ECG Signal Processing and Automatic Classification Algorithms

• Published in: International journal of crowd science Vol. 8; no. 3; pp. 122 - 129
• Main Authors: Yang, Xiaonuo, Chai, Yueting
• Format: Journal Article
• Language: English
• Published: Tsinghua University Press 01.09.2024
• Subjects: ecg classification; electrocardiogram (ecg); model stacking
• ISSN: 2398-7294; 2398-7294
• DOI: 10.26599/IJCS.2023.9100026

With heart health issues attracting much attention, wearable electrocardiogram (ECG) monitoring devices show a broad market prospect. This paper develops a generic ECG pre-processing algorithm and proposes a method for the single-lead ECG classification problem based on model stacking. Features such as RR-intervals, power spectrum, and higher-order statistics are computed and grouped into three classes. The support vector machine (SVM) classifier is trained separately based on each class of features, and subsequently, a fourth SVM classifier is trained on the prediction results of the three SVM classifiers at the first layer. To obtain more realistic results and better comparisons with previous studies, the algorithm follows the ANSI/AAMI EC57:2012 standard and is tested on a real ECG database. The experimental results show that the algorithm in this paper better overcomes the impact of the data imbalance problem and obtains good results.