Understanding Power of Graph Convolutional Neural Network on Discriminating Human EEG Signal

In this study, a channel and feature selection methodology is devised for brain-computer interface (BCI) applications using functional near-infrared spectroscopy (fNIRS). A graph convolutional network (GCN) is employed to select the appropriate and correlated fNIRS channels. Furthermore, in the feature extraction phase, the performance of two filter-based feature selection algorithms, (i) the minimum redundancy maximum relevance (mRMR) and (ii) ReliefF, is investigated. The five most commonly used temporal statistical features (i.e., mean, slope, maximum, skewness, and kurtosis) are used, whereas the conventional support vector machine (SVM) is utilized as a classifier for training and testing. The proposed methodology is validated using an available online dataset of motor imagery (left- and right-hand), mental arithmetic, and baseline tasks. First, the efficacy of the proposed methodology is shown for two-class BCI applications (i.e., left- vs. right-hand motor imagery and mental arithmetic vs. baseline). Second, the proposed framework is applied to four-class BCI applications (i.e., left- vs. right-hand motor imagery vs. mental arithmetic vs. baseline). The results show that the number of appropriate channels and features was significantly reduced, resulting in a significant increase in classification accuracy for both two-class and four-class BCI applications, respectively. Furthermore, both mRMR (i.e., 87.8% for motor imagery, 87.1% for mental arithmetic, and 78.7% for four-class) and ReliefF (i.e., 90.7% for motor imagery, 93.7% for mental arithmetic, and 81.6% for four-class) yielded high average classification accuracy p < 0.05 . However, the results of the ReliefF algorithm are more stable and significant.

show abstract

“…Two GCN layer embeddings and a SoftMax layer are used in this study. Further details about the GCN model can be found in references [64,67,68].…”

Section: Optimal Fnirs Channel Selection Using Gcnmentioning

confidence: 99%

A Hybrid GCN and Filter-Based Framework for Channel and Feature Selection: An fNIRS-BCI Study

Zafar

Kallu

Yaqub

et al. 2023

International Journal of Intelligent Systems

View full text Add to dashboard Cite

show abstract

“…The identification accuracy of our VN-GCN was compared with that of two of the most popular EEG identification models developed in recent years. These are Tina's GCN model, which was proposed in 2021 (Behrouzi and Hatzinakos, 2021), and an EEG identification model based on CNN and functional connectivity, which was proposed by Wang in 2019 (Wang et al, 2019b). The structures of these three models are listed in Table 1.…”

Section: Model Accuracy and Comparisonmentioning

confidence: 99%

Fusing the spatial structure of electroencephalogram channels can increase the individualization of the functional connectivity network

Li,

Yang,

Tian

et al. 2023

Front. Comput. Neurosci.

View full text Add to dashboard Cite

An electroencephalogram (EEG) functional connectivity (FC) network is individualized and plays a significant role in EEG-based person identification. Traditional FC networks are constructed by statistical dependence and correlation between EEG channels, without considering the spatial relationships between the channels. The individual identification algorithm based on traditional FC networks is sensitive to the integrity of channels and crucially relies on signal preprocessing; therefore, finding a new presentation for FC networks may help increase the performance of the identification algorithms. EEG signals are smooth across space owing to the volume conduction effect. Considering such spatial relationships among channels can provide a more accurate representation of FC networks. In this study, we propose an EEG FC network with virtual nodes that combines the spatial relationships and functional connectivity of channels. The comparison results for individual identification show that the novel EEG network is more individualized and achieves an accuracy of 98.64% for data without preprocessing. Furthermore, our algorithm is more robust in reducing the number of channels and can perform well even when a large area of channels is removed.

show abstract

Multi-band Functional Connectivity Features Fusion Using Multi-stream GCN for EEG Biometric Identification

Tian¹,

Li²,

Hu³

2023

Lecture Notes in Electrical Engineering

View full text Add to dashboard Cite

Understanding Power of Graph Convolutional Neural Network on Discriminating Human EEG Signal

Cited by 4 publications

References 15 publications

A Hybrid GCN and Filter-Based Framework for Channel and Feature Selection: An fNIRS-BCI Study

A Hybrid GCN and Filter-Based Framework for Channel and Feature Selection: An fNIRS-BCI Study

Fusing the spatial structure of electroencephalogram channels can increase the individualization of the functional connectivity network

Multi-band Functional Connectivity Features Fusion Using Multi-stream GCN for EEG Biometric Identification

Contact Info

Product

Resources

About