An Enhanced Neural Network Algorithm using Wi-Fi Fingerprinting

Pervasive positioning provides uninterrupted positional information in both indoor and outdoor locations for a wide spectrum of location based service (LBS) applications. With the rapid enlargement of the low-cost and high speed data communication, Wi-Fi networks in many metropolitan cities, strength of signals broadcasted from the Wi-Fi access points (APs) namely received signal strength (RSS) have been smartly adopted for indoor positioning. In this paper, a Wi-Fi positioning algorithm based on neural network modeling of Wi-Fi signal patterns is planned. This algorithm is based on the associationamong the initial parameter setting for neural network training and output of the mean square error to obtain better exhibiting of the nonlinear highly complex Wi-Fi signal power propagation surface. The test results show that this neural network based data processing algorithm can suggestively improve the neural network training surface to achieve the maximum possible exactness of the Wi-Fi fingerprinting positioning method.