A Shallow Domain Knowledge Injection (SDK-Injection) Method for Improving CNN-Based ECG Pattern Classification
Source abstract
Abstract
ECG pattern classification for identifying the progress status of various heart diseases is a typical nonlinear problem. Therefore, deep learning-based automatic ECG diagnosis is being widely studied, and for this purpose, the CNN is mainly used to classify ECG patterns. In this case, it is hard to expect any further improvement in accuracy after optimizing the parameters. We propose a shallow domain knowledge injection method that can improve the accuracy of the existing parameter-optimized CNN. The proposed method can improve the accuracy by effectively injecting shallow domain knowledge, that can be acquired by non-medical experts, into the existing parameter-optimized CNN. The experiments show that the proposed method can be applied to both heart disease diagnoses and general ECG classification tasks, while improving the existing accuracy for both types of tasks.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: ECG Monitoring and Analysis · EEG and Brain-Computer Interfaces · Advanced Computing and Algorithms
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Computer Science and Engineering, Ewha Womans University, Seoul 03760, Korea
Funding
National Research Foundation of Korea(NRF)
References (29)
Show source-provided references
1. A Survey of Data Mining Algorithms Used in Cardiovascular Disease Diagnosis from Multi-Lead ECG Data
2. Automatic Detection of Characteristic Segments of a Recorded ECG Signal with Noise Handling Methods10.1088/1757-899X/1032/1/012047 ↗
3. Automated ECG Segmentation Using Piecewise Derivative Dynamic Time Warping
4. Comparative Study of Algorithms for ECG Segmentation10.1016/j.bspc.2017.01.013 ↗
5. ECG-Based Heartbeat Classification for Arrhythmia Detection: A Survey10.1016/j.cmpb.2015.12.008 ↗
6. Barman, T., Ghongade, R., and Ratnaparkhi, A. (2016, January 9–11). Rough Set Based Segmentation and Classification Model for ECG. Proceedings of the 2016 Conference on Advances in Signal Processing (CASP), Pune, India.10.1109/CASP.2016.7746130 ↗
7. Rai, H.M., and Chatterjee, K. (2021). Hybrid CNN-LSTM Deep Learning Model and Ensemble Technique for Automatic Detection of Myocardial Infarction Using Big ECG Data. Appl. Intell., 1–19.10.1007/s10489-021-02696-6 ↗
8. An Ensemble of Deep Learning-Based Multi-Model for ECG Heartbeats Arrhythmia Classification10.1109/ACCESS.2021.3098986 ↗
9. Automated Atrial Fibrillation Detection Using a Hybrid CNN-LSTM Network on Imbalanced ECG Datasets10.1016/j.bspc.2020.102194 ↗
10. Zhang, Y., and Li, J. (2019). Application of Heartbeat-Attention Mechanism for Detection of Myocardial Infarction Using 12-Lead ECG Records. Appl. Sci., 9.10.3390/app9163328 ↗
11. Han, C., Huang, R., Yu, F., Huang, X., and Cui, L. (2021, January 10–15). EasiECG: A Novel Inter-Patient Arrhythmia Classification Method Using ECG Waves. Proceedings of the 2020 25th International Conference on Pattern Recognition (ICPR), Milan, Italy.10.1109/ICPR48806.2021.9413243 ↗
12. HADLN: Hybrid Attention-Based Deep Learning Network for Automated Arrhythmia Classification10.3389/fphys.2021.683025 ↗
13. Wang, T., Lu, C., Sun, Y., Yang, M., Liu, C., and Ou, C. (2021). Automatic ECG Classification Using Continuous Wavelet Transform and Convolutional Neural Network. Entropy, 23.10.3390/e23010119 ↗
14. Couceiro, R., Carvalho, P., Henriques, J., Antunes, M., Harris, M., and Habetha, J. (2008, January 8–11). Detection of Atrial Fibrillation Using Model-Based ECG Analysis. Proceedings of the 2008 19th International Conference on Pattern Recognition, Tampa, FL, USA.10.1109/ICPR.2008.4761755 ↗
15. Atrial Fibrillation Detection Based on Multi-Feature Extraction and Convolutional Neural Network for Processing ECG Signals10.1016/j.cmpb.2021.106009 ↗
16. A Survey on Deep Learning: Algorithms, Techniques, and Applications
17. Holzinger, A. (2018, January 23–25). From Machine Learning to Explainable AI. Proceedings of the 2018 World Symposium on Digital Intelligence for Systems and Machines (DISA), Košice, Slovakia.10.1109/DISA.2018.8490530 ↗
18. ECG Signal Denoising and Features Extraction Using Unbiased FIR Smoothing
19. On the Selection of Optimum Savitzky-Golay Filters10.1109/TSP.2012.2225055 ↗
20. Performance Analysis of Savitzky-Golay Smoothing Filter Using ECG Signal
21. Big-ECG: Cardiographic Predictive Cyber-Physical System for Stroke Management10.1109/ACCESS.2021.3109806 ↗
22. Sliding Large Kernel of Deep Learning Algorithm for Mobile Electrocardiogram Diagnosis10.1016/j.compeleceng.2021.107521 ↗
23. Sereda, I., Alekseev, S., Koneva, A., Kataev, R., and Osipov, G. (2019, January 14–19). ECG Segmentation by Neural Networks: Errors and Correction. Proceedings of the 2019 International Joint Conference on Neural Networks (IJCNN), Budapest, Hungary.10.1109/IJCNN.2019.8852106 ↗
24. Sodmann, P., and Vollmer, M. (2020, January 13–16). ECG Segmentation Using a Neural Network as the Basis for Detection of Cardiac Pathologies. Proceedings of the 2020 Computing in Cardiology, Rimini, Italy.10.22489/CinC.2020.356 ↗
25. Multiscale Residual Network Based on Channel Spatial Attention Mechanism for Multilabel ECG Classification
26. Gao, F., and Li, Z. (2021, January 26–28). Recognition of ECG Signals by Convolutional Neural Network Based on Attentional Mechanism. Proceedings of the 2021 4th International Conference on Advanced Electronic Materials, Computers and Software Engineering (AEMCSE), Changsha, China.10.1109/AEMCSE51986.2021.00033 ↗
27. Ullah, A., Tu, S., Mehmood, R.M., and Ehatisham-ul-haq, M. (2021). A Hybrid Deep CNN Model for Abnormal Arrhythmia Detection Based on Cardiac ECG Signal. Sensors, 21.10.3390/s21030951 ↗
28. (2021, September 06). Time Series Classification Website. Available online: http://www.timeseriesclassification.com/dataset.php.
29. (2021, September 06). PhysioNet Databases. Available online: https://www.physionet.org/about/database/.