초록

용어보기논문에서 용어와 풀이말을 자동 추출한 결과로, 시범 서비스 중입니다. AI-Helper

Abstract ▼ AI-Helper

Recently, the smart TV which offers functions and services using a variety of sensors and internet connection is proliferated. However, because so far the research of a context-awareness in TV has been focused on content services, it have problem that user learn a role of each function that is offer...

Recently, the smart TV which offers functions and services using a variety of sensors and internet connection is proliferated. However, because so far the research of a context-awareness in TV has been focused on content services, it have problem that user learn a role of each function that is offered the smart TV to use the functions. We aware a current user situation and offer function control services considering the situation to solve the problem. This paper proposes modular Bayesian networks using domain knowledge for context-aware of the smart TV. Bayesian networks, which can respond flexibly in uncertain situations and can be designed by domain knowledge when the data is not enough, has emerged as a powerful technique for context-aware services. And the network modeling through a modular method that is independent services and functions is possible to reduce a time complexity and can reuse the designed networks. The precision, recall and accuracy of networks which are constructed by the proposed method are at least 16%, 20% and 10% higher than the rule based system respectively. And the t-test confirms that the proposed method outperforms the rule-based system in uncertain situations at significance level of 95%.

주제어