Collaborative Trajectory Mining in Smart-Homes to Support Early Diagnosis of Cognitive Decline

Our ageing world population claims for innovative tools to support healthcare and independent living. In this article, we address this challenge by introducing a novel system to recognize symptoms of cognitive decline by exploiting modern smart-home sensors. Since several studies indicate that cognitive issues are frequently associated to locomotion anomalies, our work relies on clinical models of wandering behavior. Previous works tried to recognize wandering of elderly people in outdoor environments, using GPS data and location trace analysis. However, the recognition of wandering indoors poses additional challenges. On the one hand, when moving in a restricted indoor environment, a system for wandering recognition may produce a large number of false positive, since a person's movements are frequently more intricate indoors than outdoors. On the other hand, several indoor movements resembling wandering may be actually due to the normal execution of daily living activities, or to the particular shape of the home. To address these challenges, we adopt a collaborative learning approach, using a training set of trajectories shared by individuals living in smart-homes. New wandering episodes are classified using a personalized model, built considering the homes’ shape and the individuals’ profiles. We apply a long-term analysis of classified wandering episodes to provide a hypothesis of diagnosis to be communicated to a medical center for further inspection. We implemented our algorithms and evaluated the system with a large dataset of real-world subjects, including people with dementia, MCI persons, and cognitively healthy people. The results indicate the potential utility of this system to support the early diagnosis of cognitive impairment.