{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T02:36:46Z","timestamp":1784342206734,"version":"3.55.0"},"reference-count":61,"publisher":"MDPI AG","issue":"10","license":[{"start":{"date-parts":[[2020,5,25]],"date-time":"2020-05-25T00:00:00Z","timestamp":1590364800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Xiamen University Malaysia","award":["XMUMRF\/2019-C3\/IECE\/0007"],"award-info":[{"award-number":["XMUMRF\/2019-C3\/IECE\/0007"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>The electrocardiogram (ECG) is one of the most extensively employed signals used in the diagnosis and prediction of cardiovascular diseases (CVDs). The ECG signals can capture the heart\u2019s rhythmic irregularities, commonly known as arrhythmias. A careful study of ECG signals is crucial for precise diagnoses of patients\u2019 acute and chronic heart conditions. In this study, we propose a two-dimensional (2-D) convolutional neural network (CNN) model for the classification of ECG signals into eight classes; namely, normal beat, premature ventricular contraction beat, paced beat, right bundle branch block beat, left bundle branch block beat, atrial premature contraction beat, ventricular flutter wave beat, and ventricular escape beat. The one-dimensional ECG time series signals are transformed into 2-D spectrograms through short-time Fourier transform. The 2-D CNN model consisting of four convolutional layers and four pooling layers is designed for extracting robust features from the input spectrograms. Our proposed methodology is evaluated on a publicly available MIT-BIH arrhythmia dataset. We achieved a state-of-the-art average classification accuracy of 99.11%, which is better than those of recently reported results in classifying similar types of arrhythmias. The performance is significant in other indices as well, including sensitivity and specificity, which indicates the success of the proposed method.<\/jats:p>","DOI":"10.3390\/rs12101685","type":"journal-article","created":{"date-parts":[[2020,5,25]],"date-time":"2020-05-25T11:42:02Z","timestamp":1590406922000},"page":"1685","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":233,"title":["Classification of Arrhythmia by Using Deep Learning with 2-D ECG Spectral Image Representation"],"prefix":"10.3390","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1911-4270","authenticated-orcid":false,"given":"Amin","family":"Ullah","sequence":"first","affiliation":[{"name":"Software Engineering Department, University of Engineering and Technology Taxila, Punjab 47050, Pakistan"},{"name":"Center for research in computer vision lab (CRCV Lab), College of Engineering and Computer Science, University of Central Florida (UCF), Orlando, FL 32816, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8179-3959","authenticated-orcid":false,"given":"Syed Muhammad","family":"Anwar","sequence":"additional","affiliation":[{"name":"Software Engineering Department, University of Engineering and Technology Taxila, Punjab 47050, Pakistan"},{"name":"Center for research in computer vision lab (CRCV Lab), College of Engineering and Computer Science, University of Central Florida (UCF), Orlando, FL 32816, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4221-0877","authenticated-orcid":false,"given":"Muhammad","family":"Bilal","sequence":"additional","affiliation":[{"name":"Computer and Electronics Systems Engineering, Hankuk University of Foreign Studies, Yongin-si 17035, Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2284-0479","authenticated-orcid":false,"given":"Raja Majid","family":"Mehmood","sequence":"additional","affiliation":[{"name":"Information and Communication Technology Department, School of Electrical and Computer Engineering, Xiamen University Malaysia, Sepang 43900, Malaysia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2020,5,25]]},"reference":[{"key":"ref_1","first-page":"1","article-title":"Cardiovascular disease as a leading cause of death: How are pharmacists getting involved?","volume":"8","author":"Alzubaidi","year":"2019","journal-title":"Integr. Pharm. Res. Pract."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"569","DOI":"10.1016\/j.cjca.2015.01.009","article-title":"Global burden of cardiovascular disease and stroke: Hypertension at the core","volume":"31","author":"Lackland","year":"2015","journal-title":"Can. J. Cardiol."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"101761","DOI":"10.1016\/j.artmed.2019.101761","article-title":"A modular cluster based collaborative recommender system for cardiac patients","volume":"102","author":"Mustaqeem","year":"2020","journal-title":"Artif. Intell. Med."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Irmakci, I., Anwar, S.M., Torigian, D.A., and Bagci, U. (2020). Deep Learning for Musculoskeletal Image Analysis. arXiv.","DOI":"10.1109\/IEEECONF44664.2019.9048671"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"226","DOI":"10.1007\/s10916-018-1088-1","article-title":"Medical image analysis using convolutional neural networks: A review","volume":"42","author":"Anwar","year":"2018","journal-title":"J. Med. Syst."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"354","DOI":"10.1016\/j.patcog.2017.10.013","article-title":"Recent advances in convolutional neural networks","volume":"77","author":"Gu","year":"2018","journal-title":"Pattern Recognit."},{"key":"ref_7","unstructured":"Wu, Y., Yang, F., Liu, Y., Zha, X., and Yuan, S. (2018). A comparison of 1-D and 2-D deep convolutional neural networks in ECG classification. arXiv."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"312","DOI":"10.1016\/j.bspc.2018.08.035","article-title":"Speech emotion recognition using deep 1D & 2-D CNN LSTM networks. Biomed","volume":"47","author":"Zhao","year":"2019","journal-title":"Signal Process. Control"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Ortega, S., Fabelo, H., Iakovidis, D.K., Koulaouzidis, A., and Callico, G.M. (2019). Use of hyperspectral\/multispectral imaging in gastroenterology. Shedding some\u2013different\u2013light into the dark. J. Clin. Med., 8.","DOI":"10.3390\/jcm8010036"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1039","DOI":"10.1080\/10408398.2011.651542","article-title":"Application of Hyperspectral Imaging in Food Safety Inspection and Control: A Review","volume":"52","author":"Feng","year":"2012","journal-title":"Crit. Rev. Food Sci. Nutr."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"1121","DOI":"10.1007\/s11947-011-0725-1","article-title":"Recent Advances and Applications of Hyperspectral Imaging for Fruit and Vegetable Quality Assessment","volume":"5","author":"Lorente","year":"2011","journal-title":"Food Bioprocess Technol."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1016\/j.rti.2005.04.003","article-title":"Industrial application for inline material sorting using hyperspectral imaging in the NIR range","volume":"11","author":"Tatzer","year":"2005","journal-title":"Real-Time Imaging"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"199","DOI":"10.1016\/S1871-1731(07)80007-8","article-title":"Chapter 5 Hyperspectral Imaging: A New Technique for the Non-Invasive Study of Artworks","volume":"2","author":"Kubik","year":"2007","journal-title":"Phys. Tech. Study Art Archaeol. Cult. Herit."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"3611","DOI":"10.1002\/ett.3611","article-title":"Single image defocus estimation by modified gaussian function","volume":"30","author":"Hassan","year":"2019","journal-title":"Trans. Emerg. Telecommun. Technol."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"86","DOI":"10.1016\/j.ijleo.2017.03.051","article-title":"Metric similarity regularizer to enhance pixel similarity performance for hyperspectral unmixing","volume":"140","author":"Ahmad","year":"2017","journal-title":"Optik"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Salem, M., Taheri, S., and Yuan, J.S. (2018, January 17\u201319). ECG arrhythmia classification using transfer learning from 2-dimensional deep CNN features. Proceedings of the 2018 IEEE Biomedical Circuits and Systems Conference (BioCAS), Cleveland, OH, USA.","DOI":"10.1109\/BIOCAS.2018.8584808"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"134","DOI":"10.1016\/j.ijmedinf.2017.10.008","article-title":"A statistical analysis based recommender model for heart disease patients","volume":"108","author":"Mustaqeem","year":"2017","journal-title":"Int. J. Med. Inform."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Anwar, S.M., Gul, M., Majid, M., and Alnowami, M. (2018). Arrhythmia Classification of ECG Signals Using Hybrid Features. Comput. Math. Methods Med.","DOI":"10.1155\/2018\/1380348"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Mustaqeem, A., Anwar, S.M., and Majid, M. (2018). Multiclass classification of cardiac arrhythmia using improved feature selection and SVM invariants. Comput. Math. Methods Med.","DOI":"10.1155\/2018\/7310496"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Mustaqeem, A., Anwar, S.M., Majid, M., and Khan, A.R. (2017, January 11\u201315). Wrapper method for feature selection to classify cardiac arrhythmia. Proceedings of the 2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Jeju Island, Korea.","DOI":"10.1109\/EMBC.2017.8037650"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"179","DOI":"10.1109\/10.740880","article-title":"Real-time discrimination of ventricular tachyarrhythmia with Fourier-transform neural network","volume":"46","author":"Minami","year":"1999","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"826","DOI":"10.1109\/10.58593","article-title":"An approach to cardiac arrhythmia analysis using hidden markov models","volume":"37","author":"Coast","year":"1990","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"582","DOI":"10.1109\/TBME.2004.824138","article-title":"Support vector machine based expert system for reliable heartbeat recognition","volume":"51","author":"Osowski","year":"2004","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1016\/S0022-0736(87)80096-1","article-title":"Comparison of multigroup logistic and linear discriminant ecg and vcg classification","volume":"20","author":"Willems","year":"1987","journal-title":"J. Electrocardiol."},{"key":"ref_25","first-page":"66","article-title":"Applications of artificial neural networks for ECG signal detection and classification","volume":"26","author":"Hu","year":"1993","journal-title":"J. Electrocardiol."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"648","DOI":"10.1109\/34.56207","article-title":"Syntactic pattern recognition of the ECG","volume":"12","author":"Trahanias","year":"1990","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"2507","DOI":"10.1109\/TBME.2006.880879","article-title":"Robust neural-network-based classification of premature ventricular contractions using wavelet transform and timing interval features","volume":"53","author":"Inan","year":"2006","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"891","DOI":"10.1109\/10.623058","article-title":"A patient-adaptable ECG beat classifier using a mixture of experts approach","volume":"44","author":"Hu","year":"1997","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_29","first-page":"27","article-title":"Novel ECG diagnosis model based on multi-stage artificial neural networks","volume":"29","author":"Dehan","year":"2008","journal-title":"Chin. J. Sci. Instrum."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"286","DOI":"10.1016\/j.eswa.2006.05.014","article-title":"Comparison of FCM, PCA and WT techniques for classification ECG arrhythmias using artificial neural network","volume":"33","author":"Ceylan","year":"2007","journal-title":"Expert Syst. Appl."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"694","DOI":"10.1016\/j.dsp.2006.10.008","article-title":"Breast cancer diagnosis using least square support vector machine","volume":"17","author":"Polat","year":"2007","journal-title":"Digit. Signal Process."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"28","DOI":"10.1006\/jbin.2001.1004","article-title":"A comparison of machine learning methods for the diagnosis of pigmented skin lesions","volume":"34","author":"Dreiseitl","year":"2001","journal-title":"J. Biomed. Inform."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"4867","DOI":"10.1007\/s11227-018-2263-3","article-title":"A machine learning approach for feature selection traffic classification using security analysis","volume":"74","author":"Shafiq","year":"2018","journal-title":"J. Supercomput."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"3627","DOI":"10.1002\/ett.3627","article-title":"An optimal multitier resource allocation of cloud RAN in 5G using machine learning","volume":"30","author":"Bashir","year":"2019","journal-title":"Trans. Emerg. Telecommun. Technol."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"89","DOI":"10.1016\/S0933-3657(01)00077-X","article-title":"Machine learning for medical diagnosis: History, state of the art and perspective","volume":"23","author":"Kononenko","year":"2001","journal-title":"Artif. Intell. Med."},{"key":"ref_36","unstructured":"Ecar, A. (1987). Recommended practice for testing and reporting performance results of ventricular arrhythmia detection algorithms. Assoc. Adv. Med. Instrum., 69."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"112","DOI":"10.1007\/s00259-014-2882-8","article-title":"Machine learning models for the differential diagnosis of vascular parkinsonism and Parkinson\u2019s disease using [123 I] FP-CIT SPECT","volume":"42","author":"Jesus","year":"2015","journal-title":"Eur. J. Nucl. Med. Mol. Imaging"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"307","DOI":"10.3389\/fnins.2015.00307","article-title":"Magnetic resonance imaging biomarkers for the early diagnosis of Alzheimer\u2019s disease: A machine learning approach","volume":"9","author":"Salvatore","year":"2015","journal-title":"Front. Neurosci."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"664","DOI":"10.1109\/TBME.2015.2468589","article-title":"Real-time patient-specific ECG classification by 1-D convolutional neural networks","volume":"63","author":"Kiranyaz","year":"2015","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_40","unstructured":"Rajpurkar, P., Hannun, A.Y., Haghpanahi, M., Bourn, C., and Ng, A.Y. (2017). Cardiologist-level arrhythmia detection with convolutional neural networks. arXiv."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"389","DOI":"10.1016\/j.compbiomed.2017.08.022","article-title":"A deep convolutional neural network model to classify heartbeats","volume":"89","author":"Acharya","year":"2017","journal-title":"Comput. Biol. Med."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"120831","DOI":"10.1109\/ACCESS.2019.2937875","article-title":"Smart Heart Monitoring: Early Prediction of Heart Problems Through Predictive Analysis of ECG Signals","volume":"7","author":"Chen","year":"2019","journal-title":"IEEE Access"},{"key":"ref_43","unstructured":"Lee, S.C. (1990). Using a translation-invariant neural network to diagnose heart arrhythmia. Advances in Neural Information Processing Systems, Morgan Kaufmann."},{"key":"ref_44","first-page":"2535","article-title":"A patient-adapting heartbeat classifier using ECG morphology and heartbeat interval features","volume":"53","author":"Reilly","year":"2015","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Xiong, Z., Stiles, M.K., and Zhao, J. (2017, January 24\u201327). Robust ECG signal classification for detection of atrial fibrillation using a novel neural network. Proceedings of the 2017 Computing in Cardiology (CinC), Rennes, France.","DOI":"10.22489\/CinC.2017.066-138"},{"key":"ref_46","unstructured":"Clevert, D.A., Unterthiner, T., and Hochreiter, S. (2015). Fast and accurate deep network learning by exponential linear units (elus). arXiv."},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Li, D., Zhang, J., Zhang, Q., and Wei, X. (2017, January 12\u201315). Classification of ECG signals based on 1D convolution neural network. Proceedings of the 2017 IEEE 19th International Conference on e-Health Networking, Applications and Services (Healthcom), Dalian, China.","DOI":"10.1109\/HealthCom.2017.8210784"},{"key":"ref_48","unstructured":"Jun, T.J., Nguyen, H.M., Kang, D., Kim, D., Kim, D., and Kim, Y.H. (2018). ECG arrhythmia classification using a 2-D convolutional neural network. arXiv."},{"key":"ref_49","doi-asserted-by":"crossref","unstructured":"Mohanty, M.D., Mohanty, B., and Mohanty, M.N. (2017, January 21\u201323). R-peak detection using efficient technique for tachycardia detection. Proceedings of the 2017 2nd International Conference on Man and Machine Interfacing (MAMI), Bhubaneswar, India.","DOI":"10.1109\/MAMI.2017.8307877"},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1109\/51.932724","article-title":"The impact of the MIT-BIH arrhythmia database","volume":"20","author":"Moody","year":"2001","journal-title":"IEEE Eng. Med. Biol. Mag."},{"key":"ref_51","unstructured":"Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G.S., Davis, A., Dean, J., and Devin, M. (2016). Tensorflow: Large-scale machine learning on heterogeneous distributed systems. arXiv."},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"320","DOI":"10.1016\/j.dsp.2008.09.002","article-title":"Combining recurrent neural networks with eigenvector methods for classification of ECG beats","volume":"19","year":"2009","journal-title":"Digit. Signal Process."},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"1161","DOI":"10.1016\/j.medengphy.2010.08.007","article-title":"Correlation technique and least square support vector machine combine for frequency domain based ECG beat classification","volume":"32","author":"Dutta","year":"2010","journal-title":"Med. Eng. Phys."},{"key":"ref_54","first-page":"31","article-title":"Investigating cardiac arrhythmia in ECG using random forest classification","volume":"37","author":"Kumar","year":"2012","journal-title":"Int. J. Comput. Appl."},{"key":"ref_55","doi-asserted-by":"crossref","unstructured":"Park, J., Lee, K., and Kang, K. (2013, January 18\u201321). Arrhythmia detection from heartbeat using k-nearest neighbor classifier. Proceedings of the 2013 IEEE International Conference on Bioinformatics and Biomedicine, Shanghai, China.","DOI":"10.1109\/BIBM.2013.6732594"},{"key":"ref_56","doi-asserted-by":"crossref","first-page":"7067","DOI":"10.1109\/TIE.2016.2582729","article-title":"Real-time motor fault detection by 1-D convolutional neural networks","volume":"63","author":"Ince","year":"2016","journal-title":"IEEE Trans. Ind. Electron."},{"key":"ref_57","doi-asserted-by":"crossref","unstructured":"Izci, E., Ozdemir, M.A., Degirmenci, M., and Akan, A. (2019, January 3\u20135). Cardiac Arrhythmia Detection from 2D ECG Images by Using Deep Learning Technique. Proceedings of the 2019 Medical Technologies Congress (TIPTEKNO), Sel\u00e7uk, Turkey.","DOI":"10.1109\/TIPTEKNO.2019.8895011"},{"key":"ref_58","doi-asserted-by":"crossref","unstructured":"Rajkumar, A., Ganesan, M., and Lavanya, R. (2019, January 15\u201316). Arrhythmia classification on ECG using Deep Learning. Proceedings of the 2019 5th International Conference on Advanced Computing and Communication Systems (ICACCS), Coimbatore, India.","DOI":"10.1109\/ICACCS.2019.8728362"},{"key":"ref_59","doi-asserted-by":"crossref","first-page":"199","DOI":"10.1016\/j.patcog.2004.06.009","article-title":"ECG beat classifier designed by combined neural network model","volume":"38","author":"Guler","year":"2005","journal-title":"Pattern Recognit."},{"key":"ref_60","doi-asserted-by":"crossref","first-page":"2841","DOI":"10.1016\/j.eswa.2007.05.006","article-title":"Integration of independent component analysis and neural networks for ECG beat classification","volume":"34","author":"Yu","year":"2008","journal-title":"Expert Syst. Appl."},{"key":"ref_61","doi-asserted-by":"crossref","first-page":"667","DOI":"10.1109\/TITB.2008.923147","article-title":"Classification of electrocardiogram signals with support vector machines and particle swarm optimization","volume":"12","author":"Melgani","year":"2008","journal-title":"IEEE Trans. Inf. Technol. Biomed."}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/12\/10\/1685\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T09:32:09Z","timestamp":1760175129000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/12\/10\/1685"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5,25]]},"references-count":61,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2020,5]]}},"alternative-id":["rs12101685"],"URL":"https:\/\/doi.org\/10.3390\/rs12101685","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,5,25]]}}}