Electrocardiogram soft computing using hybrid deep learning CNN-ELM

• Published in: Applied soft computing Vol. 86; p. 105778
• Main Authors: Zhou, Shuren, Tan, Bo
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.01.2020
• Subjects: Classification; Electrocardiogram (ECG) signals; Extreme learning machine; MIT-BIH dataset; MIT-BIH dataset; Extreme learning machine; Electrocardiogram (ECG) signals; Classification
• ISSN: 1568-4946; 1872-9681
• DOI: 10.1016/j.asoc.2019.105778

Electrocardiogram (ECG) can reflect the state of human heart and is widely used in clinical cardiac examination. However, the electrocardiogram signal is very weak, the anti-interference ability is poor, easy to be affected by the noise. Doctors face difficulties in diagnosing arrhythmias. Therefore, automatic recognition and classification of ECG signals is an important and indispensable task. Since the beginning of the 21 st century, deep learning has developed rapidly and has shown the most advanced performance in various fields. This paper presents a method of combining (Convolutional neural network) CNN and ELM (extreme learning machine). The accuracy rate is 97.50%. Compared with the state-of-the-art methods, this method improves the accuracy of ECG automatic classification and has good generalization ability.