An indoor positioning system using Channel State Information based on TrAdaBoost Tranfer Learning

Abstract

With the rapidly growing demand for Location-Based Services in indoor environments, fingerprint-based indoor positioning has caused great interest due to its high positioning accuracy and low equipment cost. However, the standard signal radio map cannot provide consistent high positioning accuracy under environmental changes and new scenarios. To address this problem, we present a novel indoor positioning Transfer Learning(TL) system based on improved TrAdaBoost. We perform phase correction on the raw CSI phase, then use One-vs-Rest algorithm and One-Hot coding, which can realize the multi-classification ability of the TrAdaBoost algorithm. Meanwhile, we use a correction factor to slow down the weight of the source domain and make the fingerprint of the source domain better transfer to the target domain by the TrAdaBoost in order to form a new fingerprint database. Experimental results show that the positioning accuracy can be improved by 35% in dynamic environment conditions. The proposed method can improve the positioning accuracy by an average of 30% in new scenes and the Site Survey Overhead(SSO) is reduced by 40%. Experiments show that our proposed method has robustness in time and space, and has lower SSO under the same positioning accuracy.