Proactive Remote Healthcare Based on Machine Learning Algorithms. Home Automation Monitoring for Assisted Living Services and Anomaly Detection

      Аннотация: Monitoring the user activities for a long period of time is not an easy task. Furthermore, our solution needs to be evaluated before being applied to a real user context. For that reason, we designed a simulator to acquire large data test without requiring for months of monitoring. Then, a IR recording system is proposed to monitor a real person in his environment. The results of this IR experimentation allow us to evaluate the application of our solution in a real context. The results of this work lie in the contribution of flexible solutions adapted to all kind of users, to give them more autonomy while facilitating their use of services. Minimizing the use of sensors, another contribution of this work is to lower the installation cost, meaning to increase the implementation possibility.

Ключевые слова: Clustering, hierarchical classification, kohonen algorithm, assisted living service, scenario identification, Anomaly Detection, ergotherapist