ECG Heartbeat Arrhythmia Classification Using Time-Series Augmented Signals and Deep Learning Approach

Electrocardiogram (ECG) signals are the best way to monitor the functionality and health of the cardiovascular system and also identify ailments related to it. Abnormal heartbeats are reflected in the ECG pattern and such abnormal signals are called as Arrhythmias. Automated classification and identification of the ECG arrhythmia signal that provides faster and more accurate result is increasingly becoming the need of the moment. Various machine learning skills have been applied to advance the accuracy of results and increase the speed and robustness of the models. A lot of focus has been given to the architectures and datasets employed but preprocessing of the data being equally important. In this paper, a preprocessing technique that significantly improves the accuracy of the deep learning models used for ECG classification is proposed with a modified deep learning architecture that adds to the training stability. With this preprocessing technique and deep learning model, the system is able to attain accuracy levels of more than 99% without overfitting the model.