The ability of recognizing the environment is one of the most important functions that the ubiquitous computing system should have. With the recognition of the environment, the system can execute intelligent behaviors such as runtime configuration and semantic based process branch. This recognition can be used as context for system???s decision making. And with correct context, the system can make a proper decision. In this paper, data verifying method is proposed. This method validates the sensed data for the environment. From the proved data, the more reliable recognition of the environment can be generated. The proposed method employs probability theory for marking the reliable degree and machine learning for interpreting the semantic meaning of validated data.
展开▼
