穿戴式脑电多尺度时空注意力癫痫预测模型
DOI:
CSTR:
作者:
作者单位:

云南师范大学信息学院昆明650500

作者简介:

通讯作者:

中图分类号:

TN911.7;R318

基金项目:

国家自然科学基金(6256030308)、云南师范大学研究生科研创新基金(YJSJJ26-B082)、国家自然科学基金(12362023)、教育部中国高校产学研创新项目(2024TX005)资助


Wearable EEG multi-scale spatiotemporal attention epileptic seizure prediction model
Author:
Affiliation:

School of Information Science and Technology, Yunnan Normal University, Kunming 650500, China

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:

    针对穿戴式脑电监测设备长时程连续测量中,宽频微弱信号解析不足、分类边界模糊导致临床假阳性率高的测量痛点,构建一种多尺度时空注意与边缘对比学习的轻量级脑电解析与预测模型(multi-scale contrastive EEGNet,MC-EEGNet)。首先,采用并行多尺度分支设计多尺度时序卷积型时空注意力单元(multi-scale temporal convolutional block attention module, MS-CBAM),实现宽频脑电信号的频域解耦,并利用双重注意力机制对病灶通道与关键时序特征自适应重标定;其次,引入边缘监督对比学习损失(margin-supervised contrastive learning loss, Margin-SupCon),在高维特征流形中建立硬性类间隔离带以锐化分类决策边界;最后,提出离线预处理与在线动态相串联的双阶段数据增强策略,通过小波频域混叠与时空掩码以及引入基于物理先验的阻抗噪声模拟模块,有效补偿数据采集链路中信号瞬态中断及传感器接触不良等非理想物理约束引起的信号干扰。基于公开的CHB-MIT头皮脑电数据集,对MC-EEGNet开展了留一法交叉验证。结果表明,在30 min预测窗口下,其平均灵敏度达95.58%,每小时假阳性率(FPR/h)降至0.013,较基线模型显著降低46%,且平均预测时间延长至22.46 min。该模型有效克服传统单尺度卷积的感知局限,在低计算开销下实现了灵敏度与假阳性抑制的最优平衡,可为便携式脑电监测智能仪器的边缘端嵌入式部署提供高鲁棒性算法支撑。

    Abstract:

    To address high clinical false positive rates in wearable continuous long-term electroencephalogram (EEG) monitoring caused by insufficient broadband weak signal parsing and blurred classification boundaries, a lightweight multi-scale contrastive EEGNet (MC-EEGNet) parsing and prediction model is constructed. Firstly, a multi-scale temporal convolutional block attention module (MS-CBAM) is designed to decouple complex EEG signals in the frequency domain via parallel multi-scale branches, utilizing a dual attention mechanism to adaptively recalibrate focal channels and key temporal features; secondly, a margin-supervised contrastive learning loss (Margin-SupCon) is introduced to establish a rigid inter-class isolation band within the high-dimensional feature manifold to sharpen classification decision boundaries; lastly, a two-stage data augmentation strategy cascading offline preprocessing and online dynamic training is proposed to compensate for signal interferences under non-ideal physical measurement constraints such as transient signal interruption in EEG acquisition links and poor sensor contact via wavelet frequency mixing, spatiotemporal masking, and a physics-prior-based impedance noise simulation module. The MC-EEGNet is evaluated using leave-one-out cross-validation on the public CHB-MIT scalp EEG dataset. Results demonstrate that under a 30-minute prediction window, the model achieves an average sensitivity of 95.58%, the hourly false positive rate (FPR/h) is reduced to 0.013 (a 46% reduction compared to the baseline model), and the average prediction time is extended to 22.46 minutes. The model effectively overcomes the perceptual limitations of traditional single-scale convolutions and achieves an optimal balance between sensitivity and false positive suppression under low computational overhead, providing robust algorithmic support for the edge-embedded deployment of portable smart EEG monitoring instruments.

    参考文献
    相似文献
    引证文献
引用本文

何泰亮,孙瑜,易志坚,李志平.穿戴式脑电多尺度时空注意力癫痫预测模型[J].电子测量与仪器学报,2026,40(9):101-111

复制
分享
相关视频

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:
  • 最后修改日期:
  • 录用日期:
  • 在线发布日期: 2026-11-13
  • 出版日期:
文章二维码
×
《电子测量与仪器学报》
关于防范虚假编辑部邮件的郑重公告