Repository logo
 
Publication

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

2021-08-31Journal article Open access
Simple item page
dc.contributor.authorKhan, Rahim
dc.contributor.authorYang, Qiang
dc.contributor.authorUllah, Inam
dc.contributor.authorRehman, Ateeq Ur
dc.contributor.authorTufail, Ahsan Bin
dc.contributor.authorNOOR, ALAM
dc.contributor.authorRehman, Abdul
dc.contributor.authorCengiz, Korhan
dc.date.accessioned2021-09-27T10:38:48Z
dc.date.available2021-09-27T10:38:48Z
dc.date.issued2021-08-31
dc.description.abstractAutomatic 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-ofthings 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.pt_PT
dc.description.sponsorshipNational Natural Science Foundation of China, Grant/Award Number: 62031014; Key Research and Development Program of Hainan Province (China), Grant/Award Number: ZDYF2019195pt_PT
dc.description.versioninfo:eu-repo/semantics/publishedVersionpt_PT
dc.identifier.doi10.1049/cmu2.12269pt_PT
dc.identifier.urihttp://hdl.handle.net/10400.22/18556
dc.language.isoengpt_PT
dc.publisherWileypt_PT
dc.relation.ispartofseriesCISTER-TR-210805;
dc.relation.publisherversionhttps://ietresearch.onlinelibrary.wiley.com/doi/10.1049/cmu2.12269pt_PT
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/4.0/pt_PT
dc.title3D convolutional neural networks based automatic modulation classification in the presence of channel noisept_PT
dc.typejournal article
dspace.entity.typePublication
oaire.citation.titleIET Communicationspt_PT
person.familyNameNOOR
person.givenNameALAM
person.identifier.ciencia-idF919-244E-A2A5
person.identifier.orcid0000-0002-0077-6509
rcaap.rightsopenAccesspt_PT
rcaap.typearticlept_PT
relation.isAuthorOfPublicationd9f59cbb-6fee-45c2-ada0-77ef35475525
relation.isAuthorOfPublication.latestForDiscoveryd9f59cbb-6fee-45c2-ada0-77ef35475525

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
ART_CISTER_TR-210805_2021.pdf
Size:
825.22 KB
Format:
Adobe Portable Document Format
Download

Collections

ISEP – CISTER – Artigos