Spectrum-Weighted Tensor Discriminant Analysis for Motor Imagery-Based BCI

Abstract

Spatio-temporal filtering has been widely used for extracting discriminative features in the motor imagery-based brain-computer interface (MI-BCI). In order to obtain high performance, the algorithms need to enhance robustness or find class-discriminative bands for the spatial filter. However, the existing methods either cannot derive the spatial and spectral filters with a unique objective function for guaranteeing convergence or rarely consider the combined optimization of spatial-spectral filters and other patterns for enhancing the discrimination. In this study, we present a novel feature extraction method termed Spectrum-weighted Tensor Discriminant Analysis (SwTDA), which optimizes spectral filters along with spatial filters and other associated patterns by tensor-based discriminant analysis. The proposed method considers intrinsic spatial-spectral-temporal information contained by the physiological signal and hence can identify discriminative characteristics robustly. The effectiveness of the algorithm is demonstrated by comparing it with several state-of-the-art methods on two datasets involving 15 different subjects. Results indicate that the SwTDA method yields higher classification accuracies than the competing methods. Furthermore, interpretable spatial-spectral patterns that are determined by the algorithm can be used for further analysis of the MI-based EEG signal. INDEX TERMS Brain computer interface (BCI), spatio-spectral filter, tensor-based discriminant analysis, motor imagery. TONG WANG (Member, IEEE) received the B.Eng. degree in electrical engineering and automation from the Beijing University of Aeronautics and Astronautics (now Beihang University), Beijing, China, in 2006, and the M.Sc. degree (Hons.) in communications engineering and the Ph.D. degree in electronic engineering from the

Cross-Task Mental Workload Recognition Based on EEG Tensor Representation and Transfer Learning

“…Since multiple brain regions were involved and these regions worked collaboratively in a dynamic way when the brain is processing information, the structural characteristics of the EEG signals between different dimensions (such as time, frequency, channel, etc.) would be ignored, which result in the loss of useful information in distinguishing mental workload levels [25], [26], [27]. Various studies demonstrated that the multi-dimension information of EEG signals is sensitive to the level of mental workload [6], [16], [28].…”

“…Tensor is a representation of high-dimensional information of data, which has been widely used in the fields of gait recognition [29], image recognition [30] and so on. The intrinsic attributes of EEG data can be effectively retained by the tensorized form of representation [25], [26], [27]. In the field of brain- computer interface, Li [31] and Zhang [32] proposed EEG tensor features construction methods in decoding subjects' motion intentions in motor imagery tasks.…”

Single-Trial Kernel-Based Functional Connectivity for Enhanced Feature Extraction in Motor-Related Tasks

“…In particular, BCI faces real-world challenges, which are mostly caused by the low spatial resolution of EEG that, along with the nonstationarity present in the recorded neurophysiological signals, results in a poor signal-to-noise ratio (SNR). To enhance SNR, a regular pipeline of MI/ME processing involves the feature extraction stage using spatial filtering to increase mental states' discriminability, for which several methods are reported, like Riemannian geometry-based algorithm [12], 1 -norm unsupervised Fukunaga-Koontz transform [13], Spectrum-weighted Tensor Discriminant Analysis [14], Bayesian spatio-spectral filter optimization [15], and common spatial patterns (CSP), which maximize the variance of one class to another [16], among others. Although CSP is the most widely employed algorithm, several factors may hinder the extraction of highly separable features in terms of spatial patterns.…”