Identity intelligent identification method and system based on WiFi channel state information

Abstract

The invention belongs to the technical field of wireless communication, and discloses an intelligent personnel identity recognition method and system based on WiFi channel state information, and the method comprises the steps: sensing and collecting CSI data through a pair of WiFi receiving and transmitting equipment in a typical indoor environment; carrying out discrete wavelet transform denoising on the collected CSI data containing the personnel identity information, restraining the influence of indoor environment random noise, and keeping detail parts of signals; performing inverse Fouriertransform operation on the filtered CSI data to obtain a channel impact response, and extracting a channel power change feature quantity from the channel impact response; learning and training the extracted channel power change feature by using a deep neural network RNN model until all parameters in the RNN model are optimal; and using the trained neural network to intelligently identify identityinformation of different persons. According to the method, the defects of poor identification performance and low identification result reliability in the prior art are overcome, and the robustness and identity identification precision of the system are improved.

Description

technical field [0001] The invention belongs to the technical field of wireless communication, and in particular relates to a method and system for intelligent identification of personnel identity based on WiFi channel state information. Background technique [0002] In recent years, with the rapid development of various wireless communication services, various services based on wireless electromagnetic environment perception, such as human body position, physiological indicators, posture, action, etc., and a series of related wireless applications have gradually received widespread attention. . In recent years, the demand for human perception services has increased rapidly, and various perception systems and technologies have been extensively and deeply researched and applied. Nowadays, with the proposal and application of smart city, intelligent transportation, Internet of Vehicles, cloud computing services, and big data concepts, wireless sensing services, as an indispen...

AI Technical Summary

Problems solved by technology

[0008] (1) The existing technology lacks the ability to effectively suppress the impact of random noise in CSI data

[0009] (2) The existing technology extracts too many statistical features, and the recognition efficiency is low

[0010] (3) The existing technology lacks an effective intelligent identification algorithm for identity

Images