A study on information fusion methodology based on rough set and neural network

On the basis of performing information fusion by rough set theory and neural network theory, this article analyzes their respective advantages and existing problems, and designs the information fusion methodology that combine them. This method is based on the concept that applies rough set theory to perform attribute reduction of the pending data of neural network, so as to achieve simplification of the neural network. We uses this method to perform fusion of information in relation with gas danger in coal mines, in order to assess the gas safety of those mines. The result shows that this method decreases the number of training, and the convergence effect is better than that of the traditional neural networks.