Machine learning approaches for non-intrusive home absence detection based on appliance electrical use

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