ECG-NAT: A Self-supervised Neighborhood Attention Transformer for Multi-lead Electrocardiogram Classification
ECG-NAT:一种用于多导联心电图分类的自监督邻域注意力变换器
机构 * Department of Computer Engineering, University of Kurdistan(库尔德斯坦大学计算机工程系) ; Department of Mathematics and Operational Research, University of Mons(蒙斯大学数学与运筹学系)
专题命中 健康监测 :diagnosis(abstract);分类 cs.LG
AI总结 本文提出ECG-NAT,一种自监督学习方法,通过分阶段预训练和微调,有效提取多尺度特征,实现高效准确的多导联心电图分类,仅用1%标注数据即可达到88.1%的准确率。