Multi-layer neural network for received signal strength-based indoor localisation

In received signal strength (RSS)-based indoor wireless localisation system, radio pathloss model or radio map must be readily obtainable. However, the unpredictability of wireless channel makes it difficult to achieve high accuracy localisation in practice. In this study, the authors employed a multi-layer neural network (MLNN) for RSS-based indoor localisation without using the radio pathloss model or comparing the radio map. The proposed MLNN localisation system integrate the RSS signals transforming section, the raw data denoising section and the node locating section into a deep architecture. Furthermore, a boosting method is designed to promote location accuracy of the MLNN effectively. Experiment results demonstrate the feasibility and suitability of the proposed algorithm.