Enhanced arrhythmia detection using a convolutional model and fuzzy dynamic time warping on filtered ECG data
Mallikarjunamallu K1 and Khasim Syed2
Department of Computer Science and Engineering,Koneru Lakshmaiah Education Foundation, Vaddeswaram, Guntur, 522302,Andhra Pradesh,India1
School of Computer Science and Engineering,VIT-AP University, Inavolu, Beside AP Secretariat, Amaravati- 522237,Andhra Pradesh,India2
School of Computer Science and Engineering,VIT-AP University, Inavolu, Beside AP Secretariat, Amaravati- 522237,Andhra Pradesh,India2
Corresponding Author : Khasim Syed
Recieved : 24-April-2024; Revised : 03-October-2025; Accepted : 27-November-2025
Abstract
Cardiac arrhythmia is characterized by irregular heartbeats caused by disruptions in the heart’s electrical activity. Electrocardiograms (ECGs) are commonly used by physicians to detect arrhythmias noninvasively; however, interpreting ECG signals can be time-consuming and challenging due to inherent noise, which complicates the detection process. To address this issue, an automated system capable of accurately detecting arrhythmias in real time was developed to assist medical professionals by reducing manual interpretation time and accelerating diagnosis. In this study, arrhythmias were automatically classified into five categories: normal (N), supraventricular (S), ventricular (V), fusion (F), and unknown (Q). The Massachusetts Institute of Technology–Beth Israel Hospital (MIT-BIH) Arrhythmia dataset was utilized, and class imbalance was addressed using the synthetic minority oversampling technique (SMOTE). To reduce noise in the ECG data, an infinite impulse response (IIR) filter was applied. The filtered signals were then processed using a deep learning (DL) model integrating one-dimensional convolutional neural networks (1D-CNNs) with bidirectional long short-term memory (Bi-LSTM) layers, enabling the extraction of both short-term and long-term temporal features. A soft attention mechanism was incorporated to enhance feature selection, while fuzzy dynamic time warping (FDTW) was employed to account for temporal variations in the ECG signals. The proposed model demonstrated strong performance across multiple evaluation metrics, including accuracy, sensitivity, and specificity. It achieved an average accuracy of 99.89%, indicating high robustness and precision in arrhythmia classification. This approach presents a reliable and efficient method for arrhythmia detection, surpasses existing techniques, and contributes to improved clinical decision-making by enhancing the efficiency and accuracy of ECG-based diagnosis. Additionally, advanced noise-reduction techniques improved signal quality and reduced the likelihood of diagnostic errors
Keywords
Cardiac arrhythmia detection, ECG signal processing, Deep learning, 1D-CNN and Bi-LSTM, Attention mechanism, Fuzzy dynamic time warping (FDTW).
Cite this article
K M, Syed K. Enhanced arrhythmia detection using a convolutional model and fuzzy dynamic time warping on filtered ECG data. International Journal of Advanced Technology and Engineering Exploration. 2025;12(132):1749-1767. DOI : 10.19101/IJATEE.2024.111100625
References
[1]
Ruan Y, Bao Q, Wang L, Wang Z, Zhu W, Wang JA. Cardiovascular diseases burden attributable to ambient PM2.5 pollution from 1990 to 2019: a systematic analysis for the global burden of disease study 2019. Environmental Research. 2024; 241:117678.
[2]
Li S, Wang H, Ma W, Qiu L, Xia K, Zhang Y, et al. Monitoring blood pressure and cardiac function without positioning via a deep learning–assisted strain sensor array. Science Advances. 2023; 9(32):1-10.
[3]
Sun J, Qiao Y, Zhao M, Magnussen CG, Xi B. Global, regional, and national burden of cardiovascular diseases in youths and young adults aged 15–39 years in 204 countries/territories, 1990–2019: a systematic analysis of global burden of disease study 2019. BMC Medicine. 2023; 21(1):1-15.
[4]
Pham TH, Sree V, Mapes J, Dua S, Lih OS, Koh JE, et al. A novel machine learning framework for automated detection of arrhythmias in ECG segments. Journal of Ambient Intelligence and Humanized Computing. 2021; 12(11):10145-62.
[5]
Chi J, Shu J, Li M, Mudappathi R, Jin Y, Lewis F, et al. Artificial intelligence in metabolomics: a current review. TrAC Trends in Analytical Chemistry. 2024; 178:117852.
[6]
Sakr AS, Pławiak P, Tadeusiewicz R, Pławiak J, Sakr M, Hammad M. ECG-COVID: an end-to-end deep model based on electrocardiogram for COVID-19 detection. Information Sciences. 2023; 619:324-39.
[7]
Schwartz IS, Link KE, Daneshjou R, Cortés-penfield N. Black box warning: large language models and the future of infectious diseases consultation. Clinical Infectious Diseases. 2024; 78(4):860-6.
[8]
Yan SP, Song X, Wei L, Gong YS, Hu HY, Li YQ. Performance of heart rate adjusted heart rate variability for risk stratification of sudden cardiac death. BMC Cardiovascular Disorders. 2023; 23(1):1-14.
[9]
Xiao Q, Lee K, Mokhtar SA, Ismail I, Pauzi AL, Zhang Q, et al. Deep learning-based ECG arrhythmia classification: a systematic review. Applied Sciences. 2023; 13(8):1-25.
[10]
Leming MJ, Bron EE, Bruffaerts R, Ou Y, Iglesias JE, Gollub RL, et al. Challenges of implementing computer-aided diagnostic models for neuroimages in a clinical setting. NPJ Digital Medicine. 2023; 6(1):1-12.
[11]
Huang Y, Li H, Yu X. A novel time representation input based on deep learning for ECG classification. Biomedical Signal Processing and Control. 2023; 83:104628.
[12]
Tasin I, Nabil TU, Islam S, Khan R. Diabetes prediction using machine learning and explainable AI techniques. Healthcare Technology Letters. 2023; 10(1-2):1-10.
[13]
Elreedy D, Atiya AF, Kamalov F. A theoretical distribution analysis of synthetic minority oversampling technique (SMOTE) for imbalanced learning. Machine Learning. 2024; 113(7):4903-23.
[14]
Dhyani S, Kumar A, Choudhury S. Analysis of ECG-based arrhythmia detection system using machine learning. MethodsX. 2023; 10:1-15.
[15]
Bai M, Liu J, Long Z, Luo J, Yu D. A comparative study on class-imbalanced gas turbine fault diagnosis. Proceedings of the Institution of Mechanical Engineers, Part G: Journal of Aerospace Engineering. 2023; 237(3):672-700.
[16]
Mondal A, Manikandan MS, Pachori RB. Automatic ECG signal quality determination using CNN with optimal hyperparameters for quality-aware deep ECG analysis systems. IEEE Sensors Journal. 2024; 24(11):17825-33.
[17]
Suliman A, Farahmand M, Galeotti L, Scully CG. Clinical evaluation of the ECG noise extraction tool as a component of ECG analysis algorithms evaluation. IEEE Transactions on Biomedical Engineering. 2024; 72(7):2062-71.
[18]
Van DBK, Elgendi M, Menon C. Automatic ECG quality assessment techniques: a systematic review. Diagnostics. 2022; 12(11):1-12.
[19]
Huang X, Zhang F, Fan H, Chang H, Zhou B, Li Z. Pseudo anomalies enhanced deep support vector data description for electrocardiogram quality assessment. Computers in Biology and Medicine. 2024; 170:107928.
[20]
Zishan MA, Shihab HM, Islam SS, Riya MA, Rahman GM, Noor J. Dense neural network based arrhythmia classification on low-cost and low-compute micro-controller. Expert Systems with Applications. 2024; 239:122560.
[21]
Moreno-sánchez PA. Data-driven early diagnosis of chronic kidney disease: development and evaluation of an explainable AI model. IEEE Access. 2023; 11:38359-69.
[22]
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. Computational Intelligence and Neuroscience. 2022; 2022(1):1-8.
[23]
Al’aref SJ, Anchouche K, Singh G, Slomka PJ, Kolli KK, Kumar A, et al. Clinical applications of machine learning in cardiovascular disease and its relevance to cardiac imaging. European Heart Journal. 2019; 40(24):1975-86.
[24]
Madan P, Singh V, Singh DP, Diwakar M, Pant B, Kishor A. A hybrid deep learning approach for ECG-based arrhythmia classification. Bioengineering. 2022; 9(4):1-26.
[25]
Hammad M, Iliyasu AM, Subasi A, Ho ES, Abd EAA. A multitier deep learning model for arrhythmia detection. IEEE Transactions on Instrumentation and Measurement. 2020; 70:1-9.
[26]
Niu L, Chen C, Liu H, Zhou S, Shu M. A deep-learning approach to ECG classification based on adversarial domain adaptation. Healthcare. 2020; 8(7):1-16.
[27]
Sangaiah AK, Arumugam M, Bian GB. An intelligent learning approach for improving ECG signal classification and arrhythmia analysis. Artificial Intelligence in Medicine. 2020; 103:101788.
[28]
Wang H, Shi H, Chen X, Zhao L, Huang Y, Liu C. An improved convolutional neural network based approach for automated heartbeat classification. Journal of Medical Systems. 2020; 44(2):35.
[29]
Wang T, Lu C, Sun Y, Yang M, Liu C, Ou C. Automatic ECG classification using continuous wavelet transform and convolutional neural network. Entropy. 2021; 23(1):1-13.
[30]
Yildirim O, Talo M, Ciaccio EJ, San TR, Acharya UR. Accurate deep neural network model to detect cardiac arrhythmia on more than 10,000 individual subject ECG records. Computer Methods and Programs in Biomedicine. 2020; 197:1-12.
[31]
Zhang Y, Yu J, Zhang Y, Liu C, Li J. A convolutional neural network for identifying premature ventricular contraction beat and right bundle branch block beat. In international conference on sensor networks and signal processing (SNSP) 2018 (pp. 158-62). IEEE.
[32]
Li Z, Zhou D, Wan L, Li J, Mou W. Heartbeat classification using deep residual convolutional neural network from 2-lead electrocardiogram. Journal of Electrocardiology. 2020; 58:105-12.
[33]
Jangra M, Dhull SK, Singh KK. ECG arrhythmia classification using modified visual geometry group network (mVGGNet). Journal of Intelligent & Fuzzy Systems. 2020; 38(3):3151-65.
[34]
Meng Y, Liang G, Yue M. Deep learning‐based arrhythmia detection in electrocardiograph. Scientific Programming. 2021; 2021(1):1-7.
[35]
Meqdad MN, Abdali-mohammadi F, Kadry S. A new 12-lead ECG signals fusion method using evolutionary CNN trees for arrhythmia detection. Mathematics. 2022; 10(11):1-14.
[36]
Nanthini K, Sivabalaselvamani D, Chitra K, Mohideen PA, Raja RD. Cardiac arrhythmia detection and prediction using deep learning technique. In proceedings of fourth international conference on communication, computing and electronics systems 2022 (pp. 983-1003). Singapore: Springer Nature Singapore.
[37]
Kumar A, Kumar SA, Dutt V, Shitharth S, Tripathi E. IoT based arrhythmia classification using the enhanced hunt optimization‐based deep learning. Expert Systems. 2023; 40(7):e13298.
[38]
Shilpa K, Adilakshmi T. Hybrid machine learning and deep learning models for efficient detection of arrhythmia from ECG data. International Journal of Communication Networks and Information Security. 2024; 16(3):684-701.
[39]
Zhang J, Liang D, Liu A, Gao M, Chen X, Zhang X, et al. MLBF-Net: a multi-lead-branch fusion network for multi-class arrhythmia classification using 12-lead ECG. IEEE Journal of Translational Engineering in Health and Medicine. 202; 9:1-11.
[40]
Tao R, Wang L, Xiong Y, Zeng YR. IM-ECG: an interpretable framework for arrhythmia detection using multi-lead ECG. Expert Systems with Applications. 2024; 237:121497.
[41]
Moody GB, Mark RG. The impact of the MIT-BIH arrhythmia database. IEEE Engineering in Medicine and Biology Magazine. 2001; 20(3):45-50.
[42]
Li J, Zhu Q, Wu Q, Fan Z. A novel oversampling technique for class-imbalanced learning based on SMOTE and natural neighbors. Information Sciences. 2021; 565:438-55.
[43]
Mallikarjunamallu K, Syed K. Arrhythmia classification for non-experts using infinite impulse response (IIR)-filter-based machine learning and deep learning models of the electrocardiogram. PeerJ Computer Science. 2024; 10:1-37.
[44]
Jain S, Paul S. Design of filters using current amplifiers for removal of noises from ECG signal. Procedia Computer Science. 2023; 218:1888-904.
[45]
Zhang J, Ma F, Chen W. An Improved CNNLSTM algorithm for automatic detection of arrhythmia based on electrocardiogram signal. In international conference on database systems for advanced applications 2021 (pp. 185-96). Cham: Springer International Publishing.
[46]
Neha, Sardana HK, Dogra N, Kanawade R. Dynamic time warping based arrhythmia detection using photoplethysmography signals. Signal, Image and Video Processing. 2022; 16(7):1925-33.
[47]
González-sopeña JM, Pakrashi V, Ghosh B. An overview of performance evaluation metrics for short-term statistical wind power forecasting. Renewable and Sustainable Energy Reviews. 2021; 138:110515.
[48]
Hammad M, Iliyasu AM, Subasi A, Ho ES, Abd EAA. A multitier deep learning model for arrhythmia detection. IEEE Transactions on Instrumentation and Measurement. 2020; 70:1-9.
[49]
Wei X, Li Z, Jin Y, Tian Y, Wang M, Zhao L, et al. Automatic multi-label diagnosis of single-lead ECG using novel hybrid residual recurrent convolutional neural networks. Biomedical Signal Processing and Control. 2024; 95:106422.
[50]
Ullah A, Rehman SU, Tu S, Mehmood RM, Fawad, Ehatisham-ul-haq M. A hybrid deep CNN model for abnormal arrhythmia detection based on cardiac ECG signal. Sensors. 2021; 21(3):1-13.
[51]
Kuila S, Dhanda N, Joardar S. ECG signal classification and arrhythmia detection using ELM-RNN. Multimedia Tools and Applications. 2022; 81(18):25233-49.
[52]
Daydulo YD, Thamineni BL, Dawud AA. Cardiac arrhythmia detection using deep learning approach and time frequency representation of ECG signals. BMC Medical Informatics and Decision Making. 2023; 23(1):1-14.
[53]
Cañón-clavijo RE, Montenegro-marin CE, Gaona-garcia PA, Ortiz-guzmán J. IoT based system for heart monitoring and arrhythmia detection using machine learning. Journal of Healthcare Engineering. 2023; 2023(1):1-13.
[54]
Demiroğlu U, Şenol B, Matušů R. A fused electrocardiography arrhythmia detection method. Multimedia Tools and Applications. 2024; 83(16):49057-89.
[55]
Fatimah B, Singhal A, Singh P. ECG arrhythmia detection in an inter-patient setting using fourier decomposition and machine learning. Medical Engineering & Physics. 2024; 124:104102.