GB-SVNN: Genetic BAT assisted support vector neural network for arrhythmia classification using ECG signals Bhagyalakshmi V a,⇑ , R.V. Pujeri b , Geetha D. Devanagavi c a REVA University, Rukmini Knowledge Park, Kattigenahalli, Yelahanka, Bangalore 560 064, India b M.I.T.C.O.E, Pune, India c Reva University, Bangalore, India article info Article history: Received 9 September 2017 Revised 8 February 2018 Accepted 12 February 2018 Available online xxxx Keywords: Arrhythmia classification Genetic algorithm Bat optimization ECG signals ECG wave intervals SVNN abstract Arrhythmia is a cardiac condition generated by the abnormal electrical activity of the heart, and an elec- trocardiogram (ECG) is a tool utilized by the cardiologists for determining the arrhythmias or heart abnormalities. Owing to the existence of noise, the non-stationary nature of the ECG signal and the abnormality of the heartbeat, physicians face difficulties in the diagnosis of arrhythmias. Hence, there is a need for computer-aided diagnosis system which can achieve higher recognition accuracy. Since the existing methods of classification consumed huge time and less accurate in case of considerably sim- ilar ECG signal, this paper proposes an effective method termed as Genetic Bat optimization algorithm for training the Support Vector Neural Network (GB-SVNN) for arrhythmia classification using ECG signals. Initially, multi-resolution wavelet-based approach and the Gabor filters are used for extracting the wave interval features and other texture features from the ECG signal. Based on the features, the SVNN classi- fies the ECG signal as the affected arrhythmia or no arrhythmia signal. The SVNN is trained using the GB algorithm. The experimentation of the proposed method is done using MATLAB 2015.a, and the perfor- mance is evaluated with the existing methods, such as KNN, Neural Network (NN), Fuzzy Subtractive Clustering, and Support Vector Neural Network (SVNN) for accuracy, specificity, and sensitivity. From the results, it can be shown that the proposed GD-SVNN attains a maximum value of accuracy, sensitivity, and specificity at a rate of 0.9696, 0.99, and 0.9583 respectively. Ó 2018 Production and hosting by Elsevier B.V. on behalf of King Saud University. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/). 1. Introduction The healthcare scenario reports heart diseases as one of the major killer diseases over the past decade (Schamroth, 2009). Hence, improved and verified medical devices, such as electrocar- diogram (ECG) or the electroencephalogram (EEG) are widely employed for monitoring the health of the patients on the real- time (Banerjee and Mitra, February 2014) (Schamroth, 2009) (Goldberg, 2010). ECG is a one-dimensional signal that records the electrical activity of the heart, which changes from time-to- time and person-to-person (Buza and Schmidt-Thieme, 2010). The ECG signal is enriched with the information of the heart and the cardiovascular system (Ramanujam and Padmavathi, 2016). A single heartbeat comprises of the QRS complex, P wave, and T wave in which each of them denotes a specific task. The P wave indicates the atrial depolarization, QRS complex represents the ventricular depolarization, and the T wave denotes the ventricular repolariza- tion (Hollenberg and Walker, 2005). Any deviation in the shape or the duration of the time intervals causes the irregular heartbeat cycles termed as arrhythmia (Kusumoto, 2009)(Elsayyad et al., 2015). The pacemaker cells regulate the rhythm of the heart, which is regular under normal conditions. The irregular rhythm is charac- terized by arrhythmia, an abnormal fast or slow rate of the heart- beat (Ramanujam and Padmavathi, 2016). During the severe conditions of arrhythmia, the pumping capacity of the heart degrades leading to the trouble in breathing, chest pain, tiredness, and unconsciousness and sometimes, results in heart attack and even death. Thus, arrhythmia classification (Thomas et al., April 2015; Elhaj et al., 2016) is essential that avoids the bad effects caused by the arrhythmia (Mitra and Samanta, 2013). HEART arrhythmia (Martis et al., 2013a,b,c), an unusual behav- ior of the heart is broadly categorized into two main groups. The https://doi.org/10.1016/j.jksuci.2018.02.005 1319-1578/Ó 2018 Production and hosting by Elsevier B.V. on behalf of King Saud University. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/). ⇑ Corresponding author. E-mail address: lakshmianand04@gmail.com (V Bhagyalakshmi). Peer review under responsibility of King Saud University. Production and hosting by Elsevier Journal of King Saud University – Computer and Information Sciences xxx (2018) xxx–xxx Contents lists available at ScienceDirect Journal of King Saud University – Computer and Information Sciences journal homepage: www.sciencedirect.com Please cite this article in press as: Bhagyalakshmi, V., et al. GB-SVNN: Genetic BAT assisted support vector neural network for arrhythmia classification using ECG signals. Journal of King Saud University – Computer and Information Sciences (2018), https://doi.org/10.1016/j.jksuci.2018.02.005