Improving Neural Detectors for Slow Fluctuating Radar Targets

– Slow fluctuating radar targets have shown to be very difficult to classify using neural networks. This paper deals with the application of time-frequency decompositions for improving the performance of neural networks for this kind of targets. Several aspects, such as dimensionality reduction of the timefrequency representations and the optimum value of SNR for training are discussed. The proposed detector is compared with a single neural network for radar detection, showing that time-frequency decompositions improve the performance of neural networks for slow fluctuating radar targets detection, specially for low values of the probability of false alarm. Key-Words: Neural network, radar, detection, PCA, time-frequency analysis.