High-Performance ECG Beat Analysis Using Wavelet-Based Features And Memetic Redundancy-Optimized ROCNN
DOI:
https://doi.org/10.29284/ztd3zd24Keywords:
ECG Classification; Arrhythmia; Approximate Entropy; Sample Entropy; Lifting Wavelets; Support Vector Machine; Feature Selection.Abstract
Cardiovascular diseases are increasingly prevalent across all age groups, affecting both young and elderly populations. Early and accurate detection of cardiac abnormalities is therefore essential for timely medical intervention. This research proposes an advanced automated classification system to determine whether an Electrocardiogram (ECG) signal corresponds to a normal condition or an arrhythmia case. The key contribution of this work lies in the integration of efficient preprocessing techniques with an optimized feature selection strategy. Frequency-domain features extracted from ECG signals using wavelet lifting schemes were refined through the Memetic Redundancy (MR) approach, which effectively removes irrelevant and redundant features while preserving discriminative information. The proposed framework was evaluated using 65,448 ECG records from the MIT-BIH Arrhythmia Database and achieved a high classification accuracy of 99.75%, demonstrating its robustness and reliability for arrhythmia detection.
References
[1]. Chazal PD, Reilly RB. A patient-adapting heart beat classifier using ECG morphology and heartbeat interval features. IEEE Trans.Biomed. Eng. 2006; 53(12): 2535-2543.
[2]. Mitra S, Mitra M, Chaudhuri BB. A Rough set based inference engine for ECG classification. IEEE Trans. Instrum. Meas. 2006; 55(6): 2198-2206.
[3]. Raj S, Maurya K, Ray KC. A knowledge-based real time embedded platform for arrhythmia beat classification. Biomed. Eng.Lett. 2015; 5(4): 271-280.
[4]. Minami K, Nakajima H, Toyoshima T. Real-time discrimination of ventricular tachy arrhythmia with Fourier transform neural network. IEEE Trans. Biomed. Eng. 1999; 46(2): 179-185.
[5]. Ince T, Kiranyaz S, Gabbouj M. A generic and robust system for automated patient-specific classification of ECG signals. IEEE Trans.Biomed. Eng. 2009; 56(5): 1415-1426.
[6]. Banerjee S, Mitra M. Application of cross wavelet transform for ECG pattern analysis and classification. IEEE Trans. Instrum. Meas. 2014; 63(2): 326-333.
[7]. Raj S, Chand GSSP, Ray KC. ARM based arrhythmia beat monitoring system, Microprocess. Microsyst. 2015; 39(7): 504-511.
[8]. Melgani F, Bazi Y. Classification of electrocardiogram signals with support vector machines and particle swarm optimization. IEEE Trans. Inf. Technol. Biomed. 2008; 12(5): 667-677.
[9]. Osowski S, Hoai LT, Markiewicz T. Support vector machine based expert system for reliable heart beat recognition. IEEE Trans.Biomed. Eng. 2004; 51(4): 582–589.
[10]. Raj S, Luthra S, Ray KC. Development of hand held cardiac event monitoring system. IFAC-PapersOnLine. 2015; 48(4): 71-76.
[11]. Linh TH, Osowski S, Stodolski M. On-line heart beat recognition using Hermite polynomials and neuro-fuzzy network. IEEE Trans. Instrum. Meas. 2003; 52(4): 1224-1231.
[12]. Llamedo M, Martinez JP. Heart beat classification using feature selection driven by database generalization criteria. IEEE Trans.Biomed. Eng. 2011; 58(3): 616-625.
[13]. Fraser GD, Chan ADC, Green JR, Macisaac DT. Automated bio signal quality analysis for electromyography using a one class support vector machine. IEEE Trans. Instrum. Meas. 2014; 63(12): 2919-2930.
[14]. Raj S, Ray KC. A comparative study of multivariate approach with neural networks and support vector machines for arrhythmia classification. Proc. Int. Conf. Energy, Power Environ., Towards Sustain. Growth (ICEPE), 2015; 1-6.
[15]. Haiman D, Yang B, Suiping Z, Hongrui W, Xiuling L. A Novel Method for Diagnosing Premature Ventricular Contraction Beat Based on Chaos Theory. Proceedings of 11th
International Conference on Fuzzy Systems and Knowledge Discovery (FSKD). Xiamen,
China. 2014; 497-501.
[16]. Smruthy A, Suchetha M. Real-Time Classification of Healthy and Apnea Subjects using ECG Signals with Variational Mode Decomposition. IEEE Sensors Journal. 2017; 17(10): 3092 –3099.
[17]. Ganesh KR, Kumaraswamy YS. Spline Activated Neural Network For Classifying Cardiac Arrhythmia. Journal of Computer Science. 2014; 10 (8): 1582-1590.
[18]. Sabar S, Djanggan S, Setyawan PS, Andarini S. The Peak of the PQRST and the Trajectory Path of Each Cycle of the ECG 12-Lead Wave. Indonesian Journal of Electrical Engineering and Computer Science. 2016; 4(1): 169-175.
[19]. SriLakshmi P, LokeshRaju V. ECG De-noising using Hybrid Linearization Method. Indonesian Journal of Electrical Engineering. 2015; 15(3): 504-508.
[20]. Sarthak P, Mihir NM. Impulsive Noise Cancellation from ECG Signal using Adaptive Filters and their Comparison. Indonesian Journal of Electrical Engineering and Computer Science. 2016; 3(2): 369-376.
[21]. Moody GB, Mark RG. The impact of the MIT-BIH arrhythmia database. IEEE Eng. Med. Biol. Mag. 2001; 20(3): 45-50.
[22]. Priyanka K & Archana, T 2013, ‘A survey on different noise removal techniques of EEG signals’, Int J Adv Res Comp Communication, vol. 2, pp. 1091-1095.
[23].Vani, S & Suresh, GR 2013, ‘Performance Analysis of Lifting Based DWT and MLPNN for Epilepsy Seizure from EEG’, 2013 International Conference on Human Computer Interactions, ICHCI 2013.
[24]. Wang, Z, Tang K, and Yao, X. "A Memetic Algorithm for Multi-Level Redundancy Allocation," in IEEE Transactions on Reliability, vol. 59, no. 4, pp. 754-765, Dec. 2010.
[25]. Yunfei W, Qizheng Y, Xingwang L, Dan T. Classification of Dielectric Barrier Discharges Using Digital Image Processing Technology. IEEE Transactions On Plasma Science. 2012; 40(5): 5.
[26]. H. Li et al., “Novel ECG signal classification based on KICA nonlinear feature extraction,” Circuits, Syst., Signal Process., vol. 35, no. 4, pp. 1187–1197, Apr. 2016. [Online]. Available: http://dx.doi.org/10.1007/s00034-015-0108-3
[27]. Martis, RJ, Acharya, UR, Mandana, KM, Ray, AK, and Chakraborty, C. “Cardiac decision
making using higher order spectra,” Biomed. Signal Process. Control, vol. 8, no. 2, pp. 193–
203, Mar. 2013.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
This work is licensed under a Creative Commons Attribution 4.0 International License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
