Bi Suzhao, Lu Rongjian, Xu Qiang, Zhang Peiwen
School of Mechanical and Electronic Engineering, Nanjing Forestry University, Nanjing 210037, China.
Sensors (Basel). 2024 Dec 19;24(24):8124. doi: 10.3390/s24248124.
Electrocardiogram (ECG) signals contain complex and diverse features, serving as a crucial basis for arrhythmia diagnosis. The subtle differences in characteristics among various types of arrhythmias, coupled with class imbalance issues in datasets, often hinder existing models from effectively capturing key information within these complex signals, leading to a bias towards normal classes. To address these challenges, this paper proposes a method for arrhythmia classification based on a multi-branch, multi-head attention temporal convolutional network (MB-MHA-TCN). The model integrates three convolutional branch layers with different kernel sizes and dilation rates to capture features across varying temporal scales. A multi-head self-attention mechanism dynamically allocates weights, integrating features and correlations from different branches to enhance the recognition capability for difficult-to-classify samples. Additionally, the temporal convolutional network employs multi-layer dilated convolutions to progressively expand the receptive field for extracting long-term dependencies. To tackle data imbalance, a novel data augmentation strategy is implemented, and focal loss is utilized to increase the weight of minority classes, while Bayesian optimization is employed to fine-tune the model's hyperparameters. The results from five-fold cross-validation on the MIT-BIH Arrhythmia Database demonstrate that the proposed method achieves an overall accuracy of 98.75%, precision of 96.60%, sensitivity of 97.21%, and F1 score of 96.89% across five categories of ECG signals. Compared to other studies, this method exhibits superior performance in arrhythmia classification, significantly improving the recognition rate of minority classes.
心电图（ECG）信号包含复杂多样的特征，是心律失常诊断的关键依据。各类心律失常在特征上的细微差异，再加上数据集中的类别不平衡问题，常常阻碍现有模型有效捕捉这些复杂信号中的关键信息，导致对正常类别的偏向。为应对这些挑战，本文提出了一种基于多分支、多头注意力时间卷积网络（MB-MHA-TCN）的心律失常分类方法。该模型集成了三个具有不同内核大小和扩张率的卷积分支层，以跨不同时间尺度捕捉特征。多头自注意力机制动态分配权重，整合来自不同分支的特征和相关性，以增强对难以分类样本的识别能力。此外，时间卷积网络采用多层扩张卷积逐步扩大感受野，以提取长期依赖性。为解决数据不平衡问题，实施了一种新颖的数据增强策略，并利用焦点损失增加少数类别的权重，同时采用贝叶斯优化对模型的超参数进行微调。在麻省理工学院-贝斯以色列女执事医疗中心心律失常数据库上进行的五折交叉验证结果表明，该方法在五类心电图信号上的总体准确率达到98.75%，精确率为96.60%，灵敏度为97.21%，F1分数为96.89%。与其他研究相比，该方法在心律失常分类中表现出卓越的性能，显著提高了少数类别的识别率。
