In this paper, we propose a low-cost, non-invasive home activity recognition method using low- resolution power consumption data. Notably, we tackle the following two challenges. Firstly, we use only the time series of power consumption data aggregated per house and measured every few tens of seconds, which is usually used for demand monitoring by smart meters. We design a set of activities that can be recognized by such low-resolution data and find an appropriate feature set to train and test the balanced random forest classifier. Secondly, we consider the divergence of activity patterns seen in different households. Since supervised learning dedicated to each household is not a realistic solution, we arrange different classifiers trained by different household data in supervised learning, and present a method to automatically choose the best-fit classifier for an unseen household in the online phase. We evaluated our method with an aggregated power consumption dataset collected from eight real homes for 191 days. We confirmed that our method achieved 70% recognition accuracy for activities using such a low-resolution aggregated power consumption dataset, and that our proposed fitness scores were able to choose the best classifiers. We have evaluated our method with aggregated power consumption dataset collected from eight real homes for 191 days. We confirmed that our method achieved 70% recognition accuracy for activities from such a low- resolution aggregated power consumption dataset, and that our proposed fitness scores were able to choose the best classifiers.