Research on Rough Set-Neural Network and Its Application in Radar Signal Recognition

The purpose of reconnaissance system´s information processing is signal recognition, which is also a key step in the whole process of radar reconnaissance information processing. In order to solve the problem of radar signal recognition, a new type of recognition model is established which combines rough set and neural network closely in this paper. The model can be divided into these steps such as recognition information´s pretreatment, sample data´s reduction by rough set, neural network´s learning and training and network´s recognition to information which is not identified. The model mixes rough set´s strong rule extraction ability and the excellent classification ability of neural network through preprocessing initial information and reducing data and training network etc. The experimental results illustrate the model reduces subject factors in signal recognition, improves network´s structure. Compared with traditional signal recognition methods, this model can manage to identify radar signal objectively and effectively without any transcendental information.