Automatic Modulation Classification of Overlapped Sources Using Multi-Gene Genetic Programming With Structural Risk Minimization Principle

As the spectrum environment becomes increasingly crowded and complicated, primary users may be interfered by secondary users and other illegal users. Automatic modulation classification (AMC) of a single source cannot recognize the overlapped sources. Consequently, the AMC of overlapped sources attracts much attention. In this paper, we propose a genetic programming-based modulation classification method for overlapped sources (GPOS). The proposed GPOS consists of two stages, the training stage, and the classification stage. In the training stage, multi-gene genetic programming (MGP)-based feature engineering transforms sample estimates of cumulants into highly discriminative MGP-features iteratively, until optimal MGP-features (OMGP-features) are obtained, where the structural risk minimization principle (SRMP) is employed to evaluate the classification performance of MGP-features and train the classifier. Moreover, a self-adaptive genetic operation is designed to accelerate the feature engineering process. In the classification stage, the classification decision is made by the trained classifier using the OMGP-features. Through simulation results, we demonstrate that the proposed scheme outperforms other existing methods in terms of classification performance and robustness in case of varying power ratios and fading channel.