Cauchy non-convex sparse feature selection method for the high-dimensional small-sample problem in motor imagery EEG decoding

The time, frequency, and space information of electroencephalogram (EEG) signals is crucial for motor imagery decoding. However, these temporal-frequency-spatial features are high-dimensional small-sample data, which poses significant challenges for motor imagery decoding. Sparse regularization is a...

Full description

Saved in:
Bibliographic Details
Published in:Frontiers in neuroscience Vol. 17; p. 1292724
Main Authors: Zhang, Shaorong, Wang, Qihui, Zhang, Benxin, Liang, Zhen, Zhang, Li, Li, Linling, Huang, Gan, Zhang, Zhiguo, Feng, Bao, Yu, Tianyou
Format: Journal Article
Language:English
Published: Lausanne Frontiers Research Foundation 03.11.2023
Frontiers Media S.A
Subjects:
Classification
Datasets
Deep learning
EEG
EEG decoding
Electroencephalography
Feature selection
Frequency dependence
high-dimensional small-sample
Mental task performance
motor imagery
Motor task performance
nonconvex regularization
Regularization methods
Signal processing
Sparsity
ISSN:1662-453X, 1662-4548, 1662-453X
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The time, frequency, and space information of electroencephalogram (EEG) signals is crucial for motor imagery decoding. However, these temporal-frequency-spatial features are high-dimensional small-sample data, which poses significant challenges for motor imagery decoding. Sparse regularization is an effective method for addressing this issue. However, the most commonly employed sparse regularization models in motor imagery decoding, such as the least absolute shrinkage and selection operator (LASSO), is a biased estimation method and leads to the loss of target feature information. In this paper, we propose a non-convex sparse regularization model that employs the Cauchy function. By designing a proximal gradient algorithm, our proposed model achieves closer-to-unbiased estimation than existing models. Therefore, it can learn more accurate, discriminative, and effective feature information. Additionally, the proposed method can perform feature selection and classification simultaneously, without requiring additional classifiers. We conducted experiments on two publicly available motor imagery EEG datasets. The proposed method achieved an average classification accuracy of 82.98% and 64.45% in subjectdependent and subject-independent decoding assessment methods, respectively. The experimental results show that the proposed method can significantly improve the performance of motor imagery decoding, with better classification performance than existing feature selection and deep learning methods. Furthermore, the proposed model shows better generalization capability, with parameter consistency over different datasets and robust classification across different training sample sizes. Compared with existing sparse regularization methods, the proposed method converges faster, and with shorter model training time.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:1662-453X
1662-4548
1662-453X
DOI:10.3389/fnins.2023.1292724