As the population in the Western world is rapidly aging, the remote monitoring solutions integrated into the living environment of seniors have the potential to reduce the care burden helping them to self-manage problems associated with old age. The daily routine is considered a useful tool for addressing age-related problems having additional benefits for seniors like reduced stress and anxiety, increased feeling of safety and security. In this paper, we propose a solution for identifying the daily routines of seniors using the monitored activities of daily living and for inferring deviations from the routines that may require caregivers’ interventions. A Markov model-based method is defined to identify the daily routines, while entropy rate and cosine functions are used to measure and assess the similarity between the daily monitored activities in a day and the inferred routine. A distributed monitoring system was developed that uses Beacons and trilateration techniques for monitoring the activities of older adults. The results are promising, the proposed techniques can identify the daily routines with confidence concerning the activity duration of 0.98 and the sequence of activities in the interval of [0.0794, 0.0829]. Regarding deviation identification, our method obtains 0.88 as the best sensitivity value with an average precision of 0.95.

A person’s routine is a sequence of activities of daily living patterns recurrently performed. Sticking daily routines is a great tool to support the care of persons with dementia, and older adults in general, who are living in their homes, and also being useful for caregivers. As state-of-the-art tools based on self-reporting are subjective and rely on a person’s memory, new tools are needed for objectively detecting such routines from the monitored data coming from wearables or smart home sensors. In this paper, we propose a solution for detecting the daily routines of a person by extracting the sequences of recurrent activities and their duration from the monitored data. A genetic algorithm is defined to extract activity patterns featuring small differences that relate to the day-to-day contextual variations that occur in a person’s daily routine. The quality of the solutions is evaluated with a probabilistic-based fitness function, while a tournament-based strategy is employed for the dynamic selection of mutation and crossover operators applied for generating the offspring. The time variability of activities of daily living is addressed using the dispersion of the values of duration of that activity around the average value. The results are showing an accuracy above 80% in detecting the routines, while the optimal values of population size and the number of generations for fitness function evolution and convergence are determined using multiple linear regression analysis.