Learning Location From Sequential Signal Strength Based on GSM Experimental Data

Abstract

This study proposes two positioning algorithms, called the focused time delay neural network (FTDNN) and the distributed time delay neural network (DTDNN), to efficiently learn the mobile location from sequential received signal strength (RSS). By embedding the temporal structures of RSS into the spatial structures of networks, the proposed algorithms can extract location information from temporal variation of RSSs rather than removing them. This study applies the proposed algorithms to actual Global System for Mobile communications (GSM) networks, collecting realistic RSS measurements across a campus using commercially available mobile phones. On-site experiments clearly demonstrated that both algorithms provide better positioning accuracy than the traditional Cell-ID method, the Bayesian approach, and the multilayer perceptron with variations, where DTDNN achieves the best performance.