Abstract

Cardiac arrhythmia is a condition where heartbeat is irregular. The goal of this paper is to apply deep learning techniques in the diagnosis of cardiac arrhythmia using ECG signals with minimal possible data pre-processing. This paper employed one dimensional convolutional neural network (1D-CNN), recurrent structures such as long short-term memory (LSTM) to automatically detect the abnormality. Unlike the conventional analysis methods, the proposed method utilizes the principal component analysis (PCA) for feature extraction. Further, the existing LSTM and proposed 1D-CNN models are trained with PCA features. The optimal parameters for deep learning techniques are chosen by conducting various trails of experiments. All trails of experiments are run for 1000 epochs with learning rate in the range [0.01-0.5]. Moreover, the accuracy obtained by proposed 1D-CNN architecture is compared with existing LSTM method.

Description