between low-level signals and high-level human activities. When implemented on mobile phones, more challenges on resource limitations are present. While most existing work focuses on context recognition using a single mobile phone, collaboration among multiple phones has received little attention, and the recognition accuracy is susceptible to phone position and ambient changes. Simply putting a phone in one’s pocket can render the microphone muffled and the camera useless. Furthermore, naïve statistical learning methods used in prior work are insufficient to model the relationship between locations and activities.


Published In

HotMobile '10, Annapolis, M.D..


To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.