基于连续小波变换和残差神经网络的房颤预测研究  

Research on Atrial Fibrillation Prediction Based on Continuous Wavelet Transform and Residual Neural Networks

作　　者：朱宇翔 童基均[1] 夏淑东 朱海航 ZHU Yuxiang;TONG Jijun;XIA Shudong;ZHU Haihang(School of Information Science and Engineering,Zhejiang Sci-Tech University,Hangzhou 310018,China;The Fourth Affiliated Hospital Zhejiang University School of Medicine,Yiwu 322000,China)

机构地区：[1]浙江理工大学信息科学与工程学院,浙江杭州310018 [2]浙江大学医学院附属第四医院,浙江义乌322000

出　　处：《软件工程》2024年第9期62-66,共5页Software Engineering

基　　金：浙江省自然科学基金项目(LQ22F010006,LTGY23H170004)。

摘　　要：心房颤动(AF)是一种最常见的心律失常类型,为了提高房颤预测的准确率和可靠性,提出了一种基于连续小波变换和残差神经网络的房颤预测方法。首先,采用软阈值小波去噪方法去除心电图信号的噪声干扰;其次,通过连续小波变换生成二维时频图;最后,使用带下采样的残差神经网络进行房颤预测。为了全面评估所提方法的性能,新建立了一个包含2160条心电图(ECG)记录的综合数据集,并在此数据集上进行了实验。实验结果表明,该方法在新数据集和公开数据集(AFPDB)上分别得到92.4%和96.1%的精确度,相较于当前的深度学习方法,实现了显著提升。Atrial Fibrillation(AF)is the most common type of arrhythmia.To improve the accuracy and reliability of AF prediction,a method based on continuous wavelet transform and residual neural network is proposed.Firstly,a soft-threshold wavelet denoising method is used to remove noise interference from the Electrocardiogram(ECG)signal.Secondly,a two-dimensional time-frequency map is generated through continuous wavelet transform.Finally,a down-sampled residual neural network is used for AF prediction.To comprehensively evaluate the performance of the proposed method,a new comprehensive dataset containing 2160 ECG records has been established,and experiments have been conducted on this dataset.Experimental results show that the method achieves accuracy of 92.4%on the new dataset and 96.1%on the publicly available dataset(AFPDB),respectively,realizing significant improvements compared to current deep learning methods.

关 键 词：房颤 心电图 连续小波变换 残差网络 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]