Sparse Time-Varying Modeling and Time-Frequency Representation of EEG Data Using Scale-Adaptive Multiwavelet

ZHENG Nan; LI Yu-rong; SHI Wu-xiang; TAN Ji-yu; CHEN Wen-sheng

doi:10.12263/DZXB.20250180

您当前的位置：

首页 >

文章列表页 >

Sparse Time-Varying Modeling and Time-Frequency Representation of EEG Data Using Scale-Adaptive Multiwavelet

PAPERS | 更新时间：2025-12-27

- Sparse Time-Varying Modeling and Time-Frequency Representation of EEG Data Using Scale-Adaptive Multiwavelet
- ACTA ELECTRONICA SINICA Vol. 53, Issue 8, Pages: 2707-2718(2025)
- 作者机构：
  
  1.福州大学电气工程与自动化学院，福建福州 350108
  2.福建省医疗器械和医药技术重点实验室，福建福州 350108
- 作者简介：
- 基金信息：
  
  National Natural Science Foundation of China(62373108)
- DOI：10.12263/DZXB.20250180
  CLC： TP391;
- Received：11 March 2025，
  
  Accepted：01 August 2025，
  
  Published：25 August 2025
- 稿件说明：
移动端阅览
郑楠, 李玉榕, 史武翔, 等. 尺度自适应的多小波脑电稀疏时变建模与时频表征方法[J]. 电子学报, 2025, 53(08): 2707-2718.

ZHENG Nan, LI Yu-rong, SHI Wu-xiang, et al. Sparse Time-Varying Modeling and Time-Frequency Representation of EEG Data Using Scale-Adaptive Multiwavelet[J]. Acta Electronica Sinica, 2025, 53(08): 2707-2718.
郑楠, 李玉榕, 史武翔, 等. 尺度自适应的多小波脑电稀疏时变建模与时频表征方法[J]. 电子学报, 2025, 53(08): 2707-2718. DOI：10.12263/DZXB.20250180

ZHENG Nan, LI Yu-rong, SHI Wu-xiang, et al. Sparse Time-Varying Modeling and Time-Frequency Representation of EEG Data Using Scale-Adaptive Multiwavelet[J]. Acta Electronica Sinica, 2025, 53(08): 2707-2718. DOI：10.12263/DZXB.20250180

摘要

时频表征的准确性直接影响脑电信号内在含义和动态特性的解析.针对基于多小波的时频表征方法中存在的尺度固定、回归项选择不当等问题，本文提出一种基于尺度自适应稀疏多小波的时频表征框架，以提升表征精度.该方法通过稀疏贝叶斯学习-信息熵联合优化，从全局角度筛选时变模型的最优回归项，有效规避传统方法的局部收敛缺陷；进一步，为小波基分配尺度，从最优个体、粒子群变异和种群更新3个方面改进遗传算法并进行尺度寻优，实现小波基与最优尺度的自适应匹配，增强多小波基对时变信号的拟合能力.最终，估计的时变参数经由参数谱估计转化为准确的时频表征.在3个仿真模型的实验结果表明，所提方法至少降低23.08%的时变参数估计误差，增强2.93%的时频信息估计精度，在动态参数跟踪和时频信息估计上展现出强大竞争力.在BCI Competition II-data set III的实验结果显示，所提方法在估计事件相关同步/去同步的性能较先进时变建模方法增强（3.37→8.78）；进一步将所提方法提取的时频信息与简单卷积神经网络结合，即可在BCI Competition IV-data set 2b中取得与最先进但复杂的分类模型相当的识别准确率（88.04%），侧面证实了所提方法的时频表征能力.本文方法从模型结构筛选、寻优算法改进和基函数尺度配置3个方面进行设计，实现时变参数估计准确率与时频分辨率的协同提升，为脑电信号处理提供了一种新方法.

Abstract

The accuracy of time-frequency representation directly influences the interpretation of the intrinsic dynamics and functional significance of electroencephalogram (EEG) signals. To address the limitations of fixed scales and suboptimal regression term selection in existing multi-wavelet-based methods

this paper proposes a novel time-frequency representation framework based on scale-adaptive sparse multi-wavelets. This method adopts a joint sparse Bayesian learning and information entropy optimization framework to globally identify the optimal regression terms of the time-varying model

effectively avoiding the local convergence issues of traditional approaches. Furthermore

scales are allocated to the wavelet basis. The genetic algorithm is enhanced in three key aspects—optimal individual selection

particle swarm mutation

and population update—to optimize the scale. This achieves adaptive matching between the wavelet basis and the optimal scale

thus enhancing the fitting capability of multiple wavelet bases for time-varying signals. Ultimately

the estimated time-varying parameters are transformed into accurate time-frequency representations through parameter spectral estimation. Experiments on three simulation models show at least a 23.08% reduction in parameter estimation error and a 2.93% improvement in time-frequency resolution. Compared to state-of-the-art algorithms

it shows strong competitiveness in tracking time-varying parameters and extracting time-frequency features. On BCI Competition II-data set III

our method enhances event-related desynchronization/event-related synchronization detection

with performance improving from 3.37 to 8.78. When combined with a simple convolutional neural network

it achieves 88.04% recognition accuracy on the BCI Competition IV-dataset 2b—comparable to that of more complex state-of-the-art models—thereby indirectly validating its effectiveness in time-frequency representation. Our method is designed from three perspectives: model structure optimization

algorithm enhancement

and basis function scaling. The collaborative improvement of time-varying parameter estimation and time-frequency resolution is successfully achieved

offering a novel methodology for EEG signal.

关键词

Keywords

references

ZHENG N , LI Y R , SHI W X , et al . Sparse Bayesian based NARX modeling of cortical response: Introducing information entropy for enhancing the stability [J ] . Neurocomputing , 2025 , 626 : 129569 .

康冉斓 , 李玉榕 , 史武翔 , 等 . 基于Dempster-Shafer证据推理的EEG-fNIRS运动想象分类决策层融合方法 [J ] . 电子学报 , 2025 , 53 ( 3 ): 941 - 950 .

KANG R L , LI Y R , SHI W X , et al . Decision-level fusion of EEG-fNIRS for motor imagery classification based on dempster-shafer evidence reasoning [J ] . Acta Electronica Sinica , 2025 , 53 ( 3 ): 941 - 950 . (in Chinese)

CAI N Q , SHI W X , CHEN R K , et al . Cerebral-cerebellar cortical activity and connectivity underlying sensory trick in cervical dystonia [J ] . Annals of Clinical and Translational Neurology , 2024 , 11 ( 10 ): 2633 - 2644 .

LIU Z F , WANG L N , XU S , et al . A multiwavelet-based sparse time-varying autoregressive modeling for motor imagery EEG classification [J ] . Computers in Biology and Medicine , 2023 , 155 : 106196 .

MI Y J , LIN A J . Spectral time-varying pattern causality and its application [J ] . IEEE Journal of Biomedical and Health Informatics , 2024 , 28 ( 6 ): 3742 - 3749 .

TANG B W , DING Y P , PENG Y Q , et al . Target localization algorithm based on improved short-time Fourier transform [J ] . Digital Signal Processing , 2024 , 155 : 104734 .

ZHAO H F , GUI L . Nonparametric and parametric methods of spectral analysis [J ] . MATEC Web of Conferences , 2019 , 283 : 07002 .

LI Y , LIU Q , TAN S R , et al . High-resolution time-frequency analysis of EEG signals using multiscale radial basis functions [J ] . Neurocomputing , 2016 , 195 : 96 - 103 .

LI Y , CUI W G , HUANG H , et al . Epileptic seizure detection in EEG signals using sparse multiscale radial basis function networks and the Fisher vector approach [J ] . Knowledge-Based Systems , 2019 , 164 : 96 - 106 .

ZHENG N , LI Y R . Adaptive radial basis functions based time-varying model for EEG analysis in patients with cervical dystonia [J ] . Biomedical Signal Processing and Control , 2024 , 92 : 106135 .

XU S , LI Y , HUANG T W , et al . A sparse multiwavelet-based generalized laguerre-Volterra model for identifying time-varying neural dynamics from spiking activities [J ] . Entropy , 2017 , 19 ( 8 ): 425 .

WANG Q H , WEI H L , WANG L N , et al . A novel time-varying modeling and signal processing approach for epileptic seizure detection and classification [J ] . Neural Computing and Applications , 2021 , 33 ( 11 ): 5525 - 5541 .

LI Y , CUI W G , LUO M L , et al . High-resolution time-frequency representation of EEG data using multi-scale wavelets [J ] . International Journal of Systems Science , 2017 , 48 ( 12 ): 2658 - 2668 .

LIU Z P , TANG X Q , WANG X F , et al . Wind turbine blade bearing fault diagnosis under fluctuating speed operations via Bayesian augmented Lagrangian analysis [J ] . IEEE Transactions on Industrial Informatics , 2021 , 17 ( 7 ): 4613 - 4623 .

CHEN S , HONG X , KHALAF E F , et al . Comparative performance of complex-valued B-spline and polynomial models applied to iterative frequency-domain decision feedback equalization of Hammerstein channels [J ] . IEEE Transactions on Neural Networks and Learning Systems , 2017 , 28 ( 12 ): 2872 - 2884 .

ZHANG Z G . Spectral and time-frequency analysis [M ] // EEG Signal Processing and Feature Extraction . Singapore : Springer Singapore , 2019 : 89 - 116 .

SHARMA R , MEENA H K . Emerging trends in EEG signal processing: A systematic review [J ] . SN Computer Science , 2024 , 5 ( 4 ): 415 .

SOLLFRANK T , KOHNEN O , HILFIKER P , et al . The effects of dynamic and static emotional facial expressions of humans and their avatars on the EEG: An ERP and ERD/ERS study [J ] . Frontiers in Neuroscience , 2021 , 15 : 651044 .

BLANKERTZ B , MÜLLER K R , CURIO G , et al . The BCI competition 2003: Progress and perspectives in detection and discrimination of EEG single trials [J ] . IEEE Transactions on Bio-Medical Engineering , 2004 , 51 ( 6 ): 1044 - 1051 .

LEEB R , BRUNNER C , MÜLLER-PUTZ G , et al . BCI competition 2008-Graz data set B [J ] . Graz University of Technology , 2008 , 16 : 1 - 6 .

YAACOUB C , MHANNA G , RIHANA S . A genetic-based feature selection approach in the identification of left/right hand motor imagery for a brain-computer interface [J ] . Brain Sciences , 2017 , 7 ( 1 ): 12 .

KIM J , PARK Y , CHUNG W . Transform based feature construction utilizing magnitude and phase for convolutional neural network in EEG signal classification [C ] // 2020 8th International Winter Conference on Brain-Computer Interface . Piscataway : IEEE , 2020 : 1 - 4 .

ZHAO W , ZHANG B C , ZHOU H F , et al . Multi-scale convolutional transformer network for motor imagery brain-computer interface [J ] . Scientific Reports , 2025 , 15 : 12935 .

ARI E , TAÇGIN E . NF-EEG: A generalized CNN model for multi class EEG motor imagery classification without signal preprocessing for brain computer interfaces [J ] . Biomedical Signal Processing and Control , 2024 , 92 : 106081 .

YAN W D , LIU J Y , LUO J , et al . A temporal-spatial embedding and dynamic aggregation network with adaptive weighting spectrum for EEG motion intention recognition [J ] . IEEE Transactions on Instrumentation and Measurement , 2025 , 74 : 4007611 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Radar Signal Modulation Recognition Based on Split EfficientNet Under Low Signal-to-Noise Ratio

A Brain Functional Network Based on Continuous Wavelet Transform and Symbolic Transfer Entropy

A Space-Frequency Block Code Recognition Based on Deep Multilevel Residual Network with Low SNR

A Time-frequency Analysis Method Based on Linear Canonical Transform and Short-time Fourier Transform

Related Author

LI Qin

LIU Wei

NIU Chao-yang

BAO Yin-tu

HUI Zhou-bo

LI Ming-ai

ZHANG Yuan-yuan

ZHANG Yu-yuan

Related Institution

PLA Strategic Support Force Information Engineering University

Beijing Key Laboratory of Computational Intelligence and Intelligent System

Engineering Research Center of Digital Community（Ministry of Education）

Faculty of Information Technology, Beijing University of Technology

Department of Information Fusion, Naval Astronautical University

⁰