Classification of Activities of Daily Living for Older Adults Using Machine Learning and Fixed Time Windowing Technique

The classification of activities of daily living (ADLs) in the home of older adults makes it possible to identify risk situations and changes in behavior that may be associated with some type of problem. This information allows caregivers and health professionals to take action when these types of situations are detected. Although many machine learning classification techniques have been proposed, the effectiveness of the solution in a real-world context remains unclear in most cases due to the large number of sensors required, the type of sensors used which may pose privacy issues, and the assumption of considering only segmented sensor events for each activity before training the models. This article presents an evaluation of different machine learning techniques using fixed time windows to extract spatiotemporal features and classify ten human activities in a real smart home with unobtrusive sensors using the Aruba CASAS dataset. The three classification techniques that achieved better performance were random forest, XGBoost, and support vector machine (SVM), achieving an accuracy of 97% with our best model, outperforming other approaches from the literature that were using the same dataset under similar conditions. The proposed classification techniques were also evaluated under a more realistic scenario by reducing the amount of hardware required and using an additional class labeled "Other" to consider all raw sensor events, including those that do not belong to any specific activity, achieving an accuracy of 89%, outperforming other approaches from the literature using the same dataset under similar conditions.