Investigating the Impact of Rational Dilated Wavelet Transform on Motor Imagery EEG Decoding with Deep Learning Models

2025-10-10

AI Summary

This study addresses the challenge of decoding motor imagery electroencephalography (EEG) signals—characterized by nonstationarity and low signal-to-noise ratio—by proposing the rational discrete wavelet transform (RDWT) as a lightweight, structure-aware preprocessing method. RDWT enhances rhythm-specific discriminative features while suppressing localized noise. We systematically evaluate its integration with four state-of-the-art deep learning models—EEGNet, ShallowConvNet, MBEEG_SENet, and EEGTCNet—on benchmark datasets including BCI-IV-2a. Results demonstrate that RDWT significantly improves model robustness and consistency across architectures: it yields +4.44% and +2.23% absolute classification accuracy gains on EEGTCNet and MBEEG_SENet, respectively. These improvements confirm RDWT’s effectiveness as a low-computational-cost preprocessing module, exhibiting strong generalizability across diverse deep EEG decoders.

Technology Category

• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Machine Learning: Deep Generative Models & Autoencoders
• Intelligent Robots: State Estimation

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Web Mining and Content Analysis: Large pretrained models with web data
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

Abstract

The present study investigates the impact of the Rational Discrete Wavelet Transform (RDWT), used as a plug-in preprocessing step for motor imagery electroencephalographic (EEG) decoding prior to applying deep learning classifiers. A systematic paired evaluation (with/without RDWT) is conducted on four state-of-the-art deep learning architectures: EEGNet, ShallowConvNet, MBEEG_SENet, and EEGTCNet. This evaluation was carried out across three benchmark datasets: High Gamma, BCI-IV-2a, and BCI-IV-2b. The performance of the RDWT is reported with subject-wise averages using accuracy and Cohen's kappa, complemented by subject-level analyses to identify when RDWT is beneficial. On BCI-IV-2a, RDWT yields clear average gains for EEGTCNet (+4.44 percentage points, pp; kappa +0.059) and MBEEG_SENet (+2.23 pp; +0.030), with smaller improvements for EEGNet (+2.08 pp; +0.027) and ShallowConvNet (+0.58 pp; +0.008). On BCI-IV-2b, the enhancements observed are modest yet consistent for EEGNet (+0.21 pp; +0.044) and EEGTCNet (+0.28 pp; +0.077). On HGD, average effects are modest to positive, with the most significant gain observed for MBEEG_SENet (+1.65 pp; +0.022), followed by EEGNet (+0.76 pp; +0.010) and EEGTCNet (+0.54 pp; +0.008). Inspection of the subject material reveals significant enhancements in challenging recordings (e.g., non-stationary sessions), indicating that RDWT can mitigate localized noise and enhance rhythm-specific information. In conclusion, RDWT is shown to be a low-overhead, architecture-aware preprocessing technique that can yield tangible gains in accuracy and agreement for deep model families and challenging subjects.

Problem

• Evaluating RDWT's impact on EEG decoding using deep learning models
• Assessing performance gains across multiple datasets and neural architectures
• Investigating noise reduction and rhythm enhancement in motor imagery EEG

Innovation

• RDWT preprocessing boosts EEG decoding accuracy
• Plug-in RDWT enhances deep learning EEG classifiers
• RDWT mitigates noise in motor imagery EEG data