By combining rough sets and neural networks, this paper develops a knowledge acquisition model for colliery gas forecast, which consists of four modules: sample refreshment, rough sets preprocessing, neural network training and rules extraction. It is applied in the real-time data, whose results show that it solves the problem of the knowledge acquisition difficulty of colliery gas forecast, and has good real-time characteristic, high reliability and perfect precision. The model provides foundation for establishing knowledge database of colliery gas forecast.
Aiming the lack of effective perception mechanisms in present CSCL system, system the application of learning-Agent which has awareness function model to the CSCL system is proposed. The inter architecture of the Agent is described. The decomposition of group-task and the construction algorithm of task-graph are given. The function of awareness intensity is defined, and the process of awareness information show is described. Some general problems, such as population interaction effect, disorder of awareness information are given a better solution.
An intelligent transport system based on Digital Terrestrial Multimedia Broadcast(DTMB) is proposed, and its server system is implemented. Real-time traffic information of all styles is standardized, and encoded according to Transport Protocol Experts Group(TPEG) protocols. Information encoded is transferred into TS stream that can be transmitted through DTMB, the information is received by terminals with capability of receiving digital television after being sent through DTMB send system, terminal completes dynamic navigation using the information matched with static map. The prototype system validates the feasibility of the architecture.