Poster Abstract: Comparison of Classifiers for Prediction of Human Actions in a Smart Home

There is a strong interest in IoT-based systems that monitor and control smart home environments by accurately predicting the needs of the human occupants. Past research has focused on the accuracy of prediction of a user's future action. However, much of that work uses synthetic datasets which do not always reflect the real-world interactions that occur between an individual and the home environment. In addition, a focus on prediction accuracy often comes at the cost of slower processing time. This paper focuses on the prediction of future human actions in an intelligent environment with the goal of achieving both high accuracy and real-time performance. We performed experiments using the MavPad dataset, which was gathered from a fully-instrumented home environment, and compared several different machine learning algorithms that included both single and ensemble classifiers. The results show that using a Support Vector Machine approach achieved the best results when using a group of sensors within a local zone around the user and the Random Forest classifier achieved higher performance when using sensors that are distributed across the entire home environment.