CSI correction positioning method combined with dense connection network

Abstract

The invention discloses a CSI correction positioning method combined with a dense connection network, which comprises the following steps of: rejecting abnormal CSI by adopting an isolated forest, constructing a CSI amplitude fingerprint form containing time, frequency and antenna pair information, training an improved CSI positioning dense connection convolutional network to establish a corresponding relation between the CSI and a spatial position, and constructing an interpolation fingerprint database by using a generalized continuation interpolation method, carrying out position correction on a prediction result with relatively low maximum probability by using probability weighted position estimation based on a neural network and adopting the interpolation fingerprint database and an improved KNN correction positioning method combined with a Bhattacharyya coefficient. According to the invention, the information contained in the CSI is fully utilized; potential features of the CSI are comprehensively mined, so that the training process is more efficient; and in combination with the improved KNN correction positioning algorithm of the Bhattacharyya coefficient, the positioning error of the probability weighted positioning algorithm based on the neural network is effectively reduced, and the stability of the positioning system is improved.

Description

technical field [0001] The invention relates to the field of indoor positioning technology and data analysis technology, specifically, a CSI correction positioning method combined with a densely connected network. Background technique [0002] A large number of indoor scenarios have conditions and requirements for location-based services. Since Wi-Fi devices are widely used indoors, existing studies have used Channel State Information (CSI) that can be obtained by Wi-Fi for positioning. However, the current indoor positioning algorithm based on CSI does not maximize the potential of CSI in positioning, and there are still problems of insufficient data utilization and single positioning algorithm, which further reduces the accuracy and robustness of the indoor positioning algorithm based on CSI. Contents of the invention [0003] Aiming at the problems of poor positioning stability, low positioning accuracy and heavy fingerprint collection workload in the prior art, the pre...

Images