Skip to main content
SensOrchestra: Collaborative Sensing for Symbolic Location Recognition
Silicon Valley Campus
  • Heng-Tze Cheng, Carnegie Mellon University
  • Feng-Tso Sun, Carnegie Mellon University
  • Senaka Buthpitiya, Carnegie Mellon University
  • Martin L Griss, Carnegie Mellon University
Date of Original Version
Abstract or Description
"Symbolic location of a user, like a store name in a mall, is essential for context-based mobile advertising. Existing fingerprint- based localization using only a single phone is susceptible to noise, and has a major limitation in that the phone has to be held in the hand at all times. In this paper, we present SensOrchestra, a col- laborative sensing framework for symbolic location recognition that groups nearby phones to recognize ambient sounds and images of a location collaboratively. We investigated audio and image features, and designed a classifier fusion model to integrate estimates from diff erent phones. We also evaluated the energy consumption, band- width, and response time of the system. Experimental results show that SensOrchestra achieved 87.7% recognition accuracy, which reduces the error rate of single-phone approach by 2X, and eliminates the limitations on how users carry their phones. We believe general location or activity recognition systems can all benefifit from this collaborative framework."
Citation Information
Heng-Tze Cheng, Feng-Tso Sun, Senaka Buthpitiya and Martin L Griss. "SensOrchestra: Collaborative Sensing for Symbolic Location Recognition" (2010)
Available at: