Quantitative evaluation of environmental changes in the laboratory using radio wave strength transitions and deep learning

Abstract

This study proposes a human flow sensing system that analyzes a large data set obtained from WiFi radio wave strength. From the viewpoint of safety management in laboratories at universities and research institutes, it will be possible to detect the moving lines that deviate from the routine behavior patterns during experiments by comprehensively understanding the human flow in a laboratory. Our study measured the radio wave intensity against the human flow and objects in laboratories in advance. Based on these measurements, the optimal conditions for the installation location of the sensor unit were studied. At the same time, it was confirmed that the specific patterns shown by the time-series transition of the radio wave intensity could be detected as human flows. In addition, the transition of the radio wave strength that can occur in three basic changes in the situation of “human moving,” “human stopping,” and “nothing” was collected through experiments. We believe that the obtained data set is a small-scale component of a large-scale data set, which is an aggregate of transitions in radio wave strength generated by individual human actions. To confirm that human motion lines can be detected from these data sets, the transitions in radio wave strength were converted into image data, and detection and classification using deep learning were attempted. The results showed that three basic situational changes could be accurately classified.