A Deep Learning Based ECG Segmentation Tool for Detection of ECG Beat Parameters

The role of ECG segmentation tool has been pivotal in automated analysis of real-time ECG signals for detection of non-invasive cardiovascular and physiological conditions. Most of the existing approaches focus on traditional signal processing and/or traditional machine learning based approaches which are highly dependent on signal noise, inter/intra subject variability, etc. With the advent of deep learning based networks, it is possible to design and develop the classification model based on local features along with spatial and temporal context of the physiological signals. In this paper, we developed the attention based Convolutional Bidirectional Long Short Term Memory (Conv-BiLSTM) architecture network based on local beat features and temporal sequencing while correlating ECG beat across different positions. The performance of our ECG segmentation tool has been evaluated against the state-of-the art approaches in terms of ECG segmentation and fiducial point detection accuracy. The ECG segmentation accuracy was 95% whereas fiducial point detection accuracy was 99.4%.