{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/deep-neural-network-architectures-for","title":"Deep Neural Network Architectures for Modulation Classification","arxiv_id":"1712.00443","date":"2017-12-01","proceeding":null,"authors":["Xiaoyu Liu","Diyu Yang","Aly El Gamal"],"abstract":"In this work, we investigate the value of employing deep learning for the\ntask of wireless signal modulation recognition. Recently in [1], a framework\nhas been introduced by generating a dataset using GNU radio that mimics the\nimperfections in a real wireless channel, and uses 10 different modulation\ntypes. Further, a convolutional neural network (CNN) architecture was developed\nand shown to deliver performance that exceeds that of expert-based approaches.\nHere, we follow the framework of [1] and find deep neural network architectures\nthat deliver higher accuracy than the state of the art. We tested the\narchitecture of [1] and found it to achieve an accuracy of approximately 75% of\ncorrectly recognizing the modulation type. We first tune the CNN architecture\nof [1] and find a design with four convolutional layers and two dense layers\nthat gives an accuracy of approximately 83.8% at high SNR. We then develop\narchitectures based on the recently introduced ideas of Residual Networks\n(ResNet [2]) and Densely Connected Networks (DenseNet [3]) to achieve high SNR\naccuracies of approximately 83.5% and 86.6%, respectively. Finally, we\nintroduce a Convolutional Long Short-term Deep Neural Network (CLDNN [4]) to\nachieve an accuracy of approximately 88.5% at high SNR.","url_abs":"http://arxiv.org/abs/1712.00443v3","url_pdf":"http://arxiv.org/pdf/1712.00443v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"deep-neural-network-architectures-for","repo_url":"https://github.com/dl4amc/source","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"classification","task_name":"General Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}