Electrocardiogram signal processing: Integrating filter fusion techniques
 
More details
Hide details
1
Nikola Vaptsarov Naval Academy
 
These authors had equal contribution to this work
 
 
Submission date: 2025-05-07
 
 
Final revision date: 2025-08-29
 
 
Acceptance date: 2025-10-02
 
 
Online publication date: 2025-10-03
 
 
Publication date: 2025-10-03
 
 
Corresponding author
Iliyan Yordanov Iliev   

Nikola Vaptsarov Naval Academy
 
 
 
KEYWORDS
TOPICS
ABSTRACT
The accurate detection and analysis of the P-QRS-T complex in electrocardiogram (ECG) signals are crucial for diagnosing cardiac diseases. This paper presents a practical approach to ECG signal processing by integrating multiple filter fusion techniques to enhance detection accuracy. Recognizing the specific challenges at sea, including motion-induced noise and electromagnetic interference, the study examines the performance of low-pass, high-pass, and Chebyshev Type II filters in improving ECG signal quality. Using a dataset generated by a Dynamic Model for Synthetic ECG Signal Generation, the analysis evaluates the effectiveness of these filters under various noise conditions, such as baseline drift, electrode contact noise, and muscle noise. The proposed method combines filtered outputs from multiple channels: P and T waves are extracted using low-pass and high-pass filters, while the QRS complex is identified through the Chebyshev Type II filter. Results indicate improved detection accuracy, with performance varying based on the type of noise present. While not introducing a novel algorithm, the study demonstrates that the fusion of established filtering techniques offers a fast and reliable solution suitable for maritime health monitoring systems. However, these results are derived from simulated signals under controlled experimental settings and therefore reflect proof-of-concept performance rather than clinical validation.
FUNDING
This research paper has received funding from Ministry of Education and Science of the Republic of Bulgaria under the National Science Program "SECURITY AND DEFENSE", in implementation of the Decision of the Council of Ministers of the Republic of Bulgaria No: 731/21.10.2021 and according to Agreement No: D01-74/19.05.2022
REFERENCES (32)
1.
Abdulhady AA, Nergz SM, Maryam K, Safar MA, Zrar KA, Halgurd SM. Electrocardiogram heartbeat classification using convolutional neural network-k Nearest Neighbor. ARO-The Scientific Journal Of Koya University. 2024;15(1):61-67. https://doi.org/10.14500/aro.1....
 
2.
Hatamian A, Farshidi F, Ghobadi C, Nourinia J, Mostafapour E. Improving the quality of ECG signal using wavelet transform and adaptive filters. J. Appl. Res. Electr. Eng., 2023;2(1):45-53. https://doi.org/0.22055/jaree.....
 
3.
Atanasov V, Sivkov Y, Velikov N. An approach of feature extraction of ECG signal of CLAS database. Proc Int Conf Biomed Innovations Appl (BIA). 2020:93–96. https://doi.org/10.1109/BIA501....
 
4.
Belkadi MA, Daamouche A, Melgani F. A deep neural network approach to QRS detection using autoencoders. Expert Systems with Applications. 2021;184(115528). https://doi.org/10.1016/j.eswa....
 
5.
Brik Y, Djerioui M, Attallah B. Efficient heart disease diagnosis based on twin support vector machine. Diagnostyka. 2021;22(3):3-11. https://doi.org/10.29354/diag/....
 
6.
Ding C, Wang S, Jin X, Wang Z, Wang J. A novel transformer-based ECG dimensionality reduction stacked auto-encoders for arrhythmia beat detection. Medical Physics. 2023;52(6):5297-5932. https://doi.org/10.1002/mp.165....
 
7.
Ding Z, Vishu KC, Mohammad MK. ECG Signal Denoising Using Multi-scale Patch Embedding and Transformers. ICML 2024 Next Generation of Sequence Modeling Architectures Workshop. https://doi.org/10.48550/arXiv....
 
8.
Duranta D, Rizwan A, Kiranyaz S, Gabbouj M. Enhancing atrial fibrillation detection accuracy: A wavelet transform filtered single lead ECG signal analysis with artificial neural networks and novel feature extraction. Mach Learn Appl. 2023;12:100472. https://doi.org/10.1016/j.mlwa....
 
9.
Hulsenboom ADJ, Verdurmen KMJ, Vullings R, van der Hout-van der Jagt MB, Kwee A. Relative versus absolute rises in T/QRS ratio by ST analysis of fetal electrocardiograms in labour: A case-control pilot study. PloS ONE. 2019;14(3):e0214357. https://doi.org/10.1371/journa....
 
10.
Jan MA, Zhang W, Khan F, Abbas S, Khan R. Lightweight and smart data fusion approaches for wearable devices of the Internet of Medical Things. Information Fusion. 2023;103:102076. https://doi.org/10.1016/j.inff....
 
11.
Jenkal W, Latif R, Laaboubi M. ECG Signal denoising using an improved hybrid DWT-ADTF approach. Cardiovascular Engineering and Technology. 2024;15 (1):77-94. https://doi.org/10.1007/s13239....
 
12.
Iliev IY, Atanasov V. Electrocardiogram (ECG) signal processing. Mendeley Data. 2025;V1(2025). https://doi.org/10.17632/kxcfc....
 
13.
Kim D, Lee KR, Lim DS, Lee KH, Lee SJ, Kim DY, Sohn CB. A novel hybrid CNN-transformer model for arrhythmia detection without R-peak identification using stockwell transform. Scientific Reports. 2025;15(1), 7817. https://doi.org/10.1038/s41598....
 
14.
Larsson TJ, Lindquist C. Traumatic fatalities among Swedish seafarers 1984-1988. Saf Sci. 1992;15(3):173–82. https://doi.org/10.1016/0925-7....
 
15.
Lin M, Hong Y, Hong S, Zhang S. Discrete wavelet transform based ECG classification using gcForest: A deep ensemble method. Technology and Health Care. 2024;21:S95-S105. https://doi.org/10.3233/THC-24....
 
16.
Malik, SA, et al. An Iterative Filtering Based ECG Denoising Using Lifting Wavelet Transform Technique. ELECTRONICS. 2023; 12(2), 387. https://doi.org/10.3390/electr....
 
17.
McSharry P, Clifford GD, Tarassenko L, Smith L. A dynamical model for generating synthetic electrocardiogram signals. IEEE Trans Biomed Eng. 2003;50(3):289–94. https://doi.org/10.1109/TBME.2....
 
18.
Morteza M, Foad H. Identification of cardiovascular diseases through ECG classification using wavelet transformation. MBDI. 2024 (preprint/under review). https://doi.org/10.48550/arXiv....
 
19.
Praveena HD, Sudha K, Geetha P, Venkatanaresh M. Comprehensive time-frequency analysis of noisy ECG signals – A review. Cardiometry. 2022. https://doi.org/10.18137/cardi....
 
20.
Rizwan A, Priyanga P, Abualsauod EH, Zafrullah SN, Serbaya SH, Halifa A. A machine learning approach for the detection of QRS complexes in electrocardiogram (ECG) using discrete wavelet transform (DWT) algorithm. Comput Intell Neurosci. 2022;2022:9023478. https://doi.org/10.1155/2022/9....
 
21.
Roberts SE, Jaremin B. Cardiovascular disease mortality in British merchant shipping and among British seafarers ashore in Britain. Int Marit Health. 2010;61(3):107–116.
 
22.
Safdar M, Nowak R, Palka P. Pre-Processing techniques and artificial intelligence algorithms for electrocardiogram (ECG) signals analysis: A comprehensive review. Computers in Biology and Medicine. 2024;170:107908. https://doi.org/10.1016/j.comp....
 
23.
Soumiaa M, El HS, Mansouri M. The use of the multi-scale discrete wavelet transform and deep neural networks on ECGs for the diagnosis of 8 cardio-bascular diseases. Mendel Self Computing Journal. 2022;28(2): 62-66. https://doi.org/10.13164/mende....
 
24.
Sun LC, Lee CC, Ke HY, Wei CY, Lin KF, Lin SS, Hsin H, Chen PN. Deep learning for the classification of atrial fibrillation using wavelet transform-based visual images. BMC Med Inform Decis Mak. 2025;22(349). https://doi.org/10.1186/s12911....
 
25.
Wang J, He F, Sun S. Construction of a new smooth support vector machine model and its application in heart disease diagnosis. Plos One. 2023;18(2) e0280804. https://doi.org/10.1371/journa....
 
26.
World Health Organization. Cardiovascular diseases (CVDs). World Health Organization; 2021. Available from (accessed at 05.05.2025): https://www.who.int/news-room/...).
 
27.
Xiaohong Y, Yuanqi H, Qiang L. Automatic multichannel electrocardiogram record classification using XGBoost fusion model. front. Physiol. 2022;13: (840011). https://doi.org/10.3389/fphys.....
 
28.
Zhang Q, Chen Z, Liu G, Zhang W, Du Q, Tan J, Gao Q. Artificial intelligence clinicians can use chest computed tomography technology to automatically diagnose coronavirus disease 2019 (COVID-19) Pneumonia and Enhance Low-Quality Images. Infect Drug Resist, 2021-24(14):671-687. https://doi.org/10.2147/IDR.S2....
 
29.
Zhao W, Li Z, Hu J, Ma Y. A simple and effective deep neural network based QRS complex detection method on ECG signal. Frontiers in Physiology. 2024;15:1384356. https://doi.org/10.3389/fphys.....
 
30.
Zhang J, Liang D, Liu A, Gao M, Chen X, Zhang X, Chen X. MLBF-Net: A multi-lead-branch fusion network for multi-class arrhythmia classification using 12-Lead ECG.MBDI. 2020. https://doi.org/10.48550/arXiv...;.
 
31.
Zivaljevic D, Stamenkovic N, Stojanovic N. Optimum Chebyshev filter whit an equalised group delay response. International Journal of Electronics. 2023;110(10): 1834-1848. https://doi.org/10.1080/002072...;.
 
32.
Zholmagambetova B, Mazakov T, Jomartova S, Izat A, Bibalayev O. Methods of extracting electrocardiograms from electronic signals and images in the Python environment. Diagnostyka. 2020;21(3):95-101. https://doi.org/10.29354/diag/....
 
eISSN:2449-5220
Journals System - logo
Scroll to top