Classification of bandlimited FSK4 and FSK8 signals

This paper compares two types of classifiers applied to bandlimited FSK4 and FSK8 signals. The first classifier employs the decision-theoretic approach and the second classifier is a neural network structure. Key features are extracted using a zero crossing sampler. A novel decision tree is proposed and optimum threshold values are found for the decision theoretic approach. For the neural network, the optimum structure is found to be the smallest structure to give 100% overall success rate. The performance of the both classifiers has been evaluated by simulating bandlimited FSK4 and FSK8 signals corrupted by Gaussian noise. It is shown that the neural network outperforms the decision-theoretic approach particularly for SNR <10 dB.