An RSS-based regression model for user equipment location in cellular networks using machine learning

Dissemination of wireless networks and mobile devices, such as smartphones, has motivated the appearance of several types of location-based services. Consequently, the interest in low-complexity cost-effective mobile positioning techniques against the traditional method based on global positioning system has emerged. An interesting alternative is to utilize radio frequency (RF) signals to estimate the location of mobile terminals, as in multilateration and RF fingerprinting techniques. In this context, the objective of this work is to propose a new radio strength signal-based user equipment location method using a machine learning regression-based model to find directly the geographical coordinates of the mobile user in cellular networks. Numerical results show that, in most cases, the proposed method can meet the location accuracy requirements established by the Federal Communications Commission for network-based localization methods.