Context Sensitive Detection of Long-term Elderly Behavior Change

The detection of behavior changes by activities of daily living applications is very relevant in health care monitoring systems, particularly for older persons. Behavior change detection can be of crucial importance and which may traduce the early stage of a disease. Our research objectives are focused on building a model to conduct a continuous and long-term analysis of elderly's behavior in order to detect slow changes. The originality of this work is to use rich contextual information such as weather conditions, holidays and seasons to identify and learn routine behavior patterns. These patterns are updated throughout the aging process of the elderly person by proposing a novel dynamic behavior clustering method through an iterative process using a moving-window mechanism. The routine behavior patterns are then used for comparing each observed day's behavior to the associated routine behavior pattern in preceding period to define a similarity score. By plotting the daily score along time, we exhibit the period when the score changes over time. The observations on a use case with real datasets are promising.