CSI human fall recognition method under wifi interference environment

Abstract

The invention relates to a human body fall recognition method for WIFI CSI dynamic subcarrier selection in a WiFi interference environment, and belongs to the technical field of wireless communication. This method first analyzes the CSI interference intensity and CSI active ratio, constructs a WiFi interference feature mapping matrix, and uses the matrix to calculate the interference index of each channel to realize interference discrimination. Then, through the dynamic subcarrier selection algorithm CSI-DSSA based on the interference index, the subcarrier combination with the weakest cross-correlation in the interference data is selected for interference processing, and the multi-link data fusion method CSI-MLDF aggregates multiple data in the undisturbed data. Time-domain feature information of the stream. Finally, the feature values ​​in time domain are extracted and the SVM multi-activity classification model under the WiFi interference environment is constructed to obtain the fall activity recognition results. The invention can effectively improve the accuracy rate of human body fall activity recognition under the WiFi interference environment.

Description

technical field [0001] The invention belongs to the technical field of wireless communication, and relates to a human fall recognition method for WIFICSI dynamic subcarrier selection in a WiFi interference environment. Background technique [0002] With the continuous development of science and technology, especially the gradual maturity of wireless network technology, wireless signals not only play an important role in data transmission, but also can be used to realize environmental awareness. Using wireless signals to realize autonomous activity monitoring has become a development At the same time, it provides a new solution for the activity and health monitoring of the elderly in the home environment, which has very important social significance and broad application prospects. Human activity monitoring based on WiFi is user-centered, using the influence of human body movements on the propagation of WiFi signals to collect physiological information of the human body, incl...

AI Technical Summary

Problems solved by technology

[0003] However, with the widespread use of WiFi devices in daily life, there are often serious co-channel interference or adjacent channel interference problems between WiFi signals, which will greatly reduce the performance of WiFi fall recognition.

Most of the existing research ignores the interference between WiFi signals, and only uses general signal processing technology to filter out uncertain noise. The only related work that considers wireless interference is to use an anti-noise classification algorithm for activity recognition. to tolerate interference

Since the algorithm does not directly deal with the disturbed CSI measurements, the recognition effect is not ideal, and it cannot be well generalized to other types of sensing applications.

Images