Gaussian mixture modeling for indoor positioning WIFI systems

Different location determination methods using wireless signal strength have been proposed to improve the location accuracy and mitigate the multipath problem in indoor environment. In this paper, a fingerprinting-probabilistic approach for indoor localization using wireless technology is proposed. The method is based on the use of the Gaussian Mixture Model (GMM) to approximate the probability distribution of the strength of the signal received by a mobile from Access Points (AP). This probability distribution is then used to infer the mobile location. The performance of the proposed method is compared experimentally to that of another powerful method. The comparison shows the effectiveness of the GMM method.