Designing smart home services using machine learning and knowledge-based approaches ; Conception de services pour maison intelligente à l'aide d'approches basées sur l'apprentissage automatique et la représentation de connaissances

The intelligence of a smart home is realized by creating various services. Eachservice tries to adjust one monitored state by controlling related actuators after consideringenvironment states detected by sensors. However, the design of the logic of the services deployedin a smart home faces limitations of either dynamic adaptability (predefined rules) orexplicability (learning techniques). Four proposals that are parts of a hybrid approach combiningpredefined rules and learning techniques aim at mitigating these limitations.The first proposal is to use reinforcement learning to create a dynamic service. The deploymentof this single service includes two phases : pretraining in the simulation and continuous trainingin the real world. Our study only focuses on the simulation part. Extending the first proposal,the second proposal proposes several architectures to create multiple dynamic and conflictfreeservices. However, the created data-driven services are not explicable. Therefore, the thirdproposal aims to extract explicable knowledgebased services from dynamic data-driven services.The fourth proposal attempts to combine the second and third proposals to create dynamicand explicable services. These proposals are evaluated in a simulated environment ontemperature control, light intensity, and air quality services adapted to the activities of the inhabitant.They can be extended according to several perspectives, such as the co-simulation ofphysical phenomena, the dynamic adaptation to various inhabitant profiles, and the energy efficiencyof the deployed services. ; L'intelligence de la maison intelligente est réalisée en créant divers services. Chaque service tente d'ajuster un état monitoré en contrôlant les actionneurs associés après avoir pris en compte les états de l'environnement détectés par les capteurs. Cependant, la conception de la logique des services déployés dans une maison intelligente se heurte à des limitations soit d'adaptabilité dynamique (règles prédéfinies) soit d'explicabilité (techniques ...