The typical four-layer forward fuzzy neural network (FNN) is modified, and a two-dimension input, five-layer FNN classifier with the analysis layer included is proposed and used for intelligent target detection. The application of this new detection approach to both the simulation data and the real data shows its advantages of simple structure, fast speed and high recognition rate
Published in:
Signal Processing Proceedings, 2000. WCCC-ICSP 2000. 5th International Conference on
(Volume:3
)
Date of Conference: 2000