Neural Networks2022，Vol.14814.DOI:10.1016/j.neunet.2021.12.010

Multi-dimensional conditional mutual information with application on the EEG signal analysis for spatial cognitive ability evaluation

Li, Jingjing Liu, Yijun Dong, Xianling Saripan, M. Iqbal Song, Haiqing Han, Wei Zhou, Yanhong Wen, Dong Li, Rou Jiang, Mengmeng
Neural Networks2022，Vol.14814.DOI:10.1016/j.neunet.2021.12.010
✕
  • NSTL
  • Elsevier

Multi-dimensional conditional mutual information with application on the EEG signal analysis for spatial cognitive ability evaluation

Li, Jingjing 1Liu, Yijun 2Dong, Xianling 3Saripan, M. Iqbal 4Song, Haiqing 5Han, Wei 1Zhou, Yanhong 6Wen, Dong 7Li, Rou 1Jiang, Mengmeng1
扫码查看

作者信息

  • 1. Sch Informat Sci & Engn,Yanshan Univ
  • 2. Sch Sci,Yanshan Univ
  • 3. Dept Biomed Engn,Chengde Med Univ
  • 4. Fac Engn,Univ Putra Malaysia
  • 5. Dept Neurol,Capital Med Univ
  • 6. Sch Math & Informat Sci & Technol,Hebei Normal Univ Sci & Technol
  • 7. Inst Artificial Intelligence,Univ Sci & Technol Beijing
  • 折叠

Abstract

This study aims to explore an effective method to evaluate spatial cognitive ability, which can effectively extract and classify the feature of EEG signals collected from subjects participating in the virtual reality (VR) environment; and evaluate the training effect objectively and quantitatively to ensure the objectivity and accuracy of spatial cognition evaluation, according to the classification results. Therefore, a multi-dimensional conditional mutual information (MCMI) method is proposed, which could calculate the coupling strength of two channels considering the influence of other channels. The coupled characteristics of the multi-frequency combination were transformed into multi spectral images, and the image data were classified employing the convolutional neural networks (CNN) model. The experimental results showed that the multi-spectral image transform features based on MCMI are better in classification than other methods, and among the classification results of six band combinations, the best classification accuracy of Beta1-Beta2-Gamma combination is 98.3%. The MCMI characteristics on the Beta1-Beta2-Gamma band combination can be a biological marker for the evaluation of spatial cognition. The proposed feature extraction method based on MCMI provides a new perspective for spatial cognitive ability assessment and analysis. (C)& nbsp;2021 Elsevier Ltd. All rights reserved.

Key words

Multi-dimensional conditional mutual & nbsp/information/Multi-spectral image/Spatial cognition/Task-state EEG signal/Coupling feature extraction/DIABETES-MELLITUS/NEURAL-NETWORK/IMPAIRMENT/NAVIGATION

引用本文复制引用

出版年

2022
Neural Networks

Neural Networks

EISCI
ISSN：0893-6080
被引量4
参考文献量38
段落导航相关论文