Abstract—With the spread of Covid-19, it is important to comprehend the indoor environment. It is also important to estimate indoor population density in order to avoid three Cs: Closed space, Crowded places, and Close-contact settings. This paper proposes a system for estimating indoor population density based on indoor environment data through Wireless Sensor Network (WSN). The proposed system collects indoor environment such as temperature, humidity, illuminace, CO₂ concentration, and dust level. Then, the proposed system estimates indoor population density from collected environment data. The proposed system estimates the indoor population density from indoor environment data by machine learning. This study also investigates whether sensor data are adequate for estimating indoor population density. The experimental results show that the proposed system achieves about 80 % or more estimation accuracy by using multiple types of sensors, thereby demonstrating the effectiveness of the proposed system. The proposed system is expected to measure the closed space also estimate crowded rooms, which is a helpful finding for preventing the spread of COVID-19.

Index Terms—Wireless Sensor Network (WSN), Internet of Things (IoT), indoor environment monitoring, machine learning, population density estimation

Cite: Nobuyoshi Komuro, "Estimating Indoor Population Density from Non-contact," Journal of Communications vol. 17, no. 3, pp. 188-193, March 2022. Doi: 10.12720/jcm.17.3.188-193

Copyright © 2022 by the authors. This is an open access article distributed under the Creative Commons Attribution License (CC BY-NC-ND 4.0), which permits use, distribution and reproduction in any medium, provided that the article is properly cited, the use is non-commercial and no modifications or adaptations are made.