Energy disaggregation for identifying anomalous appliance

Energy disaggregation research claims that it can be used to identify anomalous appliances. Our study proposes a technique which checks how accurate is disaggregated data in identifying such appliances. The evaluation of proposed technique on four different homes shows that disaggregation enables to find anomalies in air conditioner and refrigerator with an average F-score of 0.35, which is low on a scale of 0 to 1.