《计算机应用》唯一官方网站 ›› 2025, Vol. 45 ›› Issue (6): 1849-1857.DOI: 10.11772/j.issn.1001-9081.2024060794

• 人工智能 • 上一篇    

融合变分图自编码器与局部-全局图网络的认知负荷脑电识别模型

周天彤1,2, 郑妍琪1,2, 魏韬1, 戴亚康3, 邹凌2,4()   

  1. 1.常州大学 计算机与人工智能学院,江苏 常州 213159
    2.常州大学 常州市生物医学信息技术重点实验室,江苏 常州 213159
    3.中国科学院 苏州生物医学工程技术研究所,江苏 苏州 215163
    4.常州大学 微电子与控制工程学院,江苏 常州 213164
  • 收稿日期:2024-06-13 修回日期:2024-10-12 接受日期:2024-10-18 发布日期:2024-11-01 出版日期:2025-06-10
  • 通讯作者: 邹凌
  • 作者简介:周天彤(1972—),男,江苏常州人,副教授,硕士,主要研究方向:人机交互
    郑妍琪(2000—),女,江苏徐州人,硕士研究生,主要研究方向:信号处理、深度学习
    魏韬(1999—),男,江苏徐州人,硕士研究生,主要研究方向:数据挖掘、推荐系统
    戴亚康(1982—),男,江苏苏州人,教授,博士,主要研究方向:智能医学影像处理、神经影像处理分析
    邹凌(1975—),女,江苏常州人,教授,博士,主要研究方向:信号处理、脑机接口。zouling@cczu.edu.cn
  • 基金资助:
    江苏省重点研发计划项目(BE2021012-5)

Cognitive load EEG recognition model integrating variational graph autoencoder and local-global graph network

Tiantong ZHOU1,2, Yanqi ZHENG1,2, Tao WEI1, Yakang DAI3, Ling ZOU2,4()   

  1. 1.School of Computer Science and Artificial Intelligence,Changzhou University,Changzhou Jiangsu 213159,China
    2.Changzhou Key Laboratory of Biomedical Information Technology,Changzhou University,Changzhou Jiangsu 213159,China
    3.Suzhou Institute of Biomedical Engineering and Technology,Chinese Academy of Sciences,Suzhou Jiangsu 215163,China
    4.School of Microelectronics and Control Engineering,Changzhou University,Changzhou Jiangsu 213164,China
  • Received:2024-06-13 Revised:2024-10-12 Accepted:2024-10-18 Online:2024-11-01 Published:2025-06-10
  • Contact: Ling ZOU
  • About author:ZHOU Tiantong, born in 1972, M. S., associate professor. His research interests include human-computer interaction.
    ZHENG Yanqi, born in 2000, M. S. candidate. Her research interests include signal processing, deep learning.
    WEI Tao, born in 1999, M. S. candidate. His research interests include data mining, recommender system.
    DAI Yakang, born in 1982, Ph. D., professor. His research interests include intelligent medical image processing, neural image processing and analysis.
    ZOU Ling, born in 1975, Ph. D., professor. Her research interests include signal processing, brain-computer interface.
  • Supported by:
    Jiangsu Province Key Research and Development Program(BE2021012-5)

摘要:

针对认知负荷识别模型存在过于依赖手动特征提取、忽视脑电图(EEG)信号的空间信息和无法有效学习图结构数据的问题,提出一种融合变分图自编码器(VGAE)与局部-全局图网络(VLGGNet)的认知负荷EEG识别模型。该模型由时间学习模块和图形学习模块这2个部分组成。首先,使用时间学习模块通过多尺度时间卷积捕捉EEG信号的动态频率表示,并通过空间与通道重建卷积(SCConv)和1×1卷积核级联模块融合多尺度卷积提取的特征;其次,使用图形学习模块将EEG数据定义为局部-全局图,其中,局部图特征提取层将节点属性聚合到一个低维向量,全局图特征提取层通过VGAE重构图结构;最后,对全局图和节点特征向量执行轻量化图卷积操作,由全连接层输出预测结果。通过嵌套交叉验证,实验结果表明,在心算任务(MAT)数据集上,相较于次优的局部-全局图网络(LGGNet),VLGGNet的平均准确率(mAcc)和平均F1分数(mF1)分别提升了4.07和3.86个百分点;在同时任务EEG工作量(STEW)数据集上,相较于表现最好的多尺度时空卷积神经网络(TSception),VLGGNet的mAcc与TSception相同,mF1仅降低了0.01个百分点。可见VLGGNet提高了认知负荷分类的性能,也验证了前额叶和额叶区域与认知负荷状态密切相关。

关键词: 认知负荷, 脑电信号, 多尺度时间卷积, 变分图自编码器, 局部-全局图网络

Abstract:

To address the issues in cognitive load recognition models such as excessive reliance on manual feature extraction, ignorance of spatial information in ElectroEncephaloGram (EEG) signals, and inability to learn graph structure data effectively, a cognitive load EEG recognition model with Variational Graph AutoEncoder (VGAE) and Local-Global Graph Network (VLGGNet) was proposed. The model was consisted of two parts: a temporal learning module and a graph learning module. Firstly, the temporal learning module was employed to capture dynamic frequency representation of EEG signals using multi-scale temporal convolution, and features extracted by the multi-scale convolution were fused through Spatial and Channel reconstruction Convolution (SCConv) and 1×1 convolutional kernel cascading module. Then, the graph learning module was employed to define the EEG data as a local-global graph, where in the local graph feature extraction layer, the node attributes were aggregated into a low-dimensional vector, and in the global graph feature extraction layer, the graph structure was reconstructed using VGAE. Finally, the lightweight graph convolution operations were performed to the global graph and the node feature vector, and the prediction results were output by the fully connected layer. Through nested cross-validation, experimental results show that VLGGNet has the mean Accuracy (mAcc) and mean F1 score (mF1) improved by 4.07 and 3.86 percentage points, respectively, compared with the sub-optimal Local-Global Graph Network (LGGNet) on Mental Arithmetic Task (MAT) dataset; compared with the best-performing multi-scale Temporal-Spatial convolutional neural network (TSception) on Simultaneous Task EEG Workload (STEW) dataset, the mAcc of VLGGNet is the same as that of TSception, and VLGGNet has the mF1 only reduced by 0.01 percentage points. It can be seen that VLGGNet improves performance of cognitive load classification, and it is verified that prefrontal and frontal regions are closely related to cognitive load status.

Key words: cognitive load, ElectroEncephaloGram (EEG) signal, multi-scale temporal convolution, Variational Graph AutoEncoder (VGAE), Local-Global Graph Network (LGGNet)

中图分类号: