电子科技大学学报2024，Vol.53Issue(6)：940-951,12.DOI:10.12178/1001-0548.2023244
基于扩散模型的心电信号去噪方法
Denoising Method of ECG Based on Diffusion Model
摘要
Abstract
Traditional and deep learning denoising techniques exhibit shortcomings in handling specific types of noise and data generalization validation in Electrocardiogram(ECG)signals.This paper proposes a generative ECG denoising model based on diffusion models,which leverages simulated data to learn the score function of clean ECG distribution and generates and separates ECG and noise based on the Euler method for solving Ordinary Differential Equations(ODE).The model is trained on simulated data and validated on an independent real dataset.Compared to other relevant methods,the obtained results demonstrate that this model has significant advantages in removing diverse noise and maintaining consistency in ECG waveforms of different amplitude features.关键词
ECG/扩散模型/去噪/神经网络/信号分离Key words
ECG/diffusion model/denoising/neural network/signal separation分类
信息技术与安全科学引用本文复制引用
罗成思,张凯旋,Abduljabbar Salem Ba-Mahel,饶妮妮..基于扩散模型的心电信号去噪方法[J].电子科技大学学报,2024,53(6):940-951,12.基金项目
国家自然科学基金(62271127) （62271127）
四川省自然科学基金(2023NSFSC0627) （2023NSFSC0627）
电子科技大学与四川大学华西医院医工合作基金(ZYGX2022YGRH011,HXDZ22005) （ZYGX2022YGRH011,HXDZ22005）
