A method and device for multi-user identity recognition based on wifi signal detection gait

Abstract

The present invention relates to a method and device for detecting gait based on WiFi signal to realize multi-user identity recognition. Using WiFi signal, after performing outlier point removal, high-frequency denoising and principal component analysis on wireless signal, according to the training model, it automatically Different time-domain signals for two users are obtained by adaptive separation, and the two signals are further divided according to the pace, features are extracted, and a classifier model that can identify multi-user identities in the smart space is trained. It solves the problem of multi-user identification in smart space, and uses the mixed WiFi signal under two-person walking, preprocessing and wireless signal separation, and then can effectively extract gait information, thereby realizing double-person user identification.

Description

technical field [0001] The invention belongs to the field of wireless communication, and in particular relates to a method and a device for realizing multi-user identification by detecting gait based on WiFi signals. Background technique [0002] With the recent rapid development of the Internet of Things and wireless communication technologies, smart spaces including smart offices and smart homes have come into the public eye. In 2019, the penetration rate of smart home has reached 33.2%, and is expected to reach 53.9% in 2023. But in a smart space, users' private information is easily exposed. Therefore, in order to provide customized services to authenticated users in a smart space, user identification is particularly important. [0003] In smart spaces, biometrics with specific qualities have been widely used, such as: voice, fingerprint, iris and so on. Recently, attention has also been paid to user identification based on gait because of its superiority over traditi...

AI Technical Summary

Problems solved by technology

However, the antenna of the WiFi device cannot be automatically rotated and positioned, and the mixed signal generated by walking is more complex and contains a large number of human-to-human interactions, so the method of independent component analysis is no longer applicable

Also, when two users are walking at the same time, only one user is detected and the method of removing the signal generated by the other user is no longer applicable.

Images