Indoor personnel activity identification method based on channel state information and man-machine interaction system

Abstract

The invention belongs to the technical field of wireless communication, and discloses an indoor personnel activity identification method based on channel state information and a man-machine interaction system. The method comprises steps of preprocessing the acquired CSI data to extract environmental change information including correlation coefficients and variances; sensing the surrounding environment by using the decision tree, monitoring the personnel activity, if the personnel activity is not detected, continuing to collect the CSI data, keeping the activity monitoring state, and otherwise, triggering an activity feature extraction module; carrying out extreme removal processing and low-pass filtering processing on the collected CSI data in the module; and performing activity matchingand heaviest personnel activity identification by using a dynamic time planning algorithm based on principal component analysis. According to the invention, indoor personnel activity monitoring and activity identification are combined, and PCA-DTW is adopted to carry out indoor personnel activity identification, the step of offline data collection training in the prior art is omitted, and the system performance and the identification rate are improved.

Description

technical field [0001] The invention belongs to the technical field of wireless communication, and in particular relates to a method for identifying indoor personnel activities based on channel state information and a human-computer interaction system. Background technique [0002] Currently, the closest existing technologies: E-eyes and WiFinger, and WiGest and CARM. [0003] Defects of the existing technology: E-eyes and WiFinger cannot effectively adapt to different environments or need to modify system parameters in different environments, and their portability is poor, which reduces the efficiency of recognition. This is because E-eyes and WiFinger lack a matching model that can quantitatively correlate CSI statistical features with indoor human activities; WiGest and CARM are very sensitive to the influence of environmental noise and indoor channel changes when performing activity recognition. This is because they need to capture small changes in activities to be able...

AI Technical Summary

Problems solved by technology

[0008] To sum up, the problems existing in the existing technology are: the current indoor occupant activity recognition technology lacks a matching model that can quantitatively correlate CSI statistical features with indoor occupant activities, resulting in the system not being well adapted to different environments, or when transplanted In different environments, it is necessary to reset the parameters, that is, the environment adaptability is poor; it is very sensitive to the influence of environmental random noise and indoor channel changes, which will lead to poor activity recognition effect and low recognition rate

Images