An Improved Neural Network Training Algorithm for Wi-Fi Fingerprinting Positioning

Abstract

Abstract:Ubiquitous positioning provides continuous positional information in both indoor and outdoor environments for a wide spectrum of location based service (LBS) applications. With the rapid development of the low-cost and high speed data communication, Wi-Fi networks in many metropolitan cities, strength of signals propagated from the Wi-Fi access points (APs) namely received signal strength (RSS) have been cleverly adopted for indoor positioning. In this paper, a Wi-Fi positioning algorithm based on neural network modeling of Wi-Fi signal patterns is proposed. This algorithm is based on the correlation between the initial parameter setting for neural network training and output of the mean square error to obtain better modeling of the nonlinear highly complex Wi-Fi signal power propagation surface. The test results show that this neural network based data processing algorithm can significantly improve the neural network training surface to achieve the highest possible accuracy of the Wi-Fi fingerprinting positioning method.

WI-FI Based Indoor Positioning Using Fingerprinting Methods (KNN Algorithm) in Real Environment

“…Same as the previous model, the highest accurate rate was achieved when K=7 with the least MSE value. In comparison with Mok and Cheung [13] model, this model achieved higher accuracy. For 4 APs model, the most precise result occurred when K=7 and K=11 with 74% and 72% accuracy respectively.…”

“…But the interesting point is that the fluctuation of result is similar to 4 APs model. According to Mok and Cheung [13], by increasing APs, the accuracy increased, since the number of inputs is increased so we can get better accuracy with increasing value of MSE compared to 4 APs model. This is because by increasing the input data, more noises included, thus produces more error.…”

“…On the other hand if the value of K is larger, then there is higher bias, so choosing the proper K depends on the data. The approach applied and the result for K=2, 3,5,7,11,13,17,19 Figure 8. The distance between estimated position and real position in testing dataset was calculated for each value of K, and then the average of error was calculated as a Mean Square Error (MSE) for various value of K. The MSE is calculated by:…”

Indoor Mobile Positioning Using Neural Networks and Fuzzy Logic Control

“…In Ref. [10], the model of context-aware computing (context-dependent browser) based on network proximity is considered. This mobile phone is considered as a proximity sensor and geo replaced positional information network proximity.…”

“…The approach to the use of ANN to solve the above problem is considered in several publications, for example, Refs. [10][11][12].…”