A wrapped time-frequency combined selection in the source domain

Cortical ROI Importance Improves MI Decoding From EEG Using Fused Light Neural Network

Decoding motor imagery (MI) using deep learning in cortical level has potential in brain computer interface based intelligent rehabilitation. However, a mass of dipoles is inconvenient to extract the personalized features and requires a more complex neural network. In consideration of the structural and functional similarity of the neurons in a neuroanatomical region, i.e., a region of interest (ROI), we propose that the comprehensive performance of each ROI may be reflected by a specific representative dipole (RD), and the time-frequency spectrums of all RDs are applied simultaneously to Random Forest algorithm to give a quantitative metric of each ROI importance (RI). Then, the more divided sub-band spectral powers are reinforced by RI, and they are interpolated to a 2-dimensional (2D) plane transformed from 3D space of all RDs, yielding an ensemble representation of RD feature image sequences (ERDFIS). Furthermore, a lightweight network, including 2D separable convolution and gated recurrent unit (2DSCG), is developed to extract and classify the frequency-spatial and temporal features from ERDFIS, forming a novel MI decoding method in cortical level (called ERDFIS-2DSCG). Based on two public datasets, the decoding accuracies of ten-fold cross-validation are 89.89% and 94.35%, respectively. The results suggest that RD can embody the overall property of ROI in time-frequency-space domains, and ROI importance is helpful to highlight the subject-based characteristics of MI-EEG. Meanwhile, 2DSCG is matched well with ERDFIS, jointly improving the decoding performance.

Exploiting pretrained CNN models for the development of an EEG-based robust BCI framework

Identifying motor and mental imagery electroencephalography (EEG) signals is imperative to realizing automated, robust brain-computer interface (BCI) systems. In the present study, we proposed a pretrained convolutional neural network (CNN)-based new automated framework feasible for robust BCI systems with small and ample samples of motor and mental imagery EEG training data. The framework is explored by investigating the implications of different limiting factors, such as learning rates and optimizers, processed versus unprocessed scalograms, and features derived from untuned pretrained models in small, medium, and large pretrained CNN models. The experiments were performed on three public datasets obtained from BCI Competition III. The datasets were denoised with multiscale principal component analysis, and time-frequency scalograms were obtained by employing a continuous wavelet transform. The scalograms were fed into several variants of ten pretrained models for feature extraction and identification of different EEG tasks. The experimental results showed that ShuffleNet yielded the maximum average classification accuracy of 99.52% using an RMSProp optimizer with a learning rate of 0.000 1. It was observed that low learning rates converge to more optimal performances compared to high learning rates. Moreover, noisy scalograms and features extracted from untuned networks resulted in slightly lower performance than denoised scalograms and tuned networks, respectively. The overall results suggest that pretrained models are robust when identifying EEG signals because of their ability to preserve the time-frequency structure of EEG signals and promising classification outcomes.

Optimal channel-based sparse time-frequency blocks common spatial pattern feature extraction method for motor imagery classification

Common spatial pattern (CSP) as a spatial filtering method has been most widely applied to electroencephalogram (EEG) feature extraction to classify motor imagery (MI) in brain-computer interface (BCI) applications. The effectiveness of CSP is determined by the quality of interception in a specific time window and frequency band. Although numerous algorithms have been designed to optimize CSP by splitting the EEG data with a sliding time window and dividing the frequency bands with a set of band-pass filters, simultaneously. However, they did not consider the drawbacks of the rapid increase in data volume and feature dimensions brought about by this method, which would reduce the classification accuracy and calculation efficiency of the model. Therefore, we propose an optimal channel-based sparse time-frequency blocks common spatial pattern (OCSB-CSP) feature extraction method to improve the model classification accuracy and computational efficiency. Comparative experiments on two public EEG datasets show that the proposed method can quickly select significant time-frequency blocks and improve classification performance. The average classification accuracies are higher than those of other winners' methods, providing a new idea for the improvement of BCI applications.