ST-CapsNet: Linking Spatial and Temporal Attention With Capsule Network for P300 Detection Improvement

Wang, Zehui; Chen, Chuangquan; Li, Junhua; Wan, Feng; Sun, Yu; Wang, Hongtao

doi:10.1109/tnsre.2023.3237319

Cited by 17 publications

(9 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Lawhern et al [27] developed EEGNet, a compact CNN-based DNN that can analyze and classify brain signals from various mental activities. Additionally, there have been improved versions of EEGNet, such as the one by Zhang et al [28] for detecting single-trial P300 signals, as well as new DNN architectures like ST-CapsNet [29], which integrates spatial and temporal attentions using a capsule network for P300 detection, and a CNN-based approach by Du et al [30] that classifies single-trial P300 signals by fusing data from multiple subjects.…”

Section: Introductionmentioning

confidence: 99%

Improving the performance of P300-based BCIs by mitigating the effects of stimuli-related evoked potentials through regularized spatial filtering

Mobaien,

Boostani,

Sanei

2024

J. Neural Eng.

View full text Add to dashboard Cite

Objective:The P300-based brain-computer interfaces (BCIs) typically employ a visual oddball paradigm, where different objects (linked to specific commands) are randomly and frequently intensified. Upon observing the target object, users experience a elicitation of a P300 event-related potential in their electroencephalography (EEG). However, detecting the P300 signal can be challenging due to its very low signal-to-noise ratio (SNR), often compromised by the sequence of visual evoked potentials (VEPs) generated in the occipital regions of the brain in response to periodic visual stimuli. The main objective of this study is to investigate how visual evoked potentials (VEPs) impact P300-based BCIs. Subsequently, the study aims to propose a method for EEG spatial filtering to alleviate the effect of VEPs and enhance the overall performance of these BCIs.Approach:Our approach entails analyzing recorded EEG signals from visual P300-based BCIs through temporal, spectral, and spatial analysis techniques to identify the impact of VEPs. Subsequently, we introduce a regularized version of the xDAWN algorithm, a well-established spatial filter known for enhancing single-trial P300s. This aims to simultaneously enhance P300 signals and suppress VEPs, contributing to an improved overall signal quality.Main results:Analyzing EEG signals shows that VEPs can significantly contaminate P300 signals, resulting in a decrease in the overall performance of P300-based BCIs. However, our proposed method for simultaneous enhancement of P300 and suppression of VEPs has demonstrated improved performance in P300-based BCIs. This improvement has been verified through several experiments conducted with real P300 data.Significance:This study focuses on the effects of VEPs on the performance of P300-based BCIs, a problem that has not been adequately addressed in previous studies. It opens up a new path for investigating these BCIs. Moreover, the proposed spatial filtering technique has the potential to further enhance the performance of these systems.

show abstract

Section: Introductionmentioning

confidence: 99%

Improving the performance of P300-based BCIs by mitigating the effects of stimuli-related evoked potentials through regularized spatial filtering

Mobaien,

Boostani,

Sanei

2024

J. Neural Eng.

View full text Add to dashboard Cite

show abstract

“…In EEG-BCIs, signals can be classified into evoked and spontaneous types. Evoked EEG involves triggering specific brain responses through external stimuli, such as P300 [20][21][22][23] and Steady-State Visual Evoked Potentials (SSVEPs) [24][25][26][27][28][29]. While extensively studied in BCI systems, P300 is susceptible to interference and prolonged fixation on light sources, while SSVEPs may lead to visual fatigue.…”

Section: Introductionmentioning

confidence: 99%

Decoding Subject-Driven Cognitive States from EEG Signals for Cognitive Brain–Computer Interface

Huang,

Wang,

Fan

et al. 2024

Brain Sciences

View full text Add to dashboard Cite

In this study, we investigated the feasibility of using electroencephalogram (EEG) signals to differentiate between four distinct subject-driven cognitive states: resting state, narrative memory, music, and subtraction tasks. EEG data were collected from seven healthy male participants while performing these cognitive tasks, and the raw EEG signals were transformed into time–frequency maps using continuous wavelet transform. Based on these time–frequency maps, we developed a convolutional neural network model (TF-CNN-CFA) with a channel and frequency attention mechanism to automatically distinguish between these cognitive states. The experimental results demonstrated that the model achieved an average classification accuracy of 76.14% in identifying these four cognitive states, significantly outperforming traditional EEG signal processing methods and other classical image classification algorithms. Furthermore, we investigated the impact of varying lengths of EEG signals on classification performance and found that TF-CNN-CFA demonstrates consistent performance across different window lengths, indicating its strong generalization capability. This study validates the ability of EEG to differentiate higher cognitive states, which could potentially offer a novel BCI paradigm.

show abstract

“…Macías-Macías et al ( 2022 ) introduced a capsule neural network that has shown promising P300 classification performance with small samples and few channels. Furthermore, Wang Z. et al ( 2023 ) proposed a novel method that integrates an attention module with a capsule neural network, aiming to enhance P300 classification effectiveness. Zhang et al ( 2022b ) proposed an improved EEGNet model, which enhances the signal-to-noise ratio through xDAWN filtering and addresses sample imbalance with a focal loss function.…”

Section: Introductionmentioning

confidence: 99%

“…It has achieved good performance in both offline and online data. Wang Z. et al ( 2023 ) combined techniques such as Mixup, stochastic weight averaging, label smoothing, and focal loss during the training of deep learning methods so as to improve the performance of models such as EEGNet in the cross-subject P300 classification task. The single-scale convolution used by these methods may not be able to comprehensively extract the temporal and spatial features of P300.…”

Section: Introductionmentioning

confidence: 99%

PSAEEGNet: pyramid squeeze attention mechanism-based CNN for single-trial EEG classification in RSVP task

Yuan,

Zhou,

Wang

et al. 2024

Front. Hum. Neurosci.

View full text Add to dashboard Cite

IntroductionAccurate classification of single-trial electroencephalogram (EEG) is crucial for EEG-based target image recognition in rapid serial visual presentation (RSVP) tasks. P300 is an important component of a single-trial EEG for RSVP tasks. However, single-trial EEG are usually characterized by low signal-to-noise ratio and limited sample sizes.MethodsGiven these challenges, it is necessary to optimize existing convolutional neural networks (CNNs) to improve the performance of P300 classification. The proposed CNN model called PSAEEGNet, integrates standard convolutional layers, pyramid squeeze attention (PSA) modules, and deep convolutional layers. This approach arises the extraction of temporal and spatial features of the P300 to a finer granularity level.ResultsCompared with several existing single-trial EEG classification methods for RSVP tasks, the proposed model shows significantly improved performance. The mean true positive rate for PSAEEGNet is 0.7949, and the mean area under the receiver operating characteristic curve (AUC) is 0.9341 (p < 0.05).DiscussionThese results suggest that the proposed model effectively extracts features from both temporal and spatial dimensions of P300, leading to a more accurate classification of single-trial EEG during RSVP tasks. Therefore, this model has the potential to significantly enhance the performance of target recognition systems based on EEG, contributing to the advancement and practical implementation of target recognition in this field.

show abstract

ST-CapsNet: Linking Spatial and Temporal Attention With Capsule Network for P300 Detection Improvement

Cited by 17 publications

References 42 publications

Improving the performance of P300-based BCIs by mitigating the effects of stimuli-related evoked potentials through regularized spatial filtering

Improving the performance of P300-based BCIs by mitigating the effects of stimuli-related evoked potentials through regularized spatial filtering

Decoding Subject-Driven Cognitive States from EEG Signals for Cognitive Brain–Computer Interface

PSAEEGNet: pyramid squeeze attention mechanism-based CNN for single-trial EEG classification in RSVP task

Contact Info

Product

Resources

About