TITLE:
An Activity Recognition System at Home Based on CO2 Sensors
AUTHORS:
Hiroyuki Matsubara
KEYWORDS:
Activity Recognition, CO2 Sensor, Internet of Things (IoT), Low Privacy-Intrusion, Heat Map
JOURNAL NAME:
Journal of Computer and Communications,
Vol.11 No.11,
November
24,
2023
ABSTRACT: Activity recognition of indoor occupants using indirect sensing with less privacy violation is one of the hot research topics. This paper proposes a CO2 sensor-based indoor occupant activity monitoring system. Using the IoT sensor node that contains CO2 sensors, the measured CO2 concentrations in three locations (laboratory, office, and bedroom) were stored in a cloud server for up to 35 days starting July 1, 2023. The CO2 measurements stored at 30-second intervals were statistically processed to produce a heat-mapped display of the hourly average or maximum CO2 concentration. From the heatmap visualizations of CO2 concentration, the proposed system estimated meeting, heating water using a portable stove, and sleep for the occupants’ activity recognition.