Convolutional Neural Networks for patient-specific ECG classification
The DOI matches its Crossref record; 18 of the 18 references it cites were found in a registry or an index.
Abstract
We propose a fast and accurate patient-specific electrocardiogram (ECG) classification and monitoring system using an adaptive implementation of 1D Convolutional Neural Networks (CNNs) that can fuse feature extraction and classification into a unified learner. In this way, a dedicated CNN will be trained for each patient by using relatively small common and patient-specific training data and thus it can also be used to classify long ECG records such as Holter registers in a fast and accurate manner. Alternatively, such a solution can conveniently be used for real-time ECG monitoring and early alert system on a light-weight wearable device. The experimental results demonstrate that the proposed system achieves a superior classification performance for the detection of ventricular ectopic beats (VEB) and supraventricular ectopic beats (SVEB).
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Kiranyaz et al. [175] presented 1D-CNN, which had the advantages of low computational complexity, highly cost-effective, and real-time application in mobile devices compared to 2D-CNN.”
From Deep Learning for Structural Health Monitoring: Data, Algorithms, Applications, Challenges, and Trends (2023) · cites this paper as [175]
Citations
Cites
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155 · cited 1×
“CNNs are hierarchical neural networks whose convolutional layers alternate with subsampling layers, reminiscent of simple and complex cells in the human visual cortex that are now commonly used for the “deep learning” tasks such as object recognition in large image archives whilst achieving the stateof-the-art perform…”
BackgroundAutomatic Classification of Heartbeats Using ECG Morphology and Heartbeat Interval Features
deChazal, P., O'Dwyer, M., & Reilly, R. B. (2004) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2004.827359 · Cited by 1,671 · cited 2×
“The classification performance of the proposed system is compared with the four existing algorithms, [10], [17], [18], and [19], all of which comply with the AAMI standards.”
MethodEvaluation of Pooling Operations in Convolutional Architectures for Object Recognition
Scherer, D., Müller, A., & Behnke, S. (2010) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-15825-4_10 · Cited by 1,503
Deep, Big, Simple Neural Nets for Handwritten Digit Recognition
Cireşan, D. C., Meier, U., Gambardella, L. M., & Schmidhuber, J. (2010) · Neural Computation · doi:10.1162/neco_a_00052 · Cited by 1,078 · cited 1×
“CNNs are hierarchical neural networks whose convolutional layers alternate with subsampling layers, reminiscent of simple and complex cells in the human visual cortex that are now commonly used for the “deep learning” tasks such as object recognition in large image archives whilst achieving the stateof-the-art perform…”
BackgroundECG beat detection using filter banks
Afonso, V. X., Tompkins, W. J., Nguyen, T. Q., & Luo, S. (1999) · IEEE Transactions on Biomedical Engineering · doi:10.1109/10.740882 · Cited by 728 · cited 1×
“A wide range of methods have been proposed in the past for generic and fully automatic ECG classification based on signal processing techniques such as frequency analysis [1], wavelet transform [2], [3], and filter banks [4], statistical [5] and heuristic approaches [6], hidden Markov models [7], support vector machin…”
A patient-adaptable ECG beat classifier using a mixture of experts approach
Hu, Y. H., Palreddy, S., & Tompkins, W. J. (1997) · IEEE Transactions on Biomedical Engineering · doi:10.1109/10.623058 · Cited by 614 · cited 5×
“A wide range of methods have been proposed in the past for generic and fully automatic ECG classification based on signal processing techniques such as frequency analysis [1], wavelet transform [2], [3], and filter banks [4], statistical [5] and heuristic approaches [6], hidden Markov models [7], support vector machin…”
MethodInfluentialSupport Vector Machine-Based Expert System for Reliable Heartbeat Recognition
Osowski, S., Hoai, L. T., & Markiewicz, T. (2004) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2004.824138 · Cited by 536
A Patient-Adapting Heartbeat Classifier Using ECG Morphology and Heartbeat Interval Features
de Chazal, P., & Reilly, R. B. (2006) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2006.883802 · Cited by 497 · cited 2×
“This makes them unreliable to be widely used clinically or in practice, and they tend to have high variations in their accuracy and efficiency for larger databases, [11], [15].”
BackgroundMethodA Generic and Robust System for Automated Patient-Specific Classification of ECG Signals
Ince, T., Kiranyaz, S., & Gabbouj, M. (2009) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2009.2013934 · Cited by 481 · cited 4×
“The classification performance of the proposed system is compared with the four existing algorithms, [10], [17], [18], and [19], all of which comply with the AAMI standards.”
MethodSelf-citationAn approach to cardiac arrhythmia analysis using hidden Markov models
Coast, D. A., Stern, R. M., Cano, G. G., & Briller, S. A. (1990) · IEEE Transactions on Biomedical Engineering · doi:10.1109/10.58593 · Cited by 475 · cited 1×
“A wide range of methods have been proposed in the past for generic and fully automatic ECG classification based on signal processing techniques such as frequency analysis [1], wavelet transform [2], [3], and filter banks [4], statistical [5] and heuristic approaches [6], hidden Markov models [7], support vector machin…”
Method
Research works printed but not linked: 2
- 1987, Recommended practice for testing and reporting performance results of ventricular arrhythmia detection algorithms, Association for the Advancement of Medical Instrumentation
- talmon, 1983, Pattern Recognition of the ECG
Cited by
Items 301–319 of 319
Chen, J., Rahman, M. A., & Hossain, M. M. (2025) · IEEE International Ultrasonics Symposium · doi:10.1109/ius62464.2025.11201491
“D CNNs were first used in patient-specific ECG signals and have become very popular in various signal processing applications, such as the early detection of arrhythmia in electrical heartbeat (ECG) beats [13], [15]–[17].”
Jiang, T., Wang, H., Li, Q., & Xu, X. (2025) · Cognitive Neurodynamics · doi:10.1007/s11571-025-10364-5
“In 2015, Kiranyaz et al. (2015) proposed a 1D-CNN model for the rapid and accurate classification and monitoring of The TE from y to x H Y X is then defined as h 2 − h 1 , it is indicate the information transfer.”
Elreify, H. M., El‐Samie, F. E. A., Dessouky, M. I., Torkey, H., El‐Khamy, S. E., & Shalaby, W. A. (2025) · Scientific Reports · doi:10.1038/s41598-025-15883-z
“The CNNs were originally developed by LeCun et al. for image recognition tasks 54 , but have since demonstrated remarkable efficacy in sequence analysis across diverse biological domains 55 .”
Saxena, A., Alaria, S. K., Raj, A., Sharma, A., & Sharma, A. (2025) · IGI Global eBooks · doi:10.4018/979-8-3373-2706-8.ch003
Real-time Risk Prediction Using Temporal Gaze Pattern and Evidence Accumulation
Yang, G., Kaskar, O. G., & Sarkar, A. (2024) · VTechWorks (Virginia Tech)
Hashiura, R., Omori, A., & Nakano, N. (2025) · Proceedings of the ISCIE International Symposium on Stochastic Systems Theory and its Applications · doi:10.5687/sss.2025.50
Xu, K., Tian, Y., Bin, L., Lai, C., & Yang, W. (2026) · Water Resources Management · doi:10.1007/s11269-026-04546-x
“Proposed by Kiranyaz et al. (2015), 1D CNN is suitable for processing sequential data and have fewer parameters with higher computational efficiency.”
Parmar, H., Kaushik, A., Agarwal, L., Chaturvedi, K., & Murari, U. K. (2026) · International Conference on Sentiment Analysis and Deep Learning (ICSADL) · doi:10.1109/icsadl67539.2026.11451988
“synthetic data generation, cross domain testing and robust evaluation metrics[10-15].”
Modélisation des séries temporelles par apprentissage profond
Haykal, V. (2019) · theses.fr (ABES) · doi:10.70675/5f7a222bzd740z48a2z9951z429c68aa91a3
Semantic-Guided Modal Alignment for Multimodal Cardiovascular Disease Detection
Zhang, G., Dongyang, L. I. U., Lu, Y., Sun, H., Lin, B., & Shi, Z. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11462156
Amezawa, Y., Shiina, T., Ogata, J., Fukayama, S., Kuroda, H., & Uchide, T. (2026) · Geophysical Journal International · doi:10.1093/gji/ggag156
An Integrated Prediction Framework for Engineered Cementitious Composite: EDFrame
Chen, P., Wang, Y., (35492), X. Z., Liu, X., Liu, H., Zhao, Q., Wang, X., Ni, W., Jia, S., & Wang, H. (2026) · Materials · doi:10.3390/ma19122465
“The traditional convolutional neural network (CNN) has been proposed to solve various problems, such as computer vision, signal processing, and structural health monitoring [65–67].”
Improving groundwater level prediction based on optimized deep learning model with Coati algorithm
Ikram, R. M. A., Han, J., Wang, M., Samantaray, S., Sahoo, A., Abdulameer, S. F., Al-Suwaiyan, M. S., & Yaseen, Z. M. (2026) · Environmental Modelling & Software · doi:10.1016/j.envsoft.2026.107071
Martinez-Ríos, E. A., Cespi, R., Gennaro, S. D., & Bustamante-Bello, R. (2026) · IEEE Access · doi:10.1109/access.2026.3706573
“Nonetheless, 1D CNNs have received less attention, despite their potential to reduce the computational burden associated with 2D CNNs [32], [42].”
Nayak, P. C., Tyagi, A., Nath, K., & Patra, J. P. (2026) · Journal of Hydrologic Engineering · doi:10.1061/jhyeff.heeng-6690
Wang, Z., Aziz, I. A., Watts, A. C., & Alipour, M. (2026) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2026.3737377
Higher-dimensional embedding of time-series data for machine learning
Singh, K., Nath, P. P., Sinha, U., & Sinha, A. (2026) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2026.1874928
An Ensemble Attention-Based CNN-LSTM Model with GAN Augmentation for ECG Classification
Bhatnagar, P., Gupta, V., Sodhi, M. S., & Koravanghat, G. (2026) · International Conference on Intelligent Systems, Metaheuristics & Swarm Intelligence (ISMSI) · doi:10.1145/3820820.3820840
“The authors in [14] proposed a deep learning approach with the help of ANNs {Artificial Neural Networks) to solve the complexities and feature selection attributes for ECG Classification.”
Frequency-embedded sequence learning for multi-class EEG-to-text interface
Saha, S., Wagner, J., & McEwan, A. L. (2026) · Frontiers in Human Neuroscience · doi:10.3389/fnhum.2026.1980894
Metadata
- Authors
- Kiranyaz, S., Ince, T., Hamila, R., & Gabbouj, M.
- Affiliations
- Qatar University (QA)
- Tampere University of Technology (FI)
- Venue
- 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)
- Publisher
- IEEE
- Published
- 2015-08
- Volume
- 2015
- Pages
- 2608-2611
- ISSN
- 2375-7477 (ISSN-L)
- OpenAlex
- W2223222085
- Cited by
- 309
- References
- 18
- Citations by year
- 2026: 12 · 2025: 33 · 2024: 52 · 2023: 51 · 2022: 47 · 2021: 39 · 2020: 37 · 2019: 23 · 2018: 9 · 2017: 5 · 2016: 1
- FWCI
- 12.56
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) (publishedVersion)
- PubMed (publishedVersion)
- Qatar University QSpace (Qatar University) (submittedVersion)
- Topics
- Health Sciences › Medicine › Cardiology and Cardiovascular Medicine › ECG Monitoring and Analysis
- Physical Sciences › Engineering › Biomedical Engineering › Non-Invasive Vital Sign Monitoring
- Health Sciences › Medicine › Cardiology and Cardiovascular Medicine › Cardiac electrophysiology and arrhythmias
- Keywords
- 1D convolutional neural network, Holter monitoring, premature ventricular contractions, supraventricular ectopic beats, real-time ECG monitoring, wearable devices, early alert systems
- MeSH terms
- Algorithms, Electrocardiography, Humans, Monitoring, Physiologic, Neural Networks, Computer, Ventricular Premature Complexes, Atrial Premature Complexes
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.