A novel deep learning approach for arrhythmia prediction on ECG classification using recurrent CNN with GWO

In recent years, one of the most active research areas has been examining and categorizing heartbeats and brain traces connected with various types of arrhythmia and seizure. In this paper, we examine various classification methods that can be used to study and categorize electrocardiogram (ECG) signals. The proposed research evaluates the ECG signals and the Recurrent Convolutional Neural Network classification technique. The PTB Diagnostic ECG and MIT-BIH arrhythmias Databases are employed for the training and testing. The Recurrent CNN (RCNN) and the Grey Wolf Optimization (GWO) methods improve the performance matrices of machine learning compared to other techniques in the literature. The outcome performs superior to the norms currently being utilized for classification. The system's accuracy is 98%, higher than the results obtained by similar machine learning and supervised machine learning methods. The proposed research has been compared with Decision Tree, K-Nearest Neighbors algorithm, Random Forest, Support Vector Machines algorithm and Logistic Regression, and it is seen that the proposed method has the highest accuracy. Although the accuracies of the other algorithms are above 90%, they are not as efficient as the proposed algorithm. © 2023, The Author(s), under exclusive licence to Bharati Vidyapeeth's Institute of Computer Applications and Management.