基于对比学习的心电信号情绪识别方法  

ECG-based emotion recognition based on contrastive learning

作　　者：龙锦益 方景龙 刘斯为 吴汉瑞 张佳 Long Jinyi;Fang Jinglong;Liu Siwei;Wu Hanrui;Zhang Jia(College of Information Science&Technology,Jinan University,Guangzhou 510632,China;Guangdong Key Lab of Traditional Chinese Medicine Information Technology,Jinan University,Guangzhou 510632,China;Pazhou Lab,Guangzhou 510335,China)

机构地区：[1]暨南大学信息科学技术学院,广州510632 [2]暨南大学广东省中医药信息技术重点实验室,广州510632 [3]广州琶洲实验室,广州510335

出　　处：《计算机应用研究》2024年第4期1123-1130,共8页Application Research of Computers

基　　金：国家自然科学基金资助项目(62276115);广东省中医药信息化重点实验室资助项目(2021B1212040007)。

摘　　要：现有的机器学习和深度学习在解决基于心电信号的情绪识别问题时主要使用全监督的学习方法。这种方法的缺点在于需要大量的有标签数据和计算资源。同时,全监督方法学习到的特征表示通常只能针对特定任务,泛化性较差。针对这些问题,提出了一种基于对比学习的心电信号情绪识别方法,该方法分为预训练和微调两步。预训练的目的是从未标记的心电数据中学习特征表示,具体为:设计了两种简单高效的心电信号增强方式,将原始数据通过这两种数据增强转换成两个相关但不同的视图;接着这两种视图在时间对比模块中学习鲁棒的时间特征表示;最后在上下文对比模块中学习具有判别性的特征表示。微调阶段则使用带标记数据来学习情绪识别任务。在三个公开数据集上的实验表明,该方法在心电信号情绪识别准确率上与现有方法相比提高了0.21%~3.81%。此外,模型在半监督设定场景中表现出高有效性。The majority of current machine learning and deep learning solutions for ECG-based emotion recognition utilize fully-supervised learning methods.Several limitations of this approach are that large human-annotated datasets and computing resources are required.Furthermore,the feature representations learned by fully supervised methods tend to be task-specific with limited generalization capability.In response to these issues,this paper proposed an approach based on contrastive lear-ning for ECG-based emotion recognition,which consisted of two steps,such as pre-training and fine-tuning.The goal of pre-training was to learn representations from unlabeled EGG data through contrastive learning.Specifically,it designed two simple and efficient ECG signal augmentation methods,and used these two views to learn robust temporal representations in the time contrastive module,followed by learning discriminative feature representations in the context contrastive module.Fine-tuning used labelled data to learn emotion recognition.Experiments show that the proposed method has reached the maximum accuracy on three public ECG-based emotion recognition datasets.Additionally,the proposed method shows high efficiency under the semi-supervised settings.

关 键 词：心电信号 情绪识别 对比学习 自监督学习 深度学习 生理信号 数据增强 自注意力机制 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]