Decoding EEG in Motor Imagery Tasks with Graph Semi-Supervised Broad Learning

Abstract

In recent years, the accurate and real-time classification of electroencephalogram (EEG) signals has drawn increasing attention in the application of brain-computer interface technology (BCI). Supervised methods used to classify EEG signals have gotten satisfactory results. However, unlabeled samples are more frequent than labeled samples, so how to simultaneously utilize limited labeled samples and many unlabeled samples becomes a research hotspot. In this paper, we propose a new graph-based semi-supervised broad learning system (GSS-BLS), which combines the graph label propagation method to obtain pseudo-labels and then trains the GSS-BLS classifier together with other labeled samples. Three BCI competition datasets are used to assess the GSS-BLS approach and five comparison algorithms: BLS, ELM, HELM, LapSVM and SMIR. The experimental results show that GSS-BLS achieves satisfying Cohen’s kappa values in three datasets. GSS-BLS achieves the better results of each subject in the 2-class and 4-class datasets and has significant improvements compared with original BLS except subject C6. Therefore, the proposed GSS-BLS is an effective semi-supervised algorithm for classifying EEG signals.

A Semi-Supervised Progressive Learning Algorithm for Brain–Computer Interface

“…Semi-supervised learning aims to build suitable machine learning models to learn both labeled and unlabeled datasets, and to improve the performance of the model on both supervised and unsupervised learning tasks [33]. In the field of collaborative learning, the Squared-loss Mutual Information Regularization (SMIR) model [34], Semi-supervised Extreme Learning Machines (SS-ELM) [35] and Graph-based Semisupervised Broad Learning System (GSS-BLS) [36] utilizes the differences and similarities in model features between the labeled and unlabeled datasets to select useful information. The collaborative representation-based semi-supervised extreme learning machine (CR-SSELM) [37] uses algorithms to reconstruct the unlabeled samples based on predictions of the ELM and define the risk degree of unlabeled samples, and then the unlabeled samples with a risk-based regularization term are further added into the training process of the model.…”

A Review on Signal Processing Approaches to Reduce Calibration Time in EEG-Based Brain–Computer Interface

“…A k -nearest neighbor graph is usually included in the Laplacian matrix to define the relationship among the nearby data points ( She et al, 2019b ; Peng et al, 2020 ).…”

“…Based on the graph label propagation algorithm and the broad learning system (BLS), a graph-based semi-supervised BLS was proposed in MI-based BCI system ( She et al, 2019b ). On the one hand, the label information can be smoothed over the graph by the graph label propagation algorithm.…”

“…The proposed approach takes advantage of ELM, deep architecture, and graph-based model. A k-nearest neighbor graph is usually included in the Laplacian matrix to define the relationship among the nearby data points (She et al, 2019b;Peng et al, 2020).…”

KCS-FCnet: Kernel Cross-Spectral Functional Connectivity Network for EEG-Based Motor Imagery Classification

“…First, relevant spatial-temporal-spectral feature maps are desired to overcome overfitting due to high intra-class variability [ 24 , 25 ]. Second, more robustness in dealing with noise in the raw EEG while avoiding complex architecture is required [ 26 , 27 ]. Third, DL lacks straightforward interpretability, which is critical to validate neural activity for medical diagnosis, monitoring, and computer-aided learning [ 28 , 29 , 30 ].…”