A Hybrid Machine Learning Approach for Mobile User Positioning in Cellular Networks

The outstanding growth of location-based services and applications for mobile devices has motivated research about wireless positioning techniques for outdoor and indoor environments. In the present paper, a machine learning approach is proposed for finding the mobile user location. More precisely, a hybrid machine learning technique is proposed to obtain the position of a mobile user in an outdoor environment of cellular networks. The proposal employs k-Nearest Neighbors as a regression model to find the distances between the mobile and the base stations, and Genetic Algorithms to estimate mobile position. Simulation results show that the proposed algorithm has better performance than the COST-231/Nelder-Mead tri- lateration technique. Friedman and Nemenyi tests are used to statistically validate the results.