A Novel Framework for ECG Signal Processing and Robust Arrhythmia Detection

Gautam Sharma; Safia Tahir; Mehwish Faiz; Huzaifa Ahmed; Abdul Moiz Afridi; Aneela Kiran; Shahzad Nasim

No Detail Found!

A Novel Framework for ECG Signal Processing and Robust Arrhythmia Detection

Author(s)

Gautam Sharma Department of Biomedical Engineering, Ziauddin University (FESTM), Karachi, Pakistan

Safia Tahir Department of Biomedical Engineering, Ziauddin University (FESTM), Karachi, Pakistan

Mehwish Faiz Department of Biomedical Engineering, Ziauddin University (FESTM), Karachi, Pakistan

Huzaifa Ahmed Department of Biomedical Engineering, Ziauddin University (FESTM), Karachi, Pakistan

Abdul Moiz Afridi Department of Biomedical Engineering, Ziauddin University (FESTM), Karachi, Pakistan

Aneela Kiran The Begum Nusrat Bhutto Women University, Sukkur Country: Pakistan

Shahzad Nasim The Begum Nusrat Bhutto Women University, Sukkur Country: Pakistan

Abstract

Cardiovascular diseases are still one of the most important public health issues that the world is facing today. Early identification of heart problems can help with early diagnosis. Analyzing the electrical signals created by the heart can provide important insight into how well a person's heart is functioning. The electrical signals generated by the heart can be disrupted by noise and interference, which effects the interpretation of these signals. This paper reveals a novel approach to process bio signals to uncover the presence of abnormal heart rhythms based on abnormally fast, slow, or irregular heartbeat patterns. The results of the experimental evaluations demonstrate that out of total 10 participants, 6 individuals have a normal heart pattern while the heart rate analysis of remaining 4 individuals indicates that they are having arrhythmia. Thus, the method used in this study successfully distinguishes between normal and abnormal cardiac conditions. This publication provides an overview of the potential use of signal processing to assist with early diagnosis of heart problems and improve ongoing monitoring of patients' health in both clinical and remote settings.

Publication Details

Page(s) 59-65

DOI DOI not available

Published Journal: Journal of Information & Communication Technology (JICT), Volume: 19, Issue: 2, Year: 2025

Request the full text from PASTIC

Keywords

reducing noise, Cardiovascular disease (CVD), abnormal heart rhythms, filtration, analyzing features, ECG

References

Mastoi Q. U.,Comput J. .2023 .“Novel framework for efficient detection of QRS morphology for the cardiac arrhythmia classification,”. , : .

Imtiaz M. N.,Khan N. .2024 .+: A robust approach to detect R peaks in ECG signals. , : 2211.

Ádám Á. N. .2025 .Comparative evaluation of filtration techniques for ECG signal denoising with emphasis on stationary wavelet transform. ” Sci. Rep, : .

Leski J. M.,Process. Control Biomed. Signal .2021 .Robust nonlinear aggregation operator for ECG powerline interference reduction,”. , : .

Alexandre N. .2024 .“ECGScorer: An open-source MATLAB toolbox for ECG signal quality assessment,” SoftwareX. , 28 : 101900.

Faiz M. .2022 ."Design of a device for the assessment of dyspnea patients,". Mehran University Research Journal of Engineering & Technology, 41(4) : 128-137.

Faiz M. .2023 ."Design of Homeostatic Temperature Control System for Hypohidrosis Patients and Its Effect on EEG Waveform,". Journal of Information & Communication Technology, 17(1) : 20-25.

Zhai D. .2023 .Precise detection and localization of Rpeaks from ECG signals. , 20(11) : 19191-19208.

Mohonta S. C.,Motin M. A.,Kumar D. K. .2022 .Electrocardiogram-based arrhythmia classification using wavelet transform with deep learning model. ” Sens. Bio-Sens. Res., 37 : 100502.

Maliha M. S.,Hossain A. K.,A. K. Das A. K. .2024 .A novel feature extraction technique for ECG arrhythmia classification using machine learning. ” Appl. Netw. Sci., 9 : 316.

Rizvi M. A.,Process Front. Signal .2024 .Comparative study of time-frequency transformation methods for ECG signal classification using deep learning,”. , 4 : 1322334.

Abagaro S.,Mekonnen T.,Electr J. .2024 .Hybrid ECG arrhythmia classification using DWT-PCA-ANFIS framework,”. , 19 : 1653-1665.

Kumar R.,Chakrapani V. .2022 .FFT-based improved AlexNet classifier for ECG arrhythmia detection. PLoS ONE, 17(e0274225) : .

Chen H.,Wearable Cardiac Monitoring Using Adaptive CNN-LSTM Architectures H. .2024 .. , : .

Singh J.,Krishnan S. M. .2023 .A review on ECG feature extraction methods across time, frequency. ” Biomed. Eng. Online, 22(1) : .

Romdhane M.,Ouni S. .2023 .ECG anomaly detection and denoising using DWT and MATLAB filtering techniques. ” SN Comput. Sci., 5(3) : 1-10.

Kumar P.,Art P. .2024 .Fusion-based deep residual ECG classification framework. ” Sci. Rep, 14(1792) : .

Maina J. .2024 .Deep learning-based multi-lead ECG arrhythmia classification. ” Nat. Sci. Data, 11 : .

Alaa F.,Ahmed S. R.,Yusoff N. .2024 .A robust ECGbased arrhythmia detection model using ensemble deep learning. ” ARASET J., 40(1) : 118-128.

Rizvi M. A. .2024 .“Time-frequency methods in ECG classification using CNNs,” Eng. Proc., 34 : 24.

Sattar S.,Usman A.,Riaz M. A.,Art M. A. .2024 .Deep selfsupervised CNN-LSTM model for arrhythmia classification. ” Sensors, 24(2484) : 1-16.

Citations

Downloads

Views