{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,28]],"date-time":"2025-10-28T15:11:31Z","timestamp":1761664291921,"version":"3.41.2"},"reference-count":53,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2021,7,12]],"date-time":"2021-07-12T00:00:00Z","timestamp":1626048000000},"content-version":"vor","delay-in-days":192,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62031014"],"award-info":[{"award-number":["62031014"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Wireless Communications and Mobile Computing"],"published-print":{"date-parts":[[2021,1]]},"abstract":"<jats:p>The wireless environment poses a significant challenge to the propagation of signals. Different effects such as multipath scattering, noise, degradation, distortion, attenuation, and fading affect the distribution of signals adversely. Deep learning techniques can be used to differentiate among different modulated signals for reliable detection in a communication system. This study aims at distinguishing COVID\u201019 disease images that have been modulated by different digital modulation schemes and are then passed through different noise channels and classified using deep learning models. We proposed a comprehensive evaluation of different 2D Convolutional Neural Network (CNN) architectures for the task of multiclass (24\u2010classes) classification of modulated images in the presence of noise and fading. It is used to differentiate between images modulated through Binary Phase Shift Keying, Quadrature Phase Shift Keying, 16\u2010 and 64\u2010Quadrature Amplitude Modulation and passed through Additive White Gaussian Noise, Rayleigh, and Rician channels. We obtained mixed results under different settings such as data augmentation, disharmony between batch normalization (BN), and dropout (DO), as well as lack of BN in the network. In this study, we found that the best performing model is a 2D\u2010CNN model using disharmony between BN and DO techniques trained using 10\u2010fold cross\u2010validation (CV) with a small value of DO before softmax and after every convolution and fully connected layer along with BN layers in the presence of data augmentation, while the least performing model is the 2D\u2010CNN model trained using 5\u2010fold CV without augmentation.<\/jats:p>","DOI":"10.1155\/2021\/5539907","type":"journal-article","created":{"date-parts":[[2021,7,12]],"date-time":"2021-07-12T19:05:08Z","timestamp":1626116708000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Classification of Digital Modulated COVID\u201019 Images in the Presence of Channel Noise Using 2D Convolutional Neural Networks"],"prefix":"10.1155","volume":"2021","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0928-915X","authenticated-orcid":false,"given":"Rahim","family":"Khan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6570-1516","authenticated-orcid":false,"given":"Qiang","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ahsan Bin","family":"Tufail","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0077-6509","authenticated-orcid":false,"given":"Alam","family":"Noor","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yong-Kui","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","published-online":{"date-parts":[[2021,7,12]]},"reference":[{"volume-title":"Classification of Communication Signals and Detection of Unknown Formats Using Artificial Neural Networks","year":"2006","author":"Iversen A.","key":"e_1_2_10_1_2"},{"key":"e_1_2_10_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/26.126703"},{"key":"e_1_2_10_3_2","doi-asserted-by":"publisher","DOI":"10.1049\/el:19940521"},{"key":"e_1_2_10_4_2","first-page":"10687","article-title":"Error rate performance of OFDMA and MIMO technology over Rayleigh fading channel in 4G networks","volume":"13","author":"Kumari D. L.","year":"2018","journal-title":"International Journal of Applied Engineering Research"},{"key":"e_1_2_10_5_2","doi-asserted-by":"publisher","DOI":"10.1145\/584091.584093"},{"key":"e_1_2_10_6_2","doi-asserted-by":"publisher","DOI":"10.1155\/2019\/5629572"},{"key":"e_1_2_10_7_2","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"e_1_2_10_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.231"},{"key":"e_1_2_10_9_2","first-page":"1799","article-title":"Joint training of a convolutional network and a graphical model for human pose estimation","volume":"2","author":"Tompson J. J.","year":"2014","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_10_10_2","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"e_1_2_10_11_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-020-08657-4"},{"key":"e_1_2_10_12_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2020.105528"},{"key":"e_1_2_10_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2662206"},{"key":"e_1_2_10_14_2","doi-asserted-by":"crossref","unstructured":"GuoS. YanZ. ZhangK. ZuoW. andZhangL. Toward convolutional blind denoising of real photographs 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2019 Long Beach CA USA 1712\u20131722 https:\/\/doi.org\/10.1109\/CVPR.2019.00181.","DOI":"10.1109\/CVPR.2019.00181"},{"key":"e_1_2_10_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2019.2912909"},{"key":"e_1_2_10_16_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2020.04.010"},{"key":"e_1_2_10_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2971698"},{"key":"e_1_2_10_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2020.2991875"},{"key":"e_1_2_10_19_2","doi-asserted-by":"crossref","unstructured":"YilmazR.andPusaneA. E. Deep learning based automatic modulation classification in the case of carrier phase shift 43rd International Conference on Telecommunications and Signal Processing (TSP) 2020 Milan Italy 354\u2013357 https:\/\/doi.org\/10.1109\/TSP49548.2020.9163509.","DOI":"10.1109\/TSP49548.2020.9163509"},{"key":"e_1_2_10_20_2","doi-asserted-by":"crossref","unstructured":"WuY. LiX. andFangJ. A deep learning approach for modulation recognition via exploiting temporal correlations 19th IEEE International Workshop on Signal Processing Advances in Wireless Communications (SPAWC) 2018 Kalamata Greece 1\u20135 https:\/\/doi.org\/10.1109\/SPAWC.2018.8445938 2-s2.0-85053463012.","DOI":"10.1109\/SPAWC.2018.8445938"},{"key":"e_1_2_10_21_2","doi-asserted-by":"crossref","unstructured":"SunJ. WangG. LinZ. RazulS. G. andLaiX. Automatic modulation classification of cochannel signals using deep learning 23rd IEEE International Conference on Digital Signal Processing (DSP) 2018 Shanghai China 1\u20135 https:\/\/doi.org\/10.1109\/ICDSP.2018.8631682 2-s2.0-85062788780.","DOI":"10.1109\/ICDSP.2018.8631682"},{"key":"e_1_2_10_22_2","doi-asserted-by":"crossref","unstructured":"LiX. ChenS. HuX. andYangJ. Understanding the disharmony between dropout and batch normalization by variance shift Proceedings of the IEEE\/CVPR Conference on Computer Vision and Pattern Recognition 2019 Long Beach CA USA 2682\u20132690.","DOI":"10.1109\/CVPR.2019.00279"},{"key":"e_1_2_10_23_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1098-y"},{"key":"e_1_2_10_24_2","unstructured":"XiaoC. ZhuJ.-Y. LiB. HeW. LiuM. andSongD. Spatially transformed adversarial examples Proceedings of 6th International Conference on Learning Representations (ICLR) 2018 Vancouver Canada."},{"key":"e_1_2_10_25_2","doi-asserted-by":"crossref","unstructured":"WorrallD. E. GarbinS. J. TurmukhambetovD. andBrostowG. J. Harmonic networks: deep translation and rotation equivariance Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017 Honolulu HI USA 7168\u20137177.","DOI":"10.1109\/CVPR.2017.758"},{"key":"e_1_2_10_26_2","unstructured":"GoodfellowI. J. ShlensJ. andSzegedyC. Explaining and harnessing adversarial examples Proceedings of International Conference on Learning Representations (ICLR) 2015 San Diego California United States."},{"key":"e_1_2_10_27_2","first-page":"1","article-title":"Why do deep convolutional networks generalize so poorly to small image transformations?","volume":"20","author":"Azulay A.","year":"2019","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_2_10_28_2","doi-asserted-by":"crossref","unstructured":"WongS. C. GattA. StamatescuV. andMcDonnellM. D. Understanding data augmentation for classification: when to warp? Proceedings of 2016 international conference on digital image computing: techniques and applications (DICTA) 2016 Gold Coast QLD Australia 1\u20136.","DOI":"10.1109\/DICTA.2016.7797091"},{"key":"e_1_2_10_29_2","doi-asserted-by":"publisher","DOI":"10.1093\/mnras\/stv632"},{"key":"e_1_2_10_30_2","doi-asserted-by":"publisher","DOI":"10.1631\/FITEE.1700808"},{"key":"e_1_2_10_31_2","doi-asserted-by":"crossref","unstructured":"SifreL.andMallatS. Rotation scaling and deformation invariant scattering for texture discrimination Proceedings of 2013 IEEE conference on computer vision and pattern recognition (CVPR) 2013 Portland OR USA 1233\u20131240.","DOI":"10.1109\/CVPR.2013.163"},{"key":"e_1_2_10_32_2","unstructured":"ZhangR. Making convolutional networks shift-invariant again International Conference on Machine Learning (ICML) 2019 Long Beach California USA 7324\u20137334."},{"key":"e_1_2_10_33_2","first-page":"646","article-title":"Measuring invariances in deep networks","volume":"22","author":"Goodfellow I.","year":"2009","journal-title":"Advances in neural information processing systems"},{"key":"e_1_2_10_34_2","unstructured":"XuY. XiaoT. ZhangJ. YangK. andZhangZ. Scale-invariant convolutional neural networks 2014 https:\/\/arxiv.org\/abs\/1411.6369."},{"key":"e_1_2_10_35_2","doi-asserted-by":"crossref","unstructured":"TorralbaA.andEfrosA. A. Unbiased look at dataset bias Proceedings of CVPR 2011 Colorado Springs CO USA 1521\u20131528.","DOI":"10.1109\/CVPR.2011.5995347"},{"key":"e_1_2_10_36_2","unstructured":"DonahueJ. JiaY. VinyalsO. HoffmanJ. ZhangN. TzengE. andDarrellT. A deep convolutional activation feature for generic visual recognition 2013 https:\/\/arxiv.org\/abs\/1310.1531."},{"key":"e_1_2_10_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.230"},{"key":"e_1_2_10_38_2","unstructured":"SohnK.andLeeH. Learning invariant representations with local transformations Proceedings of the 29 th International Conference on Machine Learning (ICML) 2012 Edinburgh Scotland UK 1339\u20131346."},{"key":"e_1_2_10_39_2","unstructured":"RudermanA. RabinowitzN. C. MorcosA. S. andZoranD. Pooling is neither necessary nor sufficient for appropriate deformation stability in CNNs 2018 https:\/\/arxiv.org\/abs\/1804.04438."},{"key":"e_1_2_10_40_2","unstructured":"BrunaJ. SzlamA. andLeCunY. Learning stable group invariant representations with convolutional networks Ist International Conference on Learning Representations (ICLR) 2013 Scottsdale Arizona USA."},{"key":"e_1_2_10_41_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.50"},{"key":"e_1_2_10_42_2","unstructured":"CohenT. S.andWellingM. Transformation properties of learned visual representations International Conference on Learning Representations (ICLR) 2015 San Diego California United States 1\u201311."},{"key":"e_1_2_10_43_2","first-page":"1125","article-title":"Sparse filtering","volume":"24","author":"Ngiam J.","year":"2011","journal-title":"Advances in neural information processing systems"},{"key":"e_1_2_10_44_2","unstructured":"HintonG. E. SrivastavaN. KrizhevskyA. SutskeverI. andSalakhutdinovR. R. Improving neural networks by preventing co-adaptation of feature detectors 2012 https:\/\/arxiv.org\/abs\/1207.0580."},{"key":"e_1_2_10_45_2","unstructured":"LabachA. SalehinejadH. andValaeeS. Survey of dropout methods for deep neural networks 2019 https:\/\/arxiv.org\/abs\/1904.13310."},{"key":"e_1_2_10_46_2","unstructured":"IoffeS.andSzegedyC. Batch normalization: accelerating deep network training by reducing internal covariate shift International Conference on Machine Learning (ICML) 2015 Lille France 448\u2013456."},{"key":"e_1_2_10_47_2","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.3015157"},{"key":"e_1_2_10_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.3016820"},{"key":"e_1_2_10_49_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2878958"},{"key":"e_1_2_10_50_2","doi-asserted-by":"publisher","DOI":"10.1109\/MGRS.2020.2979764"},{"key":"e_1_2_10_51_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2020.06.014"},{"key":"e_1_2_10_52_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11222-016-9696-4"},{"key":"e_1_2_10_53_2","unstructured":"KingmaD. P.andBaJ. Adam: a method for stochastic optimization International Conference on Learning Representations (ICLR) 2015 San Diego California United States 1\u201315."}],"container-title":["Wireless Communications and Mobile Computing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/downloads.hindawi.com\/journals\/wcmc\/2021\/5539907.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/wcmc\/2021\/5539907.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1155\/2021\/5539907","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,7]],"date-time":"2024-08-07T11:01:35Z","timestamp":1723028495000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1155\/2021\/5539907"}},"subtitle":[],"editor":[{"given":"Danfeng","family":"Hong","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2021,1]]},"references-count":53,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2021,1]]}},"alternative-id":["10.1155\/2021\/5539907"],"URL":"https:\/\/doi.org\/10.1155\/2021\/5539907","archive":["Portico"],"relation":{},"ISSN":["1530-8669","1530-8677"],"issn-type":[{"type":"print","value":"1530-8669"},{"type":"electronic","value":"1530-8677"}],"subject":[],"published":{"date-parts":[[2021,1]]},"assertion":[{"value":"2021-02-09","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-06-08","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-07-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"5539907"}}