Online ISSN: 2515-8260

Keywords : myocardial infarctions


AUTOMATED CLASSIFICATION OF ECG SIGNAL USING CONVOLUTIONAL GATED RECURRENT NEURAL NETWORK FOR CARDIAC DISEASE DETECTION

M. Mohamed Suhail; Dr.T. Abdul Razak

European Journal of Molecular & Clinical Medicine, 2020, Volume 7, Issue 9, Pages 2722-2739

Early detection of unusual heart conditions is huge to recognize heart disappointment and maintain a strategic distance from unexpected death. The human with similar heart conditions nearly has practically identical using electrocardiogram (ECG) signals. By reviewing the ECG signals' models, one can anticipate heart disease.Since the standard techniques for heart disease disclosure depend after securing morphological features of the ECG signals, which are repetitious and tedious, the customized recognizable proof of cardiovascular disease is progressively perfect. Subsequently, the programmed identification of heart diseases a satisfactory strategy is required, which could arrange the ECG signals with dark features as appeared by the similitudes among them and the ECG signals with known characteristics. If this classifier can discover the similitudes, the likelihood of cardiovascular disease disclosure is broadened. This count can change into a significant procedure in research facilities. During this examination work, and another classification technique is brought into the Convolutional Gated Recurrent Neural Network classification methodology. All the more precisely, orders ECG signals that rely upon a powerful model of the ECG signal classification. With this proposed method, a convolutional gated recurrent neural network was constructed, and its simulation results show that this classification can partition the ECG with 97% accuracy.