融合注意力机制的多视图卷积网络癫痫智能辅助检测
DOI:
作者:
作者单位:

长春理工大学计算机科学技术学院

作者简介:

通讯作者:

中图分类号:

TP391

基金项目:

吉林省科技发展计划国际科技合作项目(20200801035GH);吉林省科技发展计划国际联合研究中心建设项目(20200802004GH)


Multi-view convolutional network with fused attention for intelligent-assisted epilepsy detection and recognition
Author:
Affiliation:

School of Computer Science and Technology, Changchun University of Science and Technology

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    针对单一视图网络癫痫检测识别精度低的问题,提出一种融合注意力机制的多视图卷积网络癫痫智能辅助检测模型(multi-view convolutional network with fused attention mechanism,FAM-MCNN)。该模型从时域、频域、时频域和非线性域提取多视图特征来全面表征脑电信号;采用多尺度卷积捕捉不同层次的细节信息;引入注意力机制分别从视图维度和单个特征向量维度对特征进行加权融合,从而提高对癫痫患者不同类别脑电信号的区分能力。在CHB-MIT癫痫数据集上进行的对比实验结果显示,与单一视图网络相比,FAM-MCNN模型的平均准确率、灵敏度、特异度分别提高了14.29%、16.13%、12.54%。此外,对该模型采用少量训练样本(25%)进行实验,结果显示其检测性能达到了拥有大量训练样本(80%-90%)的对比模型水平。

    Abstract:

    In response to the problem of low accuracy in epilepsy detection and recognition using single-view networks, a multi-view convolutional network model with fused attention mechanism (FAM-MCNN) is proposed. FAM-MCNN extracts multi-view features from time, frequency, time-frequency and nonlinear domains to comprehensively characterise the EEG signals, uses multi-scale convolution to capture different levels of detail information, and introduces an attention mechanism to weight and fuse the features from the view dimensions and individual feature vector dimensions, respectively, so as to improve the ability to discriminate between different categories of EEG signals from epilepsy patients. The results of the comparison experiments performed on the CHB-MIT epilepsy dataset show that the average accuracy, sensitivity, and specificity of the FAM-MCNN model are improved by 14.29%, 16.13%, and 12.54%, respectively, when compared to a single-view network. In addition, experiments under a small number of training samples (25%) show that its detection performance reaches the level of the comparison model with a large number of training samples (80%-90%).

    参考文献
    相似文献
    引证文献
引用本文

李奇,闫旭荣,武岩,等. 融合注意力机制的多视图卷积网络癫痫智能辅助检测[J]. 科学技术与工程, , ():

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2024-01-20
  • 最后修改日期:2024-05-24
  • 录用日期:2024-06-05
  • 在线发布日期:
  • 出版日期:
×
亟待确认版面费归属稿件,敬请作者关注