A recurrent neural network for inter-localization of mobile phones

Abstract

The fact that most mobile phones are equipped with short-range communication devices, such as Bluetooth, etc., and a portion of mobile phones have GPS embedded enables us to envision to roughly localize GPS-free phones recursively and progressively by exploiting the available information. With the position of GPS equipped phones as beacons, and with the Bluetooth connection between neighbor phones as proximity constraints, we formulate the problem as an inequality problem defined on the Bluetooth network. A recurrent neural network is developed to solve the problem distributively in real time. The convergence of the neural network and the solution feasibility to the defined problem are both theoretically proven. Two applications examples are considered and simulated. Simulations demonstrate the effectiveness of the proposed method.