A New Method of Complex Maneuvering Event Detection
Wei Chen, Qing Li, Jian He, Tao Jin · Applied Mechanics and Materials · 2011
In dealing with such problems as imprecision and poor real-time performance in complex maneuverable events detection. A method based on RFNN (Rough-Fuzzy Neural Network) is proposed. Firstly, the minimal rule sets from data samples are acquired by using the Rough Set Theory; secondly, these rules are used to construct the initial scalar values of neural cells in each layer and their relative parameters in the fuzzy neural network; lastly, parameters of the network are acquired by using BP(back propagation) algorithm. The experimental results indicate that RFNN take advantage of the sample data features effectively, reduce the number of rules, simplify network structure, improve the precision of detection and the performance of real-time.