Epilepsy Classification for Mining Deeper Relationships between EEG Channels based on GCN
Abstract
Epilepsy is a brain disorder caused by abnormal discharges of neurons in brain. It is one of the most commonly studied disorders in neurology. The research of epilepsy electroencephalogram (EEG) has become a hot research topic. We find that in epilepsy EEG detection task, many previous methods focused on directly collecting the data of each channel, but these methods seldom analyse relationships between signals. Therefore, we propose the Epilepsy EEG Graph Convolutional Network EGCN, which makes full use of correlations between channels to deeply mine data information. We specifically design 5-layer graph convolutional network structure for classification of healthy and epileptic patients. The method is applied to public data set (Boon and CHB-MIT) to establish a reasonable classification model. And we compare it with some advanced algorithms. The experimental results show that the E-GCN method is superior to many existing methods in classification accuracy. In brief, the E-GCN method can be effectively used in classification and detection for epilepsy. This provides new ideas for colleagues, who study epilepsy EEG. In addition, this also provides richer experience for diagnosis of epilepsy.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In some studies on brain disorders based on GCN, the relationship of different channels of EEG is short of effective prior guidance and the adjacency matrix cannot ensure the utilisation of the coupling information between each channel.
“In some studies on brain disorders based on GCN (Chen et al., 2020; Li, Liu, et al., 2021; Zeng et al., 2020; Zhang et al., 2021; Zhao et al., 2021), the relationship of different channels of EEG is short of effective prior guidance and the adjacency matrix cannot ensure the utilisation of the coupling information between each channel.”
From <scp>Spatial–temporal</scp> graph convolutional network for Alzheimer classification based on brain functional connectivity imaging of electroencephalogram (2022) · cites this paper as Chen et al., 2020
The adjacency matrix is constructed by Pearson correlation analysis and five functional connectivities of the mini-epoch EEG channels without any preset threshold to avoid potential risk caused by manual selection.
“The adjacency matrix is constructed by Pearson correlation analysis and five functional connectivities of the mini‐epoch EEG channels without any preset threshold to avoid the potential risk caused by manual selection, such as in Chen et al. (2020), Zhang et al. (2021), and Zhao et al. (2021).”
From <scp>Spatial–temporal</scp> graph convolutional network for Alzheimer classification based on brain functional connectivity imaging of electroencephalogram (2022) · cites this paper as Chen et al., 2020
Traditional statistical functional correlation measures (Pearson correlation, Tanh nonlinearity, average correlation coefficients, and covariance) cannot fully represent complex brain connectivity.
“Traditional statistical functional correlation measures include Pearson correlation (PC) (Chen et al., 2020; Zhao et al., 2021), Tanh nonlinearity (Li, Liu, et al., 2021), average correlation coefficients (Zeng et al., 2020), and covariance (Zhang et al., 2021), which cannot fully represent the complex brain connectivity.”
From <scp>Spatial–temporal</scp> graph convolutional network for Alzheimer classification based on brain functional connectivity imaging of electroencephalogram (2022) · cites this paper as Chen et al., 2020
Cites
Geometric Deep Learning: Going beyond Euclidean data
Bronstein, M. M., Bruna, J., LeCun, Y., Szlam, A., & Vandergheynst, P. (2017) · IEEE Signal Processing Magazine · doi:10.1109/msp.2017.2693418 · Cited by 3,661 · see citing works
Seizure detection, seizure prediction, and closed-loop warning systems in epilepsy
Ramgopal, S., Thome-Souza, S., Jackson, M., Kadish, N. E., Sánchez Fernández, I., Klehm, J., Bosl, W., Reinsberger, C., Schachter, S., & Loddenkemper, T. (2014) · Epilepsy & Behavior · doi:10.1016/j.yebeh.2014.06.023 · Cited by 469 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Shan, X., Cao, J., Huo, S., Chen, L., Sarrigiannis, P. G., & Zhao, Y. (2022) · Human Brain Mapping · doi:10.1002/hbm.25994 · Cited by 75 · see citing works
“Traditional statistical functional correlation measures include Pearson correlation (PC) (Chen et al., 2020; Zhao et al., 2021), Tanh nonlinearity (Li, Liu, et al., 2021), average correlation coefficients (Zeng et al., 2020), and covariance (Zhang et al., 2021), which cannot fully represent the…”
BackgroundMethod
- Authors
- Chen, X., Zheng, Y., Niu, Y., & Li, C.
- Affiliations
- Shandong Normal University (CN)
- Shandong University of Science and Technology (CN)
- Venue
- 2020 International Conference on Computer Vision, Image and Deep Learning (CVIDL)
- Publisher
- IEEE
- Published
- 2020-07
- Pages
- 701-706
- OpenAlex
- W3108567116
- Cited by
- 34
- References
- 2
- Citations by year
- 2026: 1 · 2025: 8 · 2024: 12 · 2023: 6 · 2022: 6 · 2021: 1
- FWCI
- 4.23
- Type
- conference paper
- Language
- en
- Open access
- closed
- Licence
- Locations
- International Conference on Computer Vision, Image and Deep Learning (CVIDL) (publishedVersion)
- Funders
- National Natural Science Foundation of China
- Natural Science Foundation of Shandong Province
- Topics
- Life Sciences › Neuroscience › Cognitive Neuroscience › EEG and Brain-Computer Interfaces
- Social Sciences › Psychology › Experimental and Cognitive Psychology › Emotion and Mood Recognition
- Health Sciences › Medicine › Cardiology and Cardiovascular Medicine › ECG Monitoring and Analysis
- Keywords
- epilepsy classification, EEG, graph convolutional networks, CHB-MIT dataset, epilepsy diagnosis
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
