Alzheimer disease becomes a major issue in elder population. To enhance their autonomy and solve ... more Alzheimer disease becomes a major issue in elder population. To enhance their autonomy and solve future financial issues, we propose an adaptive game based on a non-intrusive shoe-mounted accelerometer able to recognize daily activities and errors. By solving puzzles, the user can train himself his erroneous activities, and re-learn a few. The main goal behind this game is to delay the cognitive decline while creating an evaluation tool for the health-care professional by the computation of a score taking into account the correctitude and the perseverance.
Taking care of the elders constitutes a major issue in the western societies. Smart homes appear ... more Taking care of the elders constitutes a major issue in the western societies. Smart homes appear to be a socially and economically viable solution. They consist in habitats augmented with sensors and actuators enabling to achieve activity recognition and to provide assistive services to a resident. Stationary aspect of sensors used in most smart homes makes the concept difficult to deploy in existing homes, and involves a high cost. In this paper, we propose an inexpensive non-vision-based system ably to recognize, in real-time, activities and errors of a resident. This proposed recognition system is based on a shoe equipped with a single sensor: a three-axis accelerometer and on a state-transition algorithmic approach using fuzzy logic. We have examined the learning data as frequency distributions, where the probability histograms have been directly interpreted as fuzzy set. We conducted experiments of the system in our smart home by simulating (multiple times) several scenarios based on a morning routine. These scenarios were based on clinical data gathered in a previous experiment with actual Alzheimer's patients. We obtained promising results showing that the proposed activity and error recognition system are highly effective.
Alzheimer disease becomes a major issue in elder population. To enhance their autonomy and solve ... more Alzheimer disease becomes a major issue in elder population. To enhance their autonomy and solve future financial issues, we propose an adaptive game based on a non-intrusive shoe-mounted accelerometer able to recognize daily activities and errors. By solving puzzles, the user can train himself his erroneous activities, and re-learn a few. The main goal behind this game is to delay the cognitive decline while creating an evaluation tool for the health-care professional by the computation of a score taking into account the correctitude and the perseverance.
Taking care of the elders constitutes a major issue in the western societies. Smart homes appear ... more Taking care of the elders constitutes a major issue in the western societies. Smart homes appear to be a socially and economically viable solution. They consist in habitats augmented with sensors and actuators enabling to achieve activity recognition and to provide assistive services to a resident. Stationary aspect of sensors used in most smart homes makes the concept difficult to deploy in existing homes, and involves a high cost. In this paper, we propose an inexpensive non-vision-based system ably to recognize, in real-time, activities and errors of a resident. This proposed recognition system is based on a shoe equipped with a single sensor: a three-axis accelerometer and on a state-transition algorithmic approach using fuzzy logic. We have examined the learning data as frequency distributions, where the probability histograms have been directly interpreted as fuzzy set. We conducted experiments of the system in our smart home by simulating (multiple times) several scenarios based on a morning routine. These scenarios were based on clinical data gathered in a previous experiment with actual Alzheimer's patients. We obtained promising results showing that the proposed activity and error recognition system are highly effective.
Uploads
Papers by Julien Vandewynckel