Summary: | 碩士 === 國立中正大學 === 電機工程研究所 === 101 === A context-aware system plays an important role in recognizing user’s activities and providing assistive services in smart homes. There has been a lot of research that aims at fulfilling the requirements in this topic, including specification-based and learning-based methods. Furthermore, constructing a model with understandability and reusability is necessary, which makes information exchangeable between components. Therefore, we first use ontology as the model base because of its rich semantic structure in describing the different relationships between domain concepts. Second, we combine the model with a machine learning approach, merging patterns, to enhance the limitation that knowledge must be defined by expert beforehand. After fusing these two methods, the model indeed improves the power on adaptability and scalability, making it suitable for dynamic environment adaptation and personal preference accommodation.
|