Details
| Original language | English |
|---|---|
| Article number | 105475 |
| Journal | Biomedical Signal Processing and Control |
| Volume | 87 |
| Early online date | 24 Sept 2023 |
| Publication status | Published - Jan 2024 |
Abstract
This study examines the efficacy of various neural network (NN) models in interpreting mental constructs via electroencephalogram (EEG) signals. Through the assessment of 16 prevalent NN models and their variants across four brain-computer interface (BCI) paradigms, we gauged their information representation capability. Rooted in comprehensive literature review findings, we proposed EEGNeX, a novel, purely ConvNet-based architecture. We pitted it against both existing cutting-edge strategies and the Mother of All BCI Benchmarks (MOABB) involving 11 distinct EEG motor imagination (MI) classification tasks and revealed that EEGNeX surpasses other state-of-the-art methods. Notably, it shows up to 2.1%–8.5% improvement in the classification accuracy in different scenarios with statistical significance (p < 0.05) compared to its competitors. This study not only provides deeper insights into designing efficient NN models for EEG data but also lays groundwork for future explorations into the relationship between bioelectric brain signals and NN architectures. For the benefit of broader scientific collaboration, we have made all benchmark models, including EEGNeX, publicly available at (https://github.com/chenxiachan/EEGNeX).
Keywords
- Computer-Assisted, Decoding, Electroencephalography, Feature extraction, Machine learning, Representation learning, Signal Processing
ASJC Scopus subject areas
- Computer Science(all)
- Signal Processing
- Engineering(all)
- Biomedical Engineering
- Medicine(all)
- Health Informatics
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
In: Biomedical Signal Processing and Control, Vol. 87, 105475, 01.2024.
Research output: Contribution to journal › Article › Research › peer review
}
TY - JOUR
T1 - Toward reliable signals decoding for electroencephalogram
T2 - A benchmark study to EEGNeX
AU - Chen, Xia
AU - Teng, Xiangbin
AU - Chen, Han
AU - Pan, Yafeng
AU - Geyer, Philipp
PY - 2024/1
Y1 - 2024/1
N2 - This study examines the efficacy of various neural network (NN) models in interpreting mental constructs via electroencephalogram (EEG) signals. Through the assessment of 16 prevalent NN models and their variants across four brain-computer interface (BCI) paradigms, we gauged their information representation capability. Rooted in comprehensive literature review findings, we proposed EEGNeX, a novel, purely ConvNet-based architecture. We pitted it against both existing cutting-edge strategies and the Mother of All BCI Benchmarks (MOABB) involving 11 distinct EEG motor imagination (MI) classification tasks and revealed that EEGNeX surpasses other state-of-the-art methods. Notably, it shows up to 2.1%–8.5% improvement in the classification accuracy in different scenarios with statistical significance (p < 0.05) compared to its competitors. This study not only provides deeper insights into designing efficient NN models for EEG data but also lays groundwork for future explorations into the relationship between bioelectric brain signals and NN architectures. For the benefit of broader scientific collaboration, we have made all benchmark models, including EEGNeX, publicly available at (https://github.com/chenxiachan/EEGNeX).
AB - This study examines the efficacy of various neural network (NN) models in interpreting mental constructs via electroencephalogram (EEG) signals. Through the assessment of 16 prevalent NN models and their variants across four brain-computer interface (BCI) paradigms, we gauged their information representation capability. Rooted in comprehensive literature review findings, we proposed EEGNeX, a novel, purely ConvNet-based architecture. We pitted it against both existing cutting-edge strategies and the Mother of All BCI Benchmarks (MOABB) involving 11 distinct EEG motor imagination (MI) classification tasks and revealed that EEGNeX surpasses other state-of-the-art methods. Notably, it shows up to 2.1%–8.5% improvement in the classification accuracy in different scenarios with statistical significance (p < 0.05) compared to its competitors. This study not only provides deeper insights into designing efficient NN models for EEG data but also lays groundwork for future explorations into the relationship between bioelectric brain signals and NN architectures. For the benefit of broader scientific collaboration, we have made all benchmark models, including EEGNeX, publicly available at (https://github.com/chenxiachan/EEGNeX).
KW - Computer-Assisted
KW - Decoding
KW - Electroencephalography
KW - Feature extraction
KW - Machine learning
KW - Representation learning
KW - Signal Processing
UR - http://www.scopus.com/inward/record.url?scp=85172215927&partnerID=8YFLogxK
U2 - 10.48550/arXiv.2207.12369
DO - 10.48550/arXiv.2207.12369
M3 - Article
AN - SCOPUS:85172215927
VL - 87
JO - Biomedical Signal Processing and Control
JF - Biomedical Signal Processing and Control
SN - 1746-8094
M1 - 105475
ER -