How to successfully classify EEG in motor imagery BCI: a metrological analysis of the state of the art

Abstract

Objective. Processing strategies are analysed with respect to the classification of electroencephalographic signals related to brain-computer interfaces based on motor imagery. A review of literature is carried out to understand the achievements in motor imagery classification, the most promising trends, and the challenges in replicating these results. Main focus is placed on performance by means of a rigorous metrological analysis carried out in compliance with the international vocabulary of metrology. Hence, classification accuracy and its uncertainty are considered, as well as repeatability and reproducibility. Approach. The paper works included in the review concern the classification of electroencephalographic signals in motor-imagery- based brain-computer interfaces. Article search was carried out in accordance with the PRISMA standard and 89 studies were included. Main results. Statistically-based analyses show that brain-inspired approaches are increasingly proposed, and that these are particularly successful in discriminating against multiple classes. Notably, many proposals involve convolutional neural networks. Instead, classical machine learning approaches are still effective for binary classifications. Many proposals combine common spatial pattern, least absolute shrinkage and selection operator, and support vector machines. Regarding reported classification accuracies, performance above the upper quartile is in the 85 % to 100 % range for the binary case and in the 83 % to 93 % range for multi-class one. Associated uncertainties are up to 6 % while repeatability for a predetermined dataset is up to 8 %. Reproducibility assessment was instead prevented by lack of standardization in experiments. Significance. By relying on the analysed studies, the reader is guided towards the development of a successful processing strategy as a crucial part of a brain-computer interface. Moreover, it is suggested that future studies should extend these approaches on data from more subjects and with custom experiments, even by investigating online operation. This would also enable the quantification of results reproducibility.

Modulating Frustration and Agency Using Fabricated Input for Motor Imagery BCIs in Stroke Rehabilitation

“…After each condition, participants used 7-point Likert scale items to rate their perceived control ("I felt I was in control of when the kiwi jumped/ball squeezed." from strongly disagree (1) to strongly agree (7)) and frustration ("How much frustration did you feel in this condition?" from strongly absent (1) to strongly pronounced (7)).…”

“…from strongly disagree (1) to strongly agree (7)) and frustration ("How much frustration did you feel in this condition?" from strongly absent (1) to strongly pronounced (7)). The questions were identical to those used in previous studies of frustration [8], and perceived control [54].…”

“…BCI research has sought to improve performance of BCIs through novel hardware or signal processing algorithms increasing users' BCI performance (i.e. true positive rate or classification accuracy) [7]. Alternatively, recent studies reduced frustration by creating an illusions of control through fabricated input, which consists of injections of preprogrammed positive feedback, when the BCI does not recognize valid user input attempts [8], [9].…”

Investigation of the Effects of Two and Three Dimensional Paradigms on Event-Related Potentials Using Wavelet Transform Based Method

“…Literatürde EEG sinyallerinin kullanımından elde edilen öznitelikleri kullanarak genellikle motor hayali (Arpaia, Esposito, Natalizio, & Parvis, 2022;Kevric & Subasi, 2017;Stephe & Kumar, 2022), olay ilişkili P300 potansiyel temelli (Sellers, Krusienski, McFarland, Vaughan, & Wolpaw, 2006;Won, Kwon, Ahn, & Jun, 2022;Xu vd., 2013) ve kararlı durum görsel olarak uyarılmış potansiyel tabanlı (Jalilpour, Sardouie, & Mijani, 2020;Muller-Putz & Pfurtscheller, 2007; Z. Wu, Lai, Xia, Wu, & Yao, 2008) olmak üzere üç ana yaklaşım vardır.…”

Effect of 3D Paradigm on Event-Related Potentials

“…BCI systems enable such patients to communicate their needs to their relatives [1][2][3][4][5][6]. In the literature, there are generally three main approaches utilizing features obtained from EEG signals use of motor images [7][8][9][10], event-related P300 potentials [11][12][13], and steady-state visually evoked potentials [14][15][16]. Of these, event-related P300 potential is frequently preferred in EEG-based BCI systems as they occur in a short time, are not impaired by eye movement artifacts, and these systems do not require a pretraining phase.…”