A Scalable and Accurate Chessboard-based AMC Algorithm with Low Computing Demands Data & Code

Automatic Modulation Classification (AMC) is a technique used to identify signal modulations in applications like cognitive radar, software-defined radio, and electronic warfare. With future communication systems like 6G operating at higher transmission frequencies than 5G, AMC algorithms need to be more complex yet suitable for embedded devices with limited resources. Although current AMC algorithms deliver high accuracy, they require substantial computing power, making them unsuitable for such devices. This paper introduces the novel Chessboard-based Automatic Modulation Classification (CAMC) algorithm, which is scalable and demands less computing power. Test results reveal that CAMC achieves 86% accuracy under a 3dB SNR condition and 100% above 5dB SNR. It offers comparable performance to state-of-the-art AMC algorithms, classifying mainstream modulations like BPSK, QPSK, 8PSK, and 16QAM, but requires less computing power than existing algorithms. Additionally, CAMC is hardware-friendly due to its inherent parallelism and scalability.