Dual Mode Modulation Classification Using Convolution Neural Network

With the rapid expansion of wireless communication, modulation classification has become a crucial component of spectrum management and interference detection. Traditional methods face challenges in handling complex, noisy environments. In this research, we present a dual-mode Convolutional Neural Network (CNN) framework for modulation classification, leveraging both constellation diagrams and waveforms. By integrating complementary feature representations, the proposed approach achieves improved classification accuracy and robustness. Our experimental results demonstrate a significant accuracy improvement when incorporating both modalities, underscoring the effectiveness of dual-mode learning in modulation classification.