PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
February 12, 2026Sensors0 citationsOpen Access

Enhanced EEG Emotion Recognition Using MIMO-Based Denoising and Band-Wise Attention Graph Neural Network

View Full Paper
YJYujin JiDKDo-Hyung KimJHJungpyo Hong

Key Result

The NR-BA-BFE-Net model incorporating MIMO noise reduction and band-wise attention improved emotion recognition accuracy by 3.27% over BFE-Net (95.56% vs 92.29%) in subject-independent EEG emotion classification on the SEED dataset (p=0.032).

Key Points

  • This research aims to improve emotion recognition accuracy using EEG signals by addressing noise issues and feature extraction limitations.
  • Implemented MIMO-based preprocessing for noise reduction.
  • Utilized multichannel minima-controlled recursive averaging for noise covariance estimation.
  • Proposed an attention-based mechanism for dynamic band aggregation and feature fusion.
  • Conducted experiments on the SEED and SEED-IV datasets with a subject-independent protocol.
  • Achieved a 3.27% improvement over the SOTA BFE-Net on the SEED dataset.
  • Achieved a 3.34% improvement over the SOTA BFE-Net on the SEED-IV dataset.
  • Confirmed that MIMO noise reduction and frequency-centric attention significantly enhance BCI reliability and generalization.

Structured PICO

P
Population
EEG data from the SEED and SEED-IV datasets for emotion recognition
I
Intervention
Noise-robust band-attention BFE-Net framework (MIMO-based preprocessing and attention-based band aggregation mechanism)
C
Comparator
State-of-the-art (SOTA) Band Feature Extraction Neural Network (BFE-Net)
O
Outcome
Emotion recognition performance (accuracy)

A novel noise-robust band-attention BFE-Net framework improves EEG-based emotion recognition accuracy compared to state-of-the-art methods.

Main Result

Effect estimate: 3.27% absolute improvement in accuracy vs BFE-Net

Absolute Event Rate: 95.56% vs 92.29%

p-value: p=0.032

Limitations

  • Absence of clean ground-truth EEG signals limits quantitative evaluation of noise reduction efficacy such as SNR increase.
  • Study population limited to young adults with narrow age range and 15 subjects.
  • No randomized controlled clinical trial design, limiting clinical evidence generalization.
  • Focus on algorithmic performance rather than clinical endpoints or patient outcomes.

Abstract

Electroencephalogram (EEG) signals serve as a primary input for brain–computer interface (BCI) systems, and extensive research has been conducted on EEG-based emotion recognition. However, because EEG signals are inherently contaminated with various types of noise, the performance of emotion recognition is often degraded. Furthermore, the use of a Band Feature Extraction Neural Network (BFE-Net), a state-of-the-art (SOTA) method in this field, has limitations with respect to independent band-wise feature extraction and a simplistic band aggregation process to obtain final classification results. To address these problems, this study proposes the noise-robust band-attention BFE-Net framework, aiming to improve the conventional BFE-Net from two perspectives. First, we implement multiple-input, multiple-output (MIMO)-based preprocessing. Specifically, we utilize multichannel minima-controlled recursive averaging for precise non-stationary noise covariance estimation and generalized eigenvalue decomposition for subspace filtering to enhance the signal-to-noise ratio. Second, we propose an attention-based band aggregation mechanism. By integrating a band-wise self-attention mechanism, the model learns dynamic inter-band dependencies for more sophisticated feature fusion for classification. Experimental results on the SEED and SEED-IV datasets under a subject-independent protocol show that our model outperforms the SOTA BFE-Net by 3.27% and 3.34%, respectively. This confirms that rigorous MIMO noise reduction, combined with frequency-centric attention, significantly enhances the reliability and generalization of BCI systems.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Ji et al. (2026) studied Young adults (average age 23.27 years, 7 males and 8 females) undergoing EEG-based emotion recognition with multichannel EEG capturing emotional states induced by video clips (n=15). NR-BA-BFE-Net (Noise-Robust Band-Attention BFE-Net) incorporating MIMO noise reduction and band-wise self-attention feature fusion vs. State-of-the-art models including BFE-Net, SVM, DAMGCN, DGCNN, RGNN, TANN, BiHDM, GMSS, SOGNN and variants without noise reduction or attention was evaluated on Classification accuracy of EEG-based emotion recognition under subject-independent protocol (3.27% absolute improvement in accuracy vs BFE-Net, p=0.032). The NR-BA-BFE-Net model incorporating MIMO noise reduction and band-wise attention improved emotion recognition accuracy by 3.27% over BFE-Net (95.56% vs 92.29%) in subject-independent EEG emotion classification on the SEED dataset (p=0.032).

synapsesocial.com/papers/698d6dd15be6419ac0d5300dhttps://doi.org/10.3390/s26041133
Ask AI
Helpful
Bookmark
Share
View Full Paper