Multi-dimensional conditional mutual information with application on the EEG signal analysis for spatial cognitive ability evaluation
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 t...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Published: |
Elsevier
2021
|
| _version_ | 1796984192100204544 |
|---|---|
| author | Wen, Dong Li, Rou Jiang, Mengmeng Li, Jingjing Liu, Yijun Dong, Xianling Saripan, M. Iqbal Song, Haiqing Han, Wei Zhou, Yanhong |
| author_facet | Wen, Dong Li, Rou Jiang, Mengmeng Li, Jingjing Liu, Yijun Dong, Xianling Saripan, M. Iqbal Song, Haiqing Han, Wei Zhou, Yanhong |
| author_sort | Wen, Dong |
| collection | UPM |
| description | 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. |
| first_indexed | 2024-03-06T11:16:59Z |
| format | Article |
| id | upm.eprints-102252 |
| institution | Universiti Putra Malaysia |
| last_indexed | 2024-03-06T11:16:59Z |
| publishDate | 2021 |
| publisher | Elsevier |
| record_format | dspace |
| spelling | upm.eprints-1022522023-07-10T00:58:43Z http://psasir.upm.edu.my/id/eprint/102252/ Multi-dimensional conditional mutual information with application on the EEG signal analysis for spatial cognitive ability evaluation Wen, Dong Li, Rou Jiang, Mengmeng Li, Jingjing Liu, Yijun Dong, Xianling Saripan, M. Iqbal Song, Haiqing Han, Wei Zhou, Yanhong 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. Elsevier 2021 Article PeerReviewed Wen, Dong and Li, Rou and Jiang, Mengmeng and Li, Jingjing and Liu, Yijun and Dong, Xianling and Saripan, M. Iqbal and Song, Haiqing and Han, Wei and Zhou, Yanhong (2021) Multi-dimensional conditional mutual information with application on the EEG signal analysis for spatial cognitive ability evaluation. Neural Networks, 148. 23 - 36. ISSN 0893-6080; ESSN: 1879-2782 https://www.sciencedirect.com/science/article/pii/S0893608021004834 10.1016/j.neunet.2021.12.010 |
| spellingShingle | Wen, Dong Li, Rou Jiang, Mengmeng Li, Jingjing Liu, Yijun Dong, Xianling Saripan, M. Iqbal Song, Haiqing Han, Wei Zhou, Yanhong Multi-dimensional conditional mutual information with application on the EEG signal analysis for spatial cognitive ability evaluation |
| title | Multi-dimensional conditional mutual information with application on the EEG signal analysis for spatial cognitive ability evaluation |
| title_full | Multi-dimensional conditional mutual information with application on the EEG signal analysis for spatial cognitive ability evaluation |
| title_fullStr | Multi-dimensional conditional mutual information with application on the EEG signal analysis for spatial cognitive ability evaluation |
| title_full_unstemmed | Multi-dimensional conditional mutual information with application on the EEG signal analysis for spatial cognitive ability evaluation |
| title_short | Multi-dimensional conditional mutual information with application on the EEG signal analysis for spatial cognitive ability evaluation |
| title_sort | multi dimensional conditional mutual information with application on the eeg signal analysis for spatial cognitive ability evaluation |
| work_keys_str_mv | AT wendong multidimensionalconditionalmutualinformationwithapplicationontheeegsignalanalysisforspatialcognitiveabilityevaluation AT lirou multidimensionalconditionalmutualinformationwithapplicationontheeegsignalanalysisforspatialcognitiveabilityevaluation AT jiangmengmeng multidimensionalconditionalmutualinformationwithapplicationontheeegsignalanalysisforspatialcognitiveabilityevaluation AT lijingjing multidimensionalconditionalmutualinformationwithapplicationontheeegsignalanalysisforspatialcognitiveabilityevaluation AT liuyijun multidimensionalconditionalmutualinformationwithapplicationontheeegsignalanalysisforspatialcognitiveabilityevaluation AT dongxianling multidimensionalconditionalmutualinformationwithapplicationontheeegsignalanalysisforspatialcognitiveabilityevaluation AT saripanmiqbal multidimensionalconditionalmutualinformationwithapplicationontheeegsignalanalysisforspatialcognitiveabilityevaluation AT songhaiqing multidimensionalconditionalmutualinformationwithapplicationontheeegsignalanalysisforspatialcognitiveabilityevaluation AT hanwei multidimensionalconditionalmutualinformationwithapplicationontheeegsignalanalysisforspatialcognitiveabilityevaluation AT zhouyanhong multidimensionalconditionalmutualinformationwithapplicationontheeegsignalanalysisforspatialcognitiveabilityevaluation |