Developing optimized deep learning models for automatic modulation classification that are suitable for deployment on resource-constrained edge devices.
This paper introduces a novel online Automatic Modulation Classification (AMC) scheme, IDK-OGD, which leverages Isolation Distributional Kernel (IDK) for robust signal representation and Online Gradient Descent (OGD) for adaptive model updates, achieving superior performance in time-varying channel conditions compared to existing methods.