An Interpretable Explanation Approach for Signal Modulation Classification

Signal modulation classification (SMC) has attracted extensive attention for its wide application in the military and civil fields. The current direction of combining deep-learning (DL) technology with wireless communication technology is developing hotly. DL models are riding high in the field of SMC with their highly abstract feature extraction capability. However, most DL models are decision-agnostic, limiting their application to critical areas. This article proposes combining traditional feature-based (FB) methods to set appropriate manual features as interpretable representations for different modulation classification tasks. The fitted decision tree model is used as the basis for the decision of the original model on the instance to be interpreted, and the trustworthiness of the original DL model is verified by comparing the decision tree model with the prior knowledge of the signal FB modulation classification algorithm. We apply the interpretable explanation method under the current leading DL model in the field of modulation classification. The interpretation results show that the decision basis of the model under a high signal-to-noise ratio (SNR) is consistent with the expert knowledge in the traditional SMC method. The experiments show that our method is stable and can guarantee local fidelity. The decision tree as an interpretation model is intuitive and consistent with human reasoning intuition.