Oversampling Based Imbalanced Signal Modulation Classification via Cosine-Distance and Distribution

Advances in communication technology have enabled SMC to be widely used in non-cooperative identification situations such as spectrum detection, electronic countermeasures, and target identification. In the face of complex electromagnetic environments and various classification tasks, the class imbalance phenomenon in modulated signal datasets has become a problem that cannot be ignored. For the Signal Modulation Classification (SMC) based on machine learning, the unbalanced training dataset will cause the actual decision boundary to shift, thereby reducing the prediction accuracy of minority signals. And for SMC based on deep learning, unbalanced data will lead to distortion of the feature space and affect the extraction of discriminative features. However, the existing modulation classification methods cannot effectively deal with the imbalance problem. This study introduces an oversampling method tailored for modulation signals. Our method balances the dataset by synthesizing new samples according to the distribution of signal samples and the distance between samples, which will effectively reduce the impact of the imbalance problem on the classifier. For modulated signals, experimental results show that our method performs better than other oversampling methods. In addition to the SMC task, we test the performance of the proposed method for individual identification of radiation sources on the ACARS dataset. Compared with other comparison methods, our method improves the classification performance the most.