Modulation classification using a neural tree network

A new classifier is presented for estimating the modulation type for digitally modulated signals. The new classifier is known as the neural tree network (NTN). The NTN is a self-organizing, hierarchical classifier that implements a sequential linear decision strategy. The NTN does not require a statistical analysis of the features, as do Bayesian methods or decision trees. The NTN also allows for a more flexible partitioning of feature space than the prior classification methods. The features used for modulation classification are obtained from an autoregressive model of the signal. These features include the instantaneous frequency, bandwidth, and derivative of the instantaneous frequency. The modulation types to be estimated are continuous wave, binary and quadrature phase shift keying, and binary and quadrature frequency shift keying. The experiment results show the NTN to perform well for low carrier to noise ratio (CNR) input signals, in addition to outperforming the decision tree classifier.