NESL Technical Report #: 2014-11-1
Authors:
Abstract: Indoor localization is poised to catalyze the development of smarter buildings and the creation of reactive indoor spaces, allowing for user-optimized energy expenditure and a more intimate user experience. This paper presents Social Spring, an architecture and corresponding software suite for refining indoor path estimation algorithms. Given an underlying indoor localization scheme, Social Spring attempts to reduce path estimation errors by leveraging encounters between users in real time. The driving concept behind Social Spring is that paths are treated as strings of nodes connected edgewise in a graph, while encounters are treated as additional edges in that graph. Each node attempts to minimize a local potential function dictated by a network of springs, the minimum of which is designed such that nodes converge to a lower energy (equivalently lower error) state. We further provide simulations and preliminary tests on real indoor localization datasets in order to lend credence to Social Spring's effectiveness over a range of environmental factors, demonstrating between 10% and 30% error reduction.
Publication Forum: Proceedings of the 1st ACM International Conference on Embedded Systems for Energy-Efficient Buildings (BuildSys 2014)
Page (Start): 156
Page (End): 159
Page (Count): 4
Date: 2014-11-01
Publisher: ACM
Public Document?: Yes
NESL Document?: Yes
Document category: Conference Paper
Primary Research Area: Pervasive Computing
Back