Radar target identification using the learning vector quantization neural network

Summary form only given, as follows. A study is presented of the application of neural network classifiers for identifying aircraft from coherent and noncoherent radar backscatter measurements. The neural network classifier studied is the FSCL-LVQ, a variation of Kohonen´s LVQ classifier. This classifier learns in two phases: an unsupervised first phase and a supervised second phase of training. It is shown that the performance of the neural classifier is close to that of the maximum-likelihood and the nearest-neighbor classifiers. The results also indicate that the neural classifier is relatively insensitive to the noise level of the training data and the network architecture.<>