Leblebici, MerihCalhan, AliCicioglu, Murtaza2024-08-232024-08-2320241568-49461872-9681https://doi.org/10.1016/j.asoc.2024.111412https://hdl.handle.net/20.500.12684/14415Modulation recognition using deep learning presents challenges in effectively distinguishing high -order modulation schemes while maintaining a balance between complexity and recognition accuracy. In this study, we curate a comprehensive dataset in the r theta plane, encompassing eight distinct modulation schemes. Leveraging hyperparameter optimization and transfer learning, we explore the capabilities of various CNN -based architectures, including MobileNetV2, ResNet50V2, ResNet101V2, InceptionV3, ResNet152V2, Xception, and InceptionResNetV2, for the classification of modulation schemes. The simulation results demonstrate that with signalto-noise ratio (SNR) values exceeding 5 dB, all models exhibit classification accuracies surpassing 50% and approach near -perfect accuracy at an SNR value of 20 dB. However, under low SNR conditions, such as 5 dB, the recognition accuracies of all models, except for ResNet152V2 and InceptionV3, show minimal variation. As the SNR increases by 5 dB from -5 dB to 20 dB, ResNet152V2 and InceptionV3 demonstrate remarkable classification accuracy improvements, exceeding 40%, 30%, 30%, 10%, and 15%, respectively. In contrast, the other models do not exhibit such robust responsiveness in accuracy enhancements. The remarkable performance improvements are achieved by fine-tuning pre -trained models through these processes.en10.1016/j.asoc.2024.111412info:eu-repo/semantics/closedAccessModulation recognitionDeep learningTransfer learningConstellation diagramClassificationArticle1542-s2.0-85185781736WOS:001190913100001Q1N/A