Spiking neural networks for EEG signal analysis using wavelet transform
Спайковые нейронные сети для анализа ЭЭГ-сигналов с использованием вейвлет-преобразования
2025-10-16
SCID: 54.1/498sm3yr
Discuss with AI
EEG signal analysisauditory attention decodingdiscrete wavelet transformspiking neural networksspiking transformer
Figures from the paper
Abstract (AI)
Introduction: Brain-computer interfaces (BCIs) leverage EEG signal processing to enable human-machine communication and have broad application potential. However, existing deep learning-based BCI methods face two critical limitations that hinder their practical deployment: reliance on manual EEG feature extraction, which constrains their ability to adaptively capture complex neural patterns, and high energy consumption characteristics that make them unsuitable for resource-constrained portable BCI devices requiring edge deployment. Methods: To address these limitations, this work combines wavelet transform for automatic feature extraction with spiking neural networks for energy-efficient computation. Specifically, we present a novel spiking transformer that integrates a spiking self-attention mechanism with discrete wavelet transform, termed SpikeWavformer. SpikeWavformer enables automatic EEG signal time-frequency decomposition, eliminates manual feature extraction, and provides energy-efficient classification decision-making, thereby enhancing the model's cross-scene generalization while meeting the constraints of portable BCI applications. Results: Experimental results demonstrate the effectiveness and efficiency of SpikeWavformer in emotion recognition and auditory attention decoding tasks. Discussion: These findings indicate that SpikeWavformer can address the key limitations of existing BCI methods and holds promise for practical deployment in portable, resource-constrained scenarios.
Key Findings
1
Experiments demonstrate SpikeWavformer’s effectiveness and efficiency in emotion recognition and auditory attention decoding tasks.
2
SpikeWavformer combines spiking self-attention with discrete wavelet transform for automated EEG time-frequency decomposition.
3
Spiking neural computation provides energy-efficient classification designed for portable, resource-constrained edge BCI devices.
4
The approach is reported to enhance cross-scene generalization and support practical deployment of EEG-based BCIs.
5
The method eliminates manual EEG feature extraction while adaptively capturing complex neural patterns for BCI analysis.
Research Object
EEG signals in portable brain-computer interface applications, including emotion recognition and auditory attention decoding tasks
Research Subject
Automatic time-frequency feature extraction and energy-efficient classification of EEG signals, with cross-scene generalization under resource constraints
Publication Details
Publication Date
2025-10-16
Journal
Publisher
ISSN
Cited by
9
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest