Show simple item record

3D convolutional neural networks based automatic modulation classification in the presence of channel noise

dc.contributor.authorRahim Khan
dc.contributor.authorQiang Yang
dc.contributor.authorInam Ullah
dc.contributor.authorAteeq Ur Rehman
dc.contributor.authorAhsan Bin Tufail
dc.contributor.authorAlam Noor
dc.contributor.authorAbdul Rehman
dc.contributor.authorKorhan Cengiz
dc.contributor.otherSchool of Electronics and Information Engineering Harbin Institute of Technology Harbin China
dc.contributor.otherSchool of Electronics and Information Engineering Harbin Institute of Technology Harbin China
dc.contributor.otherCollege of Internet of Things (IoT) Engineering Hohai University (HHU) Changzhou Campus Changzhou China
dc.contributor.otherDepartment of Electrical Engineering Government College University Lahore Pakistan
dc.contributor.otherSchool of Electronics and Information Engineering Harbin Institute of Technology Harbin China
dc.contributor.otherCISTER Research Centre ISEP Politécnico do Porto Portugal
dc.contributor.otherDepartment of Computer Science and Engineering Kyungpook National University Daegu South Korea
dc.contributor.otherDepartment of Electrical ‐ Electronics Engineering Trakya University Edirne Turkey
dc.date.accessioned2022-03-23T13:03:56Z
dc.date.available2025-10-02T04:16:24Z
dc.date.issued01-03-2022
dc.identifier.issn-
dc.identifier.urihttps://doi.org/10.1049/cmu2.12269
dc.description.abstractAbstract Automatic modulation classification is a task that is essentially required in many intelligent communication systems such as fibre‐optic, next‐generation 5G or 6G systems, cognitive radio as well as multimedia internet‐of‐things networks etc. Deep learning (DL) is a representation learning method that takes raw data and finds representations for different tasks such as classification and detection. DL techniques like Convolutional Neural Networks (CNNs) have a strong potential to process and analyse large chunks of data. In this work, we considered the problem of multiclass (eight classes) classification of modulated signals, which are, Binary Phase Shift Keying, Quadrature Phase Shift Keying, 16 and 64 Quadrature Amplitude Modulation corrupted by Additive White Gaussian Noise, Rician and Rayleigh fading channels using 3D‐CNN architectures in both frequency and spatial domains while deploying three approaches for data augmentation, which are, random zoomed in/out, random shift and random weak Gaussian blurring augmentation techniques with a cross‐validation (CV) based hyperparameter selection statistical approach. Simulation results testify the performance of 10‐fold CV without augmentation in the spatial domain to be the best while the worst performing method happens to be 10‐fold CV without augmentation in the frequency domain and we found learning in the spatial domain to be better than learning in the frequency domain.
dc.format-
dc.language.isoEN
dc.publisherWiley
dc.relation.uri['https://www.journals.elsevier.com/journal-of-applied-poultry-research', 'https://www.elsevier.com/journals/journal-of-applied-poultry-research/1056-6171/guide-for-authors', 'https://www.elsevier.com/authors/open-access/choice#waivers']
dc.rights['CC BY', 'CC BY-NC-ND']
dc.subject['poultry breeding', 'meat bird processing', 'poultry health', 'poultry disease', 'food safety', 'layer management', 'Animal culture', 'SF1-1100', 'Food processing and manufacture', 'TP368-456']
dc.subject.lccTelecommunication
dc.title3D convolutional neural networks based automatic modulation classification in the presence of channel noise
dc.typeArticle
dc.description.pages497-509
dc.description.doi10.1049/cmu2.12269
dc.title.journalIET Communications
dc.identifier.e-issn1751-8636
dc.identifier.oaioai:doaj.org/journal:030f9a512f9d49e7adc2e0fcbbe53765
dc.journal.infoVolume 16, Issue 5


This item appears in the following Collection(s)

Show simple item record