Most existing approaches in Context-Aware Recommender Systems (CRS) focus on recommending relevant items to users taking into account contextual information, such as time, location, or social aspects. However, few of them have considered the problem of user's content dynamicity. We introduce in this paper an algorithm that tackles the user's content dynamicity by modeling the CRS as a contextual bandit algorithm and by including a situation clustering algorithm to improve the precision of the CRS. Within a deliberately designed offline simulation framework, we conduct evaluations with real online event log data. The experimental results and detailed analysis reveal several important discoveries in context aware recommender system.

No abstract

No abstract

Domestic healthcare is becoming more and more important as the population is growing older. The last technological progresses enable numerous possibilities for monitoring and helping users in their everyday lives. Robotics and smart home are two distinct examples. They both provide great features and possibilities, but also limits. This work addresses the combination of robots and smart home. In this paper, we present a robotic framework that relies on the smart environments strengths. We tackled numerous challenges encountered by the robot for perceiving, reasoning and acting at home and that are critical for healthcare applications. Consequently, multiple solutions are presented and evaluated through both simulation and physical tests.