Artificial Neural Network Approach to Mobile Location Estimation in GSM Network

Abstract

The increase in utilisation of mobile location-based services (LBS) for commercial, safety and security purposes among others are the key drivers for improving location estimation accuracy to better serve those purposes. Hence, developing mobile location estimation with high accuracy has been an issue of a major research concern as so many methods have been proposed. Among these methods include Cell ID, global positioning system (GPS), fingerprinting, statistical, geometrical, angle, time based and recently artificial intelligence methods. The GPS techniques have offered superior measurement accuracy to others but suffer accuracy degradation in indoor and dense urban area due to non-line of sight (NLOS) propagation. This paper proposes the application of Levenberg Marquardt (LMA) training algorithm on new robust multilayered perceptron (MLP) neural network architecture for mobile positioning fitting for the urban area in the considered GSM network using received signal strength (RSS). The key performance metrics such as accuracy, cost, reliability and coverage are the major points considered in this paper. The technique was evaluated through a simulation using real data from field measurement and the results obtained proved the proposed model provides a practical positioning that meet Federal Communication Commission (FCC) accuracy requirement.