Automatic Modulation Classification via Green Machine Learning

In this work, we propose an interpretable, robust, and lightweight machine learning method for automatic modulation classification (AMC) under dynamic and noisy channel conditions. It is called green automatic modulation classification (GAMC) and targets edge artificial intelligence (AI) with low computational complexity and a small model size. GAMC operates in four stages. First, raw received I/Q signals are transformed into multi-domain representations, including constellation diagrams and spatio-temporal graphs. Second, we extract a comprehensive set of statistical and topological features from time-series signals, constellation diagrams, and graphs. Third, a supervised feature learning process leverages label guidance to project high-dimensional features into robust, discriminative low-dimensional ones. Finally, a context-aware Signal-to-Noise Ratio (SNR) soft routing mechanism ensembles predictions from downstream classifiers. Experimental results show that GAMC effectively mitigates domain shifts caused by high noise. It strikes a good balance between accuracy and efficiency, reducing the number of model parameters by $50\%$, operating at $3\%$ to $42\%$ of the computational cost of lightweight deep learning models, and maintaining higher accuracy in various SNRs.

G-AMC: A Green Automatic Modulation Classification Method

In this work, we propose an efficient and transparent green learning pipeline to address the automatic modulation classification (AMC) problem. This pipeline aims to enable receivers to blindly identify the modulation modes of the incoming signals in a computationally efficient way with a small model size. Our method includes the following steps. First, the input signal is transformed into a precise representation through the sparse coding method. Second, various features are extracted from the sparse coding representation with the statistics from the input signal. Third, the classification subspace is hierarchically partitioned with a tree structure to achieve a lightweight model size with good prediction accuracy. The experimental results demonstrate the effectiveness and efficiency in classifying the modulated features and representation of received signals. Compared to lightweight deep learning models, the number of model parameters is reduced by \textbf{41\%}, while the usage of Floating Point Operations (FLOPs) is only $\mathcal{O}(10^{-4})$ of the blind waveform recognition without pre-arranged knowledge of incoming waveforms.