{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T22:34:15Z","timestamp":1775514855795,"version":"3.50.1"},"reference-count":46,"publisher":"MDPI AG","issue":"10","license":[{"start":{"date-parts":[[2021,5,19]],"date-time":"2021-05-19T00:00:00Z","timestamp":1621382400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100010570","name":"Nieders\u00e4chsisches Ministerium f\u00fcr Wissenschaft und Kultur","doi-asserted-by":"publisher","award":["ZN3491"],"award-info":[{"award-number":["ZN3491"]}],"id":[{"id":"10.13039\/501100010570","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Early detection of atrial fibrillation from electrocardiography (ECG) plays a vital role in the timely prevention and diagnosis of cardiovascular diseases. Various algorithms have been proposed; however, they are lacking in considering varied-length signals, morphological transitions, and abnormalities over long-term recordings. We propose dynamic symbolic assignment (DSA) to differentiate a normal sinus rhythm (SR) from paroxysmal atrial fibrillation (PAF). We use ECG signals and their interbeat (RR) intervals from two public databases namely, AF Prediction Challenge Database (AFPDB) and AF Termination Challenge Database (AFTDB). We transform RR intervals into a symbolic representation and compute co-occurrence matrices. The DSA feature is extracted using varied symbol-length V, word-size W, and applied to five machine learning algorithms for classification. We test five hypotheses: (i) DSA captures the dynamics of the series, (ii) DSA is a reliable technique for various databases, (iii) optimal parameters improve DSA\u2019s performance, (iv) DSA is consistent for variable signal lengths, and (v) DSA supports cross-data analysis. Our method captures the transition patterns of the RR intervals. The DSA feature exhibit a statistically significant difference in SR and PAF conditions (p &lt; 0.005). The DSA feature with W=3 and V=3 yield maximum performance. In terms of F-measure (F), rotation forest and ensemble learning classifier are the most accurate for AFPDB (F = 94.6%) and AFTDB (F = 99.8%). Our method is effective for short-length signals and supports cross-data analysis. The DSA is capable of capturing the dynamics of varied-lengths ECG signals. Particularly, the optimal parameters-based DSA feature and ensemble learning could help to detect PAF in long-term ECG signals. Our method maps time series into a symbolic representation and identifies abnormalities in noisy, varied-length, and pathological ECG signals.<\/jats:p>","DOI":"10.3390\/s21103542","type":"journal-article","created":{"date-parts":[[2021,5,19]],"date-time":"2021-05-19T21:49:21Z","timestamp":1621460961000},"page":"3542","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":22,"title":["Automatic Detection of Atrial Fibrillation in ECG Using Co-Occurrence Patterns of Dynamic Symbol Assignment and Machine Learning"],"prefix":"10.3390","volume":"21","author":[{"given":"Nagarajan","family":"Ganapathy","sequence":"first","affiliation":[{"name":"Peter L. Reichertz Institute for Medical Informatics of TU Braunschweig and Hannover Medical School, Braunschweig, 38106 Lower Saxony, Germany"}]},{"given":"Diana","family":"Baumg\u00e4rtel","sequence":"additional","affiliation":[{"name":"Peter L. Reichertz Institute for Medical Informatics of TU Braunschweig and Hannover Medical School, Braunschweig, 38106 Lower Saxony, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3492-4407","authenticated-orcid":false,"given":"Thomas","family":"Deserno","sequence":"additional","affiliation":[{"name":"Peter L. Reichertz Institute for Medical Informatics of TU Braunschweig and Hannover Medical School, Braunschweig, 38106 Lower Saxony, Germany"}]}],"member":"1968","published-online":{"date-parts":[[2021,5,19]]},"reference":[{"key":"ref_1","first-page":"195","article-title":"Atrial fibrillation: The current epidemic","volume":"14","author":"Morillo","year":"2017","journal-title":"J. Geriatr. Cardiol."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"2163","DOI":"10.1109\/TBME.2016.2633277","article-title":"Deterioration of R-Wave Detection in Pathology and Noise: A Comprehensive Analysis Using Simultaneous Truth and Performance Level Estimation","volume":"64","author":"Kashif","year":"2016","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"e1332","DOI":"10.1016\/S2214-109X(19)30318-3","article-title":"World Health Organization cardiovascular disease risk charts: Revised models to estimate risk in 21 global regions","volume":"7","author":"Kaptoge","year":"2019","journal-title":"Lancet Glob. Health"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"305","DOI":"10.3414\/ME15-05-0009","article-title":"Computational electrocardiography: Revisiting Holter ECG monitoring","volume":"55","author":"Deserno","year":"2016","journal-title":"Methods Inf. Med."},{"key":"ref_5","unstructured":"Chandra, B.S., Sastry, C.S., Jana, S., and Patidar, S. (2017, January 24\u201327). Atrial fibrillation detection using convolutional neural networks. Proceedings of the 2017 Computing in Cardiology (CinC), Rennes, France."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1206","DOI":"10.3389\/fphys.2018.01206","article-title":"Automatic Detection of Atrial Fibrillation Based on Continuous Wavelet Transform and 2D Convolutional Neural Networks","volume":"9","author":"He","year":"2018","journal-title":"Front. Physiol."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"219","DOI":"10.1109\/RBME.2020.2976507","article-title":"A Review on the State of the Art in Atrial Fibrillation Detection Enabled by Machine Learning","volume":"14","author":"Rizwan","year":"2020","journal-title":"IEEE Rev. Biomed. Eng."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"123","DOI":"10.1109\/JBHI.2018.2792404","article-title":"Fast QRS Detection and ECG Compression Based on Signal Structural Analysis","volume":"23","author":"Burguera","year":"2018","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"2216","DOI":"10.1109\/JBHI.2019.2963786","article-title":"Delineation of Electrocardiograms Using Multiscale Parameter Estimation","volume":"24","author":"Spicher","year":"2020","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"465","DOI":"10.1016\/j.eswa.2018.08.011","article-title":"A deep learning approach for real-time detection of atrial fibrillation","volume":"115","author":"Andersen","year":"2019","journal-title":"Expert Syst. Appl."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1016\/j.ijmedinf.2017.09.006","article-title":"Improved detection of congestive heart failure via probabilistic symbolic pattern recognition and heart rate variability metrics","volume":"108","author":"Mahajan","year":"2017","journal-title":"Int. J. Med. Inform."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Wang, J., Warnecke, J.M., Haghi, M., and Deserno, T.M. (2020). Unobtrusive Health Monitoring in Private Spaces: The Smart Vehicle. Sensors, 20.","DOI":"10.3390\/s20092442"},{"key":"ref_13","first-page":"3","article-title":"Unobtrusive, through-clothing ECG and Bioimpedance Monitoring in Sleep Apnea Patients","volume":"19","author":"Castro","year":"2020","journal-title":"TC"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"36","DOI":"10.1109\/RBME.2018.2810957","article-title":"A Review of Signal Processing Techniques for Electrocardiogram Signal Quality Assessment","volume":"11","author":"Satija","year":"2018","journal-title":"IEEE Rev. Biomed. Eng."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"S501","DOI":"10.3233\/THC-151002","article-title":"Symbolic representation based on trend features for biomedical data classification","volume":"23","author":"Yin","year":"2015","journal-title":"Technol. Health Care"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"1321","DOI":"10.1109\/JBHI.2019.2942938","article-title":"Inter-Patient ECG Classification with Symbolic Representations and Multi-Perspective Convolutional Neural Networks","volume":"24","author":"Niu","year":"2019","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"133","DOI":"10.1016\/j.cmpb.2018.04.018","article-title":"Automated characterization of cardiovascular diseases using relative wavelet nonlinear features extracted from ECG signals","volume":"161","author":"Adam","year":"2018","journal-title":"Comput. Methods Programs Biomed."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"528","DOI":"10.1080\/07474946.2017.1394719","article-title":"Symbolic pattern recognition for sequential data","volume":"36","author":"Akbilgic","year":"2017","journal-title":"Seq. Anal."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"8","DOI":"10.7243\/2053-7662-4-8","article-title":"Categorizing atrial fibrillation via symbolic pattern recognition","volume":"4","author":"Akbilgic","year":"2016","journal-title":"J. Med. Stat. Inform."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"2154","DOI":"10.3934\/mbe.2019105","article-title":"Anomaly detection in ECG based on trend symbolic aggregate approximation","volume":"16","author":"Zhang","year":"2019","journal-title":"Math. Biosci. Eng."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"40","DOI":"10.1016\/j.cmpb.2010.07.011","article-title":"Prediction of paroxysmal atrial fibrillation based on non-linear analysis and spectrum and bispectrum features of the heart rate variability signal","volume":"105","author":"Mohebbi","year":"2012","journal-title":"Comput. Methods Programs Biomed."},{"key":"ref_22","first-page":"113","article-title":"Predicting the onset of paroxysmal atrial fibrillation: The computers in cardiology challenge 2001","volume":"28","author":"Moody","year":"2001","journal-title":"Comput. Cardiol."},{"key":"ref_23","first-page":"101","article-title":"Spontaneous termination of atrial fibrillation: A challenge from physionet and computers in cardiology 2004","volume":"31","author":"Moody","year":"2004","journal-title":"Comput. Cardiol."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"E215","DOI":"10.1161\/01.CIR.101.23.e215","article-title":"Physiobank, physiotoolkit, and physionet: Components of a new research resource for complex physiologic signals","volume":"101","author":"Goldberger","year":"2000","journal-title":"Circulation"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Le, N.Q.K., Do, D.T., Hung, T.N.K., Lam, L.H.T., Huynh, T.-T., and Nguyen, N.T.K. (2020). A Computational Framework Based on Ensemble Deep Neural Networks for Essential Genes Identification. Int. J. Mol. Sci., 21.","DOI":"10.3390\/ijms21239070"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"2652","DOI":"10.1016\/j.eswa.2013.11.009","article-title":"Extraction and analysis of multiple time window features associated with muscle fatigue conditions using sEMG signals","volume":"41","author":"Venugopal","year":"2014","journal-title":"Expert Syst. Appl."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1016\/j.cmpb.2017.10.024","article-title":"Surface electromyography based muscle fatigue detection using high-resolution time-frequency methods and machine learning algorithms","volume":"154","author":"Karthick","year":"2018","journal-title":"Comput. Methods Programs Biomed."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Wu, X., Gao, Y., and Jiao, D. (2019). Multi-Label Classification Based on Random Forest Algorithm for Non-Intrusive Load Monitoring System. Processes, 7.","DOI":"10.3390\/pr7060337"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"728","DOI":"10.1109\/TKDE.2019.2891622","article-title":"On Combining Biclustering Mining and AdaBoost for Breast Tumor Classification","volume":"32","author":"Huang","year":"2020","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"ref_30","unstructured":"Zong, W., Mukkamala, R., and Mark, R.G. (2001, January 23\u201326). A methodology for predicting paroxysmal atrial fibrillation based on ECG arrhythmia feature analysis. Proceedings of the Computers in Cardiology 2001 Vol28 (Cat No01CH37287), Rotterdam, The Netherlands."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1109\/JBHI.2018.2832610","article-title":"Physonline: An open source machine learning pipeline for real-time analysis of streaming physiological waveform","volume":"23","author":"Sutton","year":"2019","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"2095","DOI":"10.1109\/TSMC.2017.2705582","article-title":"Deep convolutional neural networks and learning ECG features for screening paroxysmal atrial fibrillation patients","volume":"48","author":"Pourbabaee","year":"2018","journal-title":"IEEE Trans. Syst. Man Cybern. Syst."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Le, N.Q.K., Do, D.T., Chiu, F.-Y., Yapp, E.K.Y., Yeh, H.-Y., and Chen, C.-Y. (2020). XGBoost Improves Classification of MGMT Promoter Methylation Status in IDH1 Wildtype Glioblastoma. J. Pers. Med., 10.","DOI":"10.3390\/jpm10030128"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"113571","DOI":"10.1016\/j.eswa.2020.113571","article-title":"Convolutional neural network based emotion classification using electrodermal activity signals and time-frequency features","volume":"159","author":"Ganapathy","year":"2020","journal-title":"Expert Syst. Appl."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"465","DOI":"10.1109\/JBHI.2019.2933046","article-title":"Epilepsy Seizure Prediction on EEG Using Common Spatial Pattern and Convolutional Neural Network","volume":"24","author":"Zhang","year":"2019","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref_36","unstructured":"Habib, A., Karmakar, C., and Yearwood, J. (2020). Choosing a sampling frequency for ECG QRS detection using convolutional networks. arXiv."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Castro, I.D., Varon, C., Torfs, T., Van Huffel, S., Puers, R., and Van Hoof, C. (2018). Evaluation of a Multichannel Non-Contact ECG System and Signal Quality Algorithms for Sleep Apnea Detection and Monitoring. Sensors, 18.","DOI":"10.3390\/s18020577"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1109\/TCDS.2018.2826840","article-title":"Domain Adaptation Techniques for EEG-Based Emotion Recognition: A Comparative Study on Two Public Datasets","volume":"11","author":"Lan","year":"2019","journal-title":"IEEE Trans. Cogn. Dev. Syst."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"162","DOI":"10.3389\/fnins.2018.00162","article-title":"Exploring EEG features in cross-subject emotion recognition","volume":"12","author":"Li","year":"2018","journal-title":"Front. Neurosci."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"38","DOI":"10.1186\/1475-925X-8-38","article-title":"Atrial fibrillation detection by heart rate variability in Poincare plot","volume":"8","author":"Park","year":"2009","journal-title":"Biomed. Eng. Online"},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Natarajan, A., Angarita, G., Gaiser, E., Malison, R., Ganesan, D., and Marlin, B.M. (2016, January 12\u201316). Domain adaptation methods for improving lab-to-field generalization of cocaine detection using wearable ECG. Proceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing, Heidelberg, Germany.","DOI":"10.1145\/2971648.2971666"},{"key":"ref_42","first-page":"806","article-title":"Reliability and Validation of the Hexoskin Wearable Bio-Collection Device During Walking Conditions","volume":"11","author":"Montes","year":"2018","journal-title":"Int. J. Exerc. Sci."},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Wang, J., Spicher, N., Warnecke, J., Haghi, M., Schwartze, J., and Deserno, T. (2021). Unobtrusive Health Monitoring in Private Spaces: The Smart Home. Sensors, 21.","DOI":"10.3390\/s21030864"},{"key":"ref_44","unstructured":"Carre Technologies Inc (2021, May 01). (Hexoskin), Montreal, Canada. Available online: https:\/\/www.hexoskin.com\/."},{"key":"ref_45","unstructured":"(2021, May 01). Capical GmbH, Braunschweig, Germany. Available online: http:\/\/www.capical.de."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"105931","DOI":"10.1016\/j.cmpb.2021.105931","article-title":"Adaptive learning and cross training improves R-wave detection in ECG","volume":"200","author":"Ganapathy","year":"2021","journal-title":"Comput. Methods Programs Biomed."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/10\/3542\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T06:04:18Z","timestamp":1760162658000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/10\/3542"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,19]]},"references-count":46,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2021,5]]}},"alternative-id":["s21103542"],"URL":"https:\/\/doi.org\/10.3390\/s21103542","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,5,19]]}}}