Machine Learning Approaches for Non-Intrusive Home Absence Detection Based on Appliance Electrical Use

TL;DR

This paper explores using appliance electrical consumption data, obtained via non-intrusive energy disaggregation, to detect home absence, offering an alternative to intrusive sensors with promising results demonstrated on a modified UK-DALE dataset.

Contribution

It introduces a novel approach for home absence detection using appliance energy data and evaluates multiple machine learning algorithms on artificially generated absence events.

Findings

Home absence detection using appliance energy data is feasible.

Machine learning algorithms can effectively classify presence or absence.

Non-intrusive energy-based detection outperforms traditional sensor methods.

Abstract

Home absence detection is an emerging field on smart home installations. Identifying whether or not the residents of the house are present, is important in numerous scenarios. Possible scenarios include but are not limited to: elderly people living alone, people suffering from dementia, home quarantine. The majority of published papers focus on either pressure / door sensors or cameras in order to detect outing events. Although the aforementioned approaches provide solid results, they are intrusive and require modifications for sensor placement. In our work, appliance electrical use is investigated as a means for detecting the presence or absence of residents. The energy use is the result of power disaggregation, a non intrusive / non invasive sensing method. Since a dataset providing energy data and ground truth for home absence is not available, artificial outing events were introduced on the UK-DALE dataset, a well known dataset for Non Intrusive Load Monitoring (NILM). Several machine learning algorithms were evaluated using the generated dataset. Benchmark results have shown that home absence detection using appliance power consumption is feasible.