Toward reliable signals decoding for electroencephalogram: A benchmark study to EEGNeX

Chen, Xia; Teng, Xiangbin; Chen, Han; Pan, Yafeng; Geyer, Philipp

doi:10.48550/arxiv.2207.12369

Cited by 3 publications

(6 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The model is designed specifically for EEG data and enables automatic feature extraction. The third model, EEGNeX [25], builds upon the EEGNet model, by altering specific elements to enhance performance, such as thickening the spatial information extraction, replacing the separable convolution with 2D convolutions, using an inverted bottleneck, and reducing the number of activation functions for network dilation. Our final model was TCNetFusion [13], a CNN model that integrates various techniques, including temporal convolution neural networks (TCNs), separable convolution, depth-wise convolution, and layer fusion.…”

Section: Models Training and Evaluationmentioning

confidence: 99%

Individual-finger motor imagery classification: a data-driven approach with Shapley-informed augmentation

Alsuradi,

Khattak,

Fakhry

et al. 2024

J. Neural Eng.

View full text Add to dashboard Cite

Objective. Classifying motor imagery (MI) tasks that involve fine motor control of the individual five fingers presents unique challenges when utilizing electroencephalography (EEG) data. In this paper, we systematically assess the classification of MI functions for the individual five fingers using single-trial time-domain EEG signals. This assessment encompasses both within-subject and cross-subject scenarios, supported by data-driven analysis that provides statistical validation of the neural correlate that could potentially discriminate between the five fingers. Approach. We present Shapley-informed augmentation, an informed approach to enhance within-subject classification accuracy. This method is rooted in insights gained from our data-driven analysis, which revealed inconsistent temporal features encoding the five fingers MI across sessions of the same subject. To evaluate its impact, we compare within-subject classification performance both before and after implementing this augmentation technique. Main results. Both the data-driven approach and the model explainability analysis revealed that the parietal cortex contains neural information that helps discriminate the individual five fingers' MI apart. Shapley-informed augmentation successfully improved classification accuracy in sessions severely affected by inconsistent temporal features. The accuracy for sessions impacted by inconsistency in their temporal features increased by an average of 26.3% ± 6.70, thereby enabling a broader range of subjects to benefit from brain-computer interaction (BCI) applications involving five-fingers MI classification. Conversely, non-impacted sessions experienced only a negligible average accuracy decrease of 2.01 ± 5.44%. The average classification accuracy achieved is around 60.0% (within-session), 50.0% (within-subject) and 40.0% (leave-one-subject-out). Significance. This research offers data-driven evidence of neural correlates that could discriminate between the individual five fingers MI and introduces a novel Shapley-informed augmentation method to address temporal variability of features, ultimately contributing to the development of personalized systems.

show abstract

Section: Models Training and Evaluationmentioning

confidence: 99%

Individual-finger motor imagery classification: a data-driven approach with Shapley-informed augmentation

Alsuradi,

Khattak,

Fakhry

et al. 2024

J. Neural Eng.

View full text Add to dashboard Cite

show abstract

“…Our proposed model is an ensemble of two models; the first is EEGNex [22] which is purely a 2D CNN model, while the second is a modified version of the TCNet Fusion model [23], called squeeze-andexcite TCNet Fusion (SE TCNet Fusion). EEGNex is an improved version of the famous EEGNet.…”

Section: Proposed Modelmentioning

confidence: 99%

“…Four points were considered during the design process of EEGNex: (1) strengthening the network spatial feature extraction by adding additional 2D Conv layer [20], (2) reinforcing the temporal features learning ability by replacing separable convolution with a 2D Conv layer (3), inverted bottleneck architecture based on recent design recommendations [28], (4) and reduced number of activation functions and added dilations in the later Conv layers [29]. These modifications proved to have a positive impact on the network's performance as outlined in [22]. TCNet Fusion on the other hand consists of two main blocks; the first is an EEGNet feature extractor followed by a TCN.…”

Section: Proposed Modelmentioning

confidence: 99%

“…Many researchers in the field were inspired by the success of EEGNet, leading to the proposal of several models and improved versions of EEGNet soon after. For instance, EEGNex [22] is a recent 2D CNN model that applied four carefully examined modifications on the EEGNet model that proved to significantly improve the classification accuracy on several EEG datasets. Other models, such as TCNet-Fusion, incorporate a temporal convolutional network (TCN), which is a recent variant of CNN, designed specifically for time-series classification [23].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

An ensemble deep-learning approach for single-trial EEG classification of vibration intensity

Alsuradi,

Park,

Eid

2023

J. Neural Eng.

View full text Add to dashboard Cite

Objective. Single-trial electroencephalography (EEG) classification is a promising approach to evaluate the cognitive experience associated with haptic feedback. Convolutional neural networks (CNNs), which are among the most widely used deep learning techniques, have demonstrated their effectiveness in extracting EEG features for the classification of different cognitive functions, including the perception of vibration intensity that is often experienced during human-computer interaction. This paper proposes a novel CNN ensemble model to classify the vibration-intensity from a single trial EEG data that outperforms the state-of-the-art EEG models. Approach. The proposed ensemble model, named SE NexFusion, builds upon the observed complementary learning behaviors of the EEGNex and TCNet Fusion models, exhibited in learning personal as well generic neural features associated with vibration intensity. The proposed ensemble employs multi-branch feature encoders corroborated with squeeze-and-excitation units that enables rich-feature encoding while at the same time recalibrating the weightage of the obtained feature maps based on their discriminative power. The model takes in a single trial of raw EEG as an input and does not require complex EEG signal-preprocessing. Main results. The proposed model outperforms several state-of-the-art bench-marked EEG models by achieving an average accuracy of 60.7 % and 61.6 % under leave-one-subject-out and within-subject cross-validation (three-classes), respectively. We further validate the robustness of the model through Shapley values explainability method, where the most influential spatio-temporal features of the model are counter-checked with the neural correlates that encode vibration intensity. Significance. Results show that SE NexFusion outperforms other benchmarked EEG models in classifying the vibration intensity. Additionally, explainability analysis confirms the robustness of the model in attending to features associated with the neural correlates of vibration intensity.

show abstract

“…For instance, FBCNet and FBMSNet both implement temporal-spatial convolution to filtered EEG data [17] [18]. A recent benchmark network, namely, EEGNeX, is a pure convolution-based architecture derived from analogy investigations between the EEG and neural network architecture [19]. Besides, Altaheri et al proposed attention-based temporal convolutional network ATCNet and D-ATCNet and validated them on BCI competition IV 2a dataset [20] [21].…”

mentioning

confidence: 99%

A Multi-Domain Convolutional Neural Network for EEG-Based Motor Imagery Decoding

Zhi,

Yu,

et al. 2023

IEEE Trans. Neural Syst. Rehabil. Eng.

View full text Add to dashboard Cite

Motor imagery (MI) decoding plays a crucial role in the advancement of electroencephalography (EEG)-based braincomputer interface (BCI) technology. Currently, most researches focus on complex deep learning structures for MI decoding. The growing complexity of networks may result in overfitting and lead to inaccurate decoding outcomes due to the redundant information. To address this limitation and make full use of the multi-domain EEG features, a multi-domain temporal-spatialfrequency convolutional neural network (TSFCNet) is proposed for MI decoding. The proposed network provides a novel mechanism that utilize the spatial and temporal EEG features combined with frequency and time-frequency characteristics. This network enables powerful feature extraction without complicated network structure. Specifically, the TSFCNet first employs the MixConv-Residual block to extract multiscale temporal features from multi-band filtered EEG data. Next, the temporal-spatial-frequency convolution block implements three shallow, parallel and independent convolutional operations in spatial, frequency and time-frequency domain, and captures high discriminative representations from these domains respectively. Finally, these features are effectively aggregated by average pooling layers and variance layers, and the network is trained with the joint supervision of the cross-entropy and the center loss. Our experimental results show that the TSFCNet outperforms the state-of-the-art models with superior classification accuracy and kappa values (82.72% and 0.7695 for dataset BCI competition IV 2a, 86.39% and 0.7324 for dataset BCI competition IV 2b). These competitive results demonstrate that the proposed network is promising for enhancing the decoding performance of MI BCIs.

show abstract

Toward reliable signals decoding for electroencephalogram: A benchmark study to EEGNeX

Cited by 3 publications

References 32 publications

Individual-finger motor imagery classification: a data-driven approach with Shapley-informed augmentation

Individual-finger motor imagery classification: a data-driven approach with Shapley-informed augmentation

An ensemble deep-learning approach for single-trial EEG classification of vibration intensity

A Multi-Domain Convolutional Neural Network for EEG-Based Motor Imagery Decoding

Contact Info

Product

Resources

About