FUZZY LOGIC AND NEURAL NETWORK BASED INDOOR FINGERPRINT POSITIONING ALGORITHMS IN WiFi

In this paper, a method that uses RBF-BP neural network to generate fingerprint database (FD) is proposed to improve the quality. The reference points in the database present regular tetrahedron distribution in three-dimensional space. To improve the accuracy of selecting which points are considered to locate currently and estimating their weights, two positioning algorithms based on signal strength difference values (SSDV) are proposed through analyzing the characteristic of difference values between mobile receiver and reference points. The first one is fuzzy logic algorithm (FLA). It uses different fuzzy logic models to calculate the weights of considered points. The second one is RBF-BP neural network algorithm (NNA). It uses different neural network models to estimate the spatial distances between mobile receiver and reference points. The points which have small sum of distances are considered. Their weights are calculated by a newly proposed method. The proposed algorithms use more than one weight to describe the distance to one considered point, which is more accurate. The test results demonstrate the improvement and effectiveness of proposed methods by comparing with other existing methods.