Activity Detection from Electricity Consumption and Communication Usage Data for Monitoring Lonely Deaths

As the number of single-person households grows worldwide, the need to monitor their safety is gradually increasing. Among several approaches developed previously, analyzing the daily lifelog data generated unwittingly, such as electricity consumption or communication usage, has been discussed. However, data analysis methods in the domain are currently based on anomaly detection. This presents accuracy issues and the challenge of securing service reliability. We propose a new analysis method that finds activities such as operation or movement from electricity consumption and communication usage data. This is evidence of safety. As a result, we demonstrate better performance through comparative verification. Ultimately, this study aims to contribute to a more reliable implementation of a service that enables monitoring of lonely deaths.