军事知识服务平台
一种基于智能手表PPG信号的多类心律失常分类方法
摘要 目前,心血管疾病仍是全球人类面临的主要挑战之一.心血管疾病引起的各种心律失常会影响心脏的有效收缩和血液射出,从而导致血栓等严重并发症.因此,心律失常的便捷检测和快速分类非常必要,且具有良好的应用前景.本文提出了一种基于智能手表光电容积脉搏波(PPG)信号的多类心律失常分类方法.该方法采用所提出的MGERB模型,能够识别六种不同类型的心律失常.我们结合多尺度组卷积和高效通道注意力(MGE)机制设计了一种新的MGE块,改进了残差网络(ResNet)的残差块.并通过堆叠MGE块来提取PPG信号的空间特征后,将特征向量传输到双向门控循环单元(BiGRU)提取到PPG信号的时间特征.最后,将MGE块的空间特征和BiGRU的时间特征融合,用以识别心律失常的类型.实验表明,所提出的方法在公开数据集上的总体准确率为91.11%,在自收集数据集上的准确率为95.57%,证实了本方法的准确性和有效性.
Abstract:
Currently,cardiovascular diseases remain one of the major challenges facing humanity globally.Various types of arrhythmias caused by cardiovascular disease can affect the effective heart contraction and blood ejection,leading to serious complications such as thrombosis.Therefore,convenient detection and rapid classification of arrhythmias is very necessary and has a good application prospect.In this article,we investigate a classification method of multiclass arrhythmia based on photoplethysmography(PPG)signals of smart-watches.The arrhythmia classification method,utilizing the proposed multiscale group convolution and efficient channel attention en-hanced residual network and bidirectional gated recurrent unit(MGERB)model,can identify six different types of arrhythmias.By com-bining the multiscale group convolution and efficient channel attention(MGE)mechanisms,we design a new MGE block to improve the residual blocks of the residual network(ResNet).The spatial features of PPG signals are extracted by stacking the MGE blocks.Subse-quently,the feature vectors are input into the bidirectional gated recurrent unit(BiGRU)to extract the temporal features of PPG signals.Fi-nally,the spatial features from the MGE blocks and the temporal features from the BiGRU are fused to classify the types of arrhythmias.Experiments show that the proposed method achieved an overall accuracy of 91.11%on the public dataset and 95.57%on the self-collected dataset,which verifies the accuracy and effectiveness of the proposed method.
年,卷(期): 2026, 31(4)
分类号: R541
机标分类号: TP391 R54 TP183
在线出版日期: 2026年10月10日