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.
Computer and Systems Architecture Commons, Data Storage Systems Commons, Digital Circuits Commons, Digital Communications and Networking Commons, Hardware Systems Commons, Other Computer Engineering Commons, Other Electrical and Computer Engineering Commons, Robotics Commons, Systems and Communications Commons, VLSI and Circuits, Embedded and Hardware Systems Commons
HotMobile '10, Annapolis, M.D..