Multi-scale features for heartbeat classification using directed acyclic graph CNN

• Published in: Applied artificial intelligence Vol. 32; no. 7-8; pp. 613 - 628
• Main Authors: Golrizkhatami, Zahra, Taheri, Shahram, Acan, Adnan
• Format: Journal Article
• Language: English
• Published: Philadelphia Taylor & Francis 14.09.2018; Taylor & Francis Ltd; Taylor & Francis Group
• Subjects: Arrhythmia; Artificial neural networks; Classification; Classifiers; Electrocardiography; Feature extraction; Neural networks; State of the art

A new architecture of deep neural networks, directed acyclic graph convolutional neural networks (DAG-CNNs), is used to classify heartbeats from electrocardiogram (ECG) signals into different subject-based classes. DAG-CNNs not only fuse the feature extraction and classification stages of the ECG cl...