{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,27]],"date-time":"2026-10-27T00:01:52Z","timestamp":1793059312049,"version":"4.5.0"},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2021,1,28]],"date-time":"2021-01-28T00:00:00Z","timestamp":1611792000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2021,1,28]],"date-time":"2021-01-28T00:00:00Z","timestamp":1611792000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100010909","name":"Young Scientists Fund","doi-asserted-by":"publisher","award":["61801104"],"award-info":[{"award-number":["61801104"]}],"id":[{"id":"10.13039\/501100010909","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010909","name":"Young Scientists Fund","doi-asserted-by":"publisher","award":["61902058"],"award-info":[{"award-number":["61902058"]}],"id":[{"id":"10.13039\/501100010909","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BioMed Eng OnLine"],"published-print":{"date-parts":[[2021,12]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec>\n                <jats:title>Background<\/jats:title>\n                <jats:p>Atrial fibrillation (AF) represents the most common arrhythmia worldwide, related to increased risk of ischemic stroke or systemic embolism. It is critical to screen and diagnose AF for the benefits of better cardiovascular health in lifetime. The ECG-based AF detection, the gold standard in clinical care, has been restricted by the need to attach electrodes on the body surface. Recently, ballistocardiogram (BCG) has been investigated for AF diagnosis, which is an unobstructive and convenient technique to monitor heart activity in daily life. However, here is a lack of high-dimension representation and deep learning analysis of BCG.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Method<\/jats:title>\n                <jats:p>Therefore, this paper proposes an attention-based multi-scale features fusion method by using BCG signal. The 1-D morphology feature extracted from Bi-LSTM network and 2-D rhythm feature extracted from reconstructed phase space are integrated by means of CNN network to improve the robustness of AF detection. To the best of our knowledge, this is the first study where the phase space trajectory of BCG is conducted.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Results<\/jats:title>\n                <jats:p>2000 segments (AF and NAF) of BCG signals were collected from 59 volunteers suffering from paroxysmal AF in this survey. Compared to the classical time and frequency features and the state-of-the-art energy features with the popular machine learning classifiers, AF detection performance of the proposed method is superior, which has 0.947 accuracy, 0.935 specificity, 0.959 sensitivity, and 0.937 precision, for the same BCG dataset. The experimental results show that combined feature could excavate more potential characteristics, and the attention mechanism could enhance the pertinence for AF recognition.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Conclusions<\/jats:title>\n                <jats:p>The proposed method can provide an innovative solution to capture the diverse scale descriptions of BCG and explore ways to involve the deep learning method to accurately screen AF in routine life.<\/jats:p>\n              <\/jats:sec>","DOI":"10.1186\/s12938-021-00848-w","type":"journal-article","created":{"date-parts":[[2021,1,28]],"date-time":"2021-01-28T09:36:17Z","timestamp":1611826577000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":19,"title":["Attention-based multi-scale features fusion for unobtrusive atrial fibrillation detection using ballistocardiogram signal"],"prefix":"10.1186","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5822-9842","authenticated-orcid":false,"given":"Fangfang","family":"Jiang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chuhang","family":"Hong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianqing","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haoqian","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bowen","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Biyong","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,1,28]]},"reference":[{"key":"848_CR1","doi-asserted-by":"publisher","first-page":"1042","DOI":"10.1161\/01.CIR.0000140263.20897.42","volume":"110","author":"DM LloydJones","year":"2004","unstructured":"LloydJones DM, Wang TJ, Leip EP, Larson MG, Levy D, Vasan RS, et al. Lifetime risk for development of atrial fibrillation: the Framingham heart study. Circulation. 2004;110:1042\u20136.","journal-title":"Circulation."},{"key":"848_CR2","doi-asserted-by":"publisher","first-page":"949","DOI":"10.1093\/eurheartj\/ehi825","volume":"27","author":"J Heeringa","year":"2006","unstructured":"Heeringa J, Kuip DA, Hofman A, Hofman A, Kors JA, Herpen GA, et al. Prevalence, incidence and lifetime risk of atrial fibrillation: the Rotterdam study. Eur Heart J. 2006;27:949\u201353.","journal-title":"Eur Heart J."},{"key":"848_CR3","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1378\/chest.14-0321","volume":"147","author":"Y Guo","year":"2015","unstructured":"Guo Y, Tian Y, Wang H, Si QJ, Wang Y, Lip GYH. Prevalence, incidence, and lifetime risk of atrial fibrillation in China: new insights into the global burden of atrial fibrillation. Chest. 2015;147:109\u201319.","journal-title":"Chest."},{"key":"848_CR4","doi-asserted-by":"publisher","first-page":"e006350","DOI":"10.1161\/CIRCEP.118.006350","volume":"11","author":"LP Mou","year":"2018","unstructured":"Mou LP, Norby FL, Chen LY, O\u2019Neal WT, Lewis TT, Loehr LR, et al. Lifetime risk of atrial fibrillation by race and socioeconomic status: the atherosclerosis risk in communities (ARIC) study. Circ Arrhythm Electrophysiol. 2018;11:e006350.","journal-title":"Circ Arrhythm Electrophysiol."},{"key":"848_CR5","doi-asserted-by":"publisher","first-page":"1003","DOI":"10.1109\/TBME.2016.2585109","volume":"64","author":"D Shao","year":"2017","unstructured":"Shao D, Tsow F, Liu C, Yang Y, Tao N. Simultaneous monitoring of ballistocardiogram and photoplethysmogram using a camera. IEEE Trans Biomed Eng. 2017;64:1003\u201310.","journal-title":"IEEE Trans Biomed Eng."},{"key":"848_CR6","doi-asserted-by":"publisher","first-page":"162","DOI":"10.1109\/TITB.2012.2225067","volume":"17","author":"C Bruser","year":"2013","unstructured":"Bruser C, Diesel J, Zink MDH, Winter S, Schauerte P, Leonhardt S. Automatic detection of atrial fibrillation in cardiac vibration signals. IEEE J Biomed Health Inform. 2013;17:162\u201371.","journal-title":"IEEE J Biomed Health Inform."},{"key":"848_CR7","first-page":"1","volume":"2015","author":"MD Zink","year":"2015","unstructured":"Zink MD, Br\u00fcser C, Winnersbach P, Napp A, Leonhardt S, Marx N, et al. Heartbeat cycle length detection by a ballistocardiographic sensor in atrial fibrillation and sinus rhythm. Biomed Res Intern. 2015;2015:1\u201310.","journal-title":"Biomed Res Intern."},{"key":"848_CR8","unstructured":"Yu B, Zhang B, Xu L, Fang P, Jun H. Automatic detection of atrial fibrillation from ballistocardiogram (BCG) using wavelet features and machine learning. In: 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). Berlin, Germany. 2019;2019(1):4322\u20135."},{"key":"848_CR9","doi-asserted-by":"publisher","first-page":"1093","DOI":"10.1109\/JBHI.2019.2927165","volume":"24","author":"X Wen","year":"2020","unstructured":"Wen X, Huang Y, Wu XM, Zhang B. A feasible feature extraction method for atrial fibrillation detection from BCG. IEEE J Biomed Health Inform. 2020;24:1093\u2013103.","journal-title":"IEEE J Biomed Health Inform."},{"key":"848_CR10","doi-asserted-by":"crossref","unstructured":"Wu Z, Ding X, Zhang G, Xu X, et al. A novel features learning method for ECG arrhythmias using deep belief networks. In: 6th International Conference on Digital Home (ICDH), Guangzhou, China. 2016;1:192\u20136.","DOI":"10.1109\/ICDH.2016.048"},{"key":"848_CR11","doi-asserted-by":"publisher","first-page":"102119","DOI":"10.1109\/ACCESS.2019.2931500","volume":"7","author":"R He","year":"2019","unstructured":"He R, Liu Y, Wang K, Zhao N, et al. Automatic cardiac arrhythmia classification using combination of deep residual network and bidirectional LSTM. IEEE Access. 2019;7:102119\u201335.","journal-title":"IEEE Access."},{"key":"848_CR12","doi-asserted-by":"publisher","first-page":"1744","DOI":"10.1109\/JBHI.2018.2858789","volume":"22","author":"X Fan","year":"2018","unstructured":"Fan X, Yao Q, Cai Y, Miao F, Sun F, Li Y. Multiscaled fusion of deep convolutional neural networks for screening atrial fibrillation from single lead short ECG recordings. IEEE J Biomed Health Inform. 2018;22:1744\u201353.","journal-title":"IEEE J Biomed Health Inform."},{"key":"848_CR13","doi-asserted-by":"publisher","first-page":"1943","DOI":"10.1166\/jmihi.2019.2819","volume":"9","author":"F Jiang","year":"2019","unstructured":"Jiang F, Xu J, Lu Z, Song B, Hu Z, Li R. A transfer learning approach to detect paroxysmal atrial fibrillation automatically based on ballistocardiogram signal. J Med Imag Health Inform. 2019;9:1943\u20139.","journal-title":"J Med Imag Health Inform."},{"key":"848_CR14","doi-asserted-by":"publisher","first-page":"2095","DOI":"10.1109\/TSMC.2017.2705582","volume":"48","author":"B Pourbabaee","year":"2018","unstructured":"Pourbabaee B, Roshtkhari MJ, Khorasani K. Deep convolutional neural networks and learning ECG features for screening paroxysmal atrial brillation patients. IEEE Trans Syst Man Cybernet ICS Syst. 2018;48:2095\u2013104.","journal-title":"IEEE Trans Syst Man Cybernet ICS Syst."},{"key":"848_CR15","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1016\/j.ins.2017.04.012","volume":"405","author":"UR Acharya","year":"2017","unstructured":"Acharya UR, Fujita H, Lih OS, Hagiwara Y, Tan JH, Adam M. Automated detection of arrhythmias using different intervals of tachycardia ECG segments with convolutional neural network. Inform Sci. 2017;405:81\u201390.","journal-title":"Inform Sci."},{"key":"848_CR16","first-page":"176","volume":"30","author":"J Jin","year":"2009","unstructured":"Jin J, Wang X, Yang D. Heart rate measurement based on uttering signal from human body. J Northeastern Univ Nat Sci. 2009;30:176\u20139.","journal-title":"J Northeastern Univ Nat Sci."},{"key":"848_CR17","doi-asserted-by":"publisher","first-page":"503","DOI":"10.1093\/biomet\/76.3.503","volume":"76","author":"B Prabir","year":"1989","unstructured":"Prabir B. A comparative study of ordinary cross-validation, v-fold cross-validation and the repeated learning-testing methods. Biometrika. 1989;76:503\u201314.","journal-title":"Biometrika."},{"key":"848_CR18","first-page":"361","volume":"898","author":"F Takens","year":"1981","unstructured":"Takens F. Detecting strange attractors in turbulenee. Lecture Notes. 1981;898:361\u201381.","journal-title":"Lecture Notes."},{"key":"848_CR19","doi-asserted-by":"publisher","first-page":"159","DOI":"10.1007\/s10462-007-9052-3","volume":"26","author":"SB Kotsiantis","year":"2006","unstructured":"Kotsiantis SB, Zaharakis ID, Pintelas PE. Machine learning: a review of classification and combining techniques. Artif Intell Rev. 2006;26:159\u201390.","journal-title":"Artif Intell Rev."},{"key":"848_CR20","doi-asserted-by":"crossref","unstructured":"Caruana R, Niculescu-Mizil A. An empirical comparison of supervised learning algorithms. In: 23rd International Conference on Machine Learning, Pittsburgh, PA. 2006;1:161\u2013168.","DOI":"10.1145\/1143844.1143865"},{"key":"848_CR21","first-page":"671","volume":"II","author":"A Kuvaev","year":"2019","unstructured":"Kuvaev A, Khudorozhkov R. An attention-based cnn for ECG classification. Polish River Basins and Lakes Part. 2019;II:671\u20137.","journal-title":"Polish River Basins and Lakes Part"},{"key":"848_CR22","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter S, Schmidhuber J. Long short-term memory. Neural Comput. 1997;9:1735\u201380.","journal-title":"Neural Comput."},{"key":"848_CR23","doi-asserted-by":"publisher","first-page":"2086","DOI":"10.1109\/TNSRE.2018.2876129","volume":"26","author":"P Wang","year":"2018","unstructured":"Wang P, Jiang A, Liu X, Shang J, Zhang L. LSTM-based EEG classification in motor imagery tasks. IEEE Trans Neural Syst Rehabil Eng. 2018;26:2086\u201395.","journal-title":"IEEE Trans Neural Syst Rehabil Eng."},{"key":"848_CR24","doi-asserted-by":"publisher","first-page":"515","DOI":"10.1109\/JBHI.2019.2911367","volume":"24","author":"S Saadatnejad","year":"2020","unstructured":"Saadatnejad S, Oveisi M, Hashemi M. LSTM-based ECG classification for continuous monitoring on personal wearable devices. IEEE J Biomed Health Inform. 2020;24:515\u201323.","journal-title":"IEEE J Biomed Health Inform."},{"key":"848_CR25","first-page":"1","volume":"1","author":"ZC Lipton","year":"2016","unstructured":"Lipton ZC, Kale DC, Elkan C. Learning to diagnose with LSTM recurrent neural networks. Intern Conf Learn Represent 2016 San Juan Puerto Rico. 2016;1:1\u201318.","journal-title":"Intern Conf Learn Represent 2016 San Juan Puerto Rico."},{"key":"848_CR26","unstructured":"Huang B, Kinsner W. Impact of low-rate sampling on the reconstruction of ECG in phase-space. In: 2000 Canadian Conference on Electrical and Computer Engineering. Conference Proceedings. Navigating to a New Era (Cat. No.00TH8492), Halifax, NS, Canada. 2000;1:508\u201312."},{"key":"848_CR27","unstructured":"Su F, Dong H. Prediction of ECG signal based on TS fuzzy model of phase space reconstruction. In: 12th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI), Suzhou. China. 2019;2019:1\u20136."},{"key":"848_CR28","doi-asserted-by":"crossref","unstructured":"Sun Z, Wang Q, Xue Q,Liu Q, Tan Q. Data prediction of ECG based on phase space reconstruction and neural network. In: 2018 8th International Conference on Electronics Information and Emergency Communication (ICEIEC), Beijing. 2018;162\u2013165.","DOI":"10.1109\/ICEIEC.2018.8473502"},{"key":"848_CR29","doi-asserted-by":"publisher","first-page":"026209","DOI":"10.1103\/PhysRevE.66.026209","volume":"66","author":"MB Kennel","year":"2002","unstructured":"Kennel MB, Abarbanel HDI. False neighbors and false strands: a reliable minimum embedding dimension algorithm. Phys Rev E. 2002;66:026209.","journal-title":"Phys Rev E."},{"key":"848_CR30","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1016\/S0167-2789(98)00151-1","volume":"121","author":"L Cao","year":"1997","unstructured":"Cao L. Practical method for determining the minimum embedding dimension of a scalar time series. Phys D-Nonlinear Phenom. 1997;121:75\u201388.","journal-title":"Phys D-Nonlinear Phenom"},{"key":"848_CR31","doi-asserted-by":"publisher","first-page":"7073","DOI":"10.1103\/PhysRevA.45.7073","volume":"45","author":"T Buzug","year":"1992","unstructured":"Buzug T, Pfister G. Optimal delay time and embedding dimension for delay-time coordinates by analysis of the global static and local dynamical behavior of strange attractors. Phys Rev A. 1992;45:7073\u201384.","journal-title":"Phys Rev A."},{"key":"848_CR32","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1016\/0167-2789(94)90226-7","volume":"73","author":"MT Rosenstein","year":"1994","unstructured":"Rosenstein MT, Collins JJ, De Luca CJ. Reconstruction expansion as a geometrybased framework for choosing proper delay times. Phys D Nonlinear Phenom. 1994;73:82\u201398.","journal-title":"Phys D Nonlinear Phenom."},{"key":"848_CR33","doi-asserted-by":"publisher","first-page":"024001","DOI":"10.1088\/1361-6579\/aaa93d","volume":"39","author":"PJ Aston","year":"2018","unstructured":"Aston PJ, Christie MI, Huang YH, et al. Beyond HRV: attractor reconstruction using the entire cardiovascular waveform data for novel feature extraction. Physiolog Measure. 2018;39:024001.","journal-title":"Physiolog Measure."},{"key":"848_CR34","unstructured":"Chaudhari S, Polatkan G, Ramanath R, Mithal V. An attentive survey of attention models. 2019 (Preprint)."},{"key":"848_CR35","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L,Gomez A, et al. Attention is all you need. In: Proceedings of the 31st International Conference on Neural Information Processing Systems, New York, United States. 2017;1:6000\u201310."},{"key":"848_CR36","doi-asserted-by":"crossref","unstructured":"Woo SY, Park J, Lee J-Y, Kweon IS. CBAM: convolutional block attention module. European Conference on Computer Vision 2018, Munich, Germany. 2018;1:1\u201317.","DOI":"10.1007\/978-3-030-01234-2_1"}],"container-title":["BioMedical Engineering OnLine"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s12938-021-00848-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1186\/s12938-021-00848-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s12938-021-00848-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,1,28]],"date-time":"2021-01-28T10:33:42Z","timestamp":1611830022000},"score":1,"resource":{"primary":{"URL":"https:\/\/biomedical-engineering-online.biomedcentral.com\/articles\/10.1186\/s12938-021-00848-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,28]]},"references-count":36,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2021,12]]}},"alternative-id":["848"],"URL":"https:\/\/doi.org\/10.1186\/s12938-021-00848-w","relation":{},"ISSN":["1475-925X"],"issn-type":[{"value":"1475-925X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,1,28]]},"assertion":[{"value":"11 October 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 January 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 January 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The experimental protocol was established, according to the ethical guidelines of the Helsinki Declaration and was approved by the Biological and Medical Ethics Committee of Northeastern University (No. 2020B018).","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare that they have no competing interests.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"12"}}