Spatial Cognitive EEG Feature Extraction and Classification Based on MSSECNN and PCMI
With the aging population rising, the decline in spatial cognitive ability has become a critical issue affecting the quality of life among the elderly. Electroencephalogram (EEG) signal analysis presents substantial potential in spatial cognitive assessments. However, conventional methods struggle t...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-12-01
|
| Series: | Bioengineering |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2306-5354/12/1/25 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832589089270923264 |
|---|---|
| author | Xianglong Wan Yue Sun Yiduo Yao Wan Zuha Wan Hasan Dong Wen |
| author_facet | Xianglong Wan Yue Sun Yiduo Yao Wan Zuha Wan Hasan Dong Wen |
| author_sort | Xianglong Wan |
| collection | DOAJ |
| description | With the aging population rising, the decline in spatial cognitive ability has become a critical issue affecting the quality of life among the elderly. Electroencephalogram (EEG) signal analysis presents substantial potential in spatial cognitive assessments. However, conventional methods struggle to effectively classify spatial cognitive states, particularly in tasks requiring multi-class discrimination of pre- and post-training cognitive states. This study proposes a novel approach for EEG signal classification, utilizing Permutation Conditional Mutual Information (PCMI) for feature extraction and a Multi-Scale Squeezed Excitation Convolutional Neural Network (MSSECNN) model for classification. Specifically, the MSSECNN classifies spatial cognitive states into two classes—before and after cognitive training—based on EEG features. First, the PCMI extracts nonlinear spatial features, generating spatial feature matrices across different channels. SENet then adaptively weights these features, highlighting key channels. Finally, the MSCNN model captures local and global features using convolution kernels of varying sizes, enhancing classification accuracy and robustness. This study systematically validates the model using cognitive training data from a brain-controlled car and manually operated UAV tasks, with cognitive state assessments performed through spatial cognition games combined with EEG signals. The experimental findings demonstrate that the proposed model significantly outperforms traditional methods, offering superior classification accuracy, robustness, and feature extraction capabilities. The MSSECNN model’s advantages in spatial cognitive state classification provide valuable technical support for early identification and intervention in cognitive decline. |
| format | Article |
| id | doaj-art-fc3577655cf14461bb58736a3adc3e88 |
| institution | Kabale University |
| issn | 2306-5354 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Bioengineering |
| spelling | doaj-art-fc3577655cf14461bb58736a3adc3e882025-01-24T13:23:00ZengMDPI AGBioengineering2306-53542024-12-011212510.3390/bioengineering12010025Spatial Cognitive EEG Feature Extraction and Classification Based on MSSECNN and PCMIXianglong Wan0Yue Sun1Yiduo Yao2Wan Zuha Wan Hasan3Dong Wen4School of Intelligence Science and Technology, University of Science and Technology Beijing, Beijing 100083, ChinaSchool of Intelligence Science and Technology, University of Science and Technology Beijing, Beijing 100083, ChinaSchool of Intelligence Science and Technology, University of Science and Technology Beijing, Beijing 100083, ChinaDepartment of Electrical and Electronic Engineering, Faculty of Engineering, Universiti Putra Malaysia, Serdang 43400, MalaysiaSchool of Intelligence Science and Technology, University of Science and Technology Beijing, Beijing 100083, ChinaWith the aging population rising, the decline in spatial cognitive ability has become a critical issue affecting the quality of life among the elderly. Electroencephalogram (EEG) signal analysis presents substantial potential in spatial cognitive assessments. However, conventional methods struggle to effectively classify spatial cognitive states, particularly in tasks requiring multi-class discrimination of pre- and post-training cognitive states. This study proposes a novel approach for EEG signal classification, utilizing Permutation Conditional Mutual Information (PCMI) for feature extraction and a Multi-Scale Squeezed Excitation Convolutional Neural Network (MSSECNN) model for classification. Specifically, the MSSECNN classifies spatial cognitive states into two classes—before and after cognitive training—based on EEG features. First, the PCMI extracts nonlinear spatial features, generating spatial feature matrices across different channels. SENet then adaptively weights these features, highlighting key channels. Finally, the MSCNN model captures local and global features using convolution kernels of varying sizes, enhancing classification accuracy and robustness. This study systematically validates the model using cognitive training data from a brain-controlled car and manually operated UAV tasks, with cognitive state assessments performed through spatial cognition games combined with EEG signals. The experimental findings demonstrate that the proposed model significantly outperforms traditional methods, offering superior classification accuracy, robustness, and feature extraction capabilities. The MSSECNN model’s advantages in spatial cognitive state classification provide valuable technical support for early identification and intervention in cognitive decline.https://www.mdpi.com/2306-5354/12/1/25spatial cognitionEEGmulti-scale convolutional neural networksqueezed excitation networkpermutation conditional mutual information |
| spellingShingle | Xianglong Wan Yue Sun Yiduo Yao Wan Zuha Wan Hasan Dong Wen Spatial Cognitive EEG Feature Extraction and Classification Based on MSSECNN and PCMI Bioengineering spatial cognition EEG multi-scale convolutional neural network squeezed excitation network permutation conditional mutual information |
| title | Spatial Cognitive EEG Feature Extraction and Classification Based on MSSECNN and PCMI |
| title_full | Spatial Cognitive EEG Feature Extraction and Classification Based on MSSECNN and PCMI |
| title_fullStr | Spatial Cognitive EEG Feature Extraction and Classification Based on MSSECNN and PCMI |
| title_full_unstemmed | Spatial Cognitive EEG Feature Extraction and Classification Based on MSSECNN and PCMI |
| title_short | Spatial Cognitive EEG Feature Extraction and Classification Based on MSSECNN and PCMI |
| title_sort | spatial cognitive eeg feature extraction and classification based on mssecnn and pcmi |
| topic | spatial cognition EEG multi-scale convolutional neural network squeezed excitation network permutation conditional mutual information |
| url | https://www.mdpi.com/2306-5354/12/1/25 |
| work_keys_str_mv | AT xianglongwan spatialcognitiveeegfeatureextractionandclassificationbasedonmssecnnandpcmi AT yuesun spatialcognitiveeegfeatureextractionandclassificationbasedonmssecnnandpcmi AT yiduoyao spatialcognitiveeegfeatureextractionandclassificationbasedonmssecnnandpcmi AT wanzuhawanhasan spatialcognitiveeegfeatureextractionandclassificationbasedonmssecnnandpcmi AT dongwen spatialcognitiveeegfeatureextractionandclassificationbasedonmssecnnandpcmi |