Intelligent indoor localization based on CSI via radio images and deep learning

Abstract

Abstract The universality of intelligent indoor localization based on WIFI has increasingly emerged as a multifold challenge. However, in practical applications, its indoor localization accuracy is limited by noises, diffractions, and multipath effects. To overcome these drawbacks, we design a new intelligent indoor localization system based on channel state information (CSI) of the wireless signal from multiple-input multiple-output (MIMO): IILC. In IILC, the initial amplitude information is first processed in the measured CSI data, which can effectively suppress the impact from noise and other interferences. Next, we devised a method to construct radio images. It can fully use space-frequency and time-frequency information from CSI-MIMO to obtain more location information. Next, we design a new deep learning network to determine the optimal effectiveness of radio image classification. Subsequently, a mixed norm is proposed to impose sparsity penalty and overfit constraint on the loss function, making the valuable feature units active and the others inactive. The experimental results verify that the IILC system exhibits excellent performance. The overall localization accuracy of the IILC in the office scene can reach 97.10%, and the probability of localization error within 1.2 m is 86.21%.