COAL: Context Aware Localization for high energy efficiency in wireless networks

Localization is one of the key enabling technologies for wireless services now penetrating into everyday life. Unfortunately, existing localization schemes are often energy inefficient (such as GPS), or inaccurate (based on signal-distance conversion), or labor intensive (requiring periodic fingerprinting). In this paper we propose a novel localization scheme termed COAL, for COntext Aware Localization, to target at both energy efficiency and accuracy. Our key idea is to leverage users' context information such as an ongoing event to facilitate the localization scheme. By employing these context information, we can significantly reduce localization frequency to conserve energy while maintaining high degree of accuracy. COAL is complementary to existing location schemes using any wireless signal and can be implemented readily as their enhancement. We implement our scheme in iPAQ smart phones using WiFi signals and perform extensive tests in real life and on synthetic data. The results show that the scheme can significantly reduce localization frequency while maintaining high accuracy.