4.5 Article

Multi-Dimensional Enhanced Seizure Prediction Framework Based on Graph Convolutional Network

期刊

FRONTIERS IN NEUROINFORMATICS
卷 15, 期 -, 页码 -

出版社

FRONTIERS MEDIA SA
DOI: 10.3389/fninf.2021.605729

关键词

epilepsy EEG signal; seizures prediction; multichannel relationship; graph convolutional network; space-time prediction

资金

  1. National Natural Science Foundation of China [61572300, 81871508, 61773246]
  2. Taishan Scholar Program of Shandong Province of China [TSHW201502038]
  3. Major Program of Shandong Province Natural Science Foundation [ZR2018ZB0419]

向作者/读者索取更多资源

In the context of seizure prediction, a multi-dimensional enhanced framework was proposed to fully explore the relational data information among multiple channels of epileptic EEG. Through experiments on the CHB-MIT dataset, the model achieved a sensitivity of 98.61%, demonstrating the effectiveness of the proposed approach.
In terms of seizure prediction, how to fully mine relational data information among multiple channels of epileptic EEG? This is a scientific research subject worthy of further exploration. Recently, we propose a multi-dimensional enhanced seizure prediction framework, which mainly includes information reconstruction space, graph state encoder, and space-time predictor. It takes multi-channel spatial relationship as breakthrough point. At the same time, it reconstructs data unit from frequency band level, updates graph coding representation, and explores space-time relationship. Through experiments on CHB-MIT dataset, sensitivity of the model reaches 98.61%, which proves effectiveness of the proposed model.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.5
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据