eduzhai > Applied Sciences > Engineering >

A Novel Method for ECG Signal Classification via One-Dimensional Convolutional Neural Network

  • Save

... pages left unread,continue reading

Document pages: 14 pages

Abstract: This paper presents an end-to-end ECG signal classification method based on anovel segmentation strategy via 1D Convolutional Neural Networks (CNN) to aidthe classification of ECG signals. The ECG segmentation strategy named R-R-Rstrategy (i.e., retaining ECG data between the R peaks just before and afterthe current R peak) for segmenting the original ECG data into segments in orderto train and test the 1D CNN models. The novel strategy mimics physicians inscanning ECG to a greater extent, and maximizes the inherent information of ECGsegments. The performance of the classification models for 5-class and 6-classare verified with ECG signals from 48 records of the MIT-BIH arrhythmiadatabase. As the heartbeat types are divided into 5 classes (i.e., normal beat,left bundle branch block beat, right bundle branch block beat, ventricularectopic beat, and paced beat) in the MIT-BIH, the best classification accuracy,the area under the curve (AUC), the sensitivity and the F1-score reach 99.24 ,0.9994, 0.99 and 0.99, respectively. As the heartbeat types are divided into 6classes (i.e., normal beat, left bundle branch block beat, right bundle branchblock beat, ventricular ectopic beat, paced beat and other beats) in theMIT-BIH, the beat classification accuracy, the AUC, the sensitivity, and theF1-score reach 97.02 , 0.9966, 0.97, and 0.97, respectively. Meanwhile,according to the recommended practice from the Association for Advancement ofMedical Instrumentation (AAMI), the heartbeat types are divided into 5 classes(i.e., normal beat, supraventricular ectopic beats, ventricular ectopic beats,fusion beats, and unclassifiable beats), the beat classification accuracy, thesensitivity, and the F1-score reach 97.45 , 0.97, and 0.97, respectively. Theexperimental results show that the proposed method achieves better performancethan the state-of-the-art methods.

Please select stars to rate!

         

0 comments Sign in to leave a comment.

    Data loading, please wait...
×