Objective. Processing strategies are analyzed with respect to the classification of electroencephalographic signals related to brain-computer interfaces (BCIs) based on motor imagery (MI). A review of literature is carried out to understand the achievements in MI 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 BCIs. Article search was carried out in accordance with the Preferred Reporting Items for Systematic reviews and Meta-Analyses 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%–100% range for the binary case and in the 83%–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 analyzed studies, the reader is guided towards the development of a successful processing strategy as a crucial part of a BCI. 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 the results reproducibility.

Objective. Recent trends in brain–computer interface (BCI) research concern the passive monitoring of brain activity, which aim to monitor a wide variety of cognitive states. Engagement is such a cognitive state, which is of interest in contexts such as learning, entertainment or rehabilitation. This study proposes a novel approach for real-time estimation of engagement during different tasks using electroencephalography (EEG). Approach. Twenty-three healthy subjects participated in the BCI experiment. A modified version of the d2 test was used to elicit engagement. Within-subject classification models which discriminate between engaging and resting states were trained based on EEG recorded during a d2 test based paradigm. The EEG was recorded using eight electrodes and the classification model was based on filter-bank common spatial patterns and a linear discriminant analysis. The classification models were evaluated in cross-task applications, namely when playing Tetris at different speeds (i.e. slow, medium, fast) and when watching two videos (i.e. advertisement and landscape video). Additionally, subjects’ perceived engagement was quantified using a questionnaire. Main results. The models achieved a classification accuracy of 90% on average when tested on an independent d2 test paradigm recording. Subjects’ perceived and estimated engagement were found to be greater during the advertisement compared to the landscape video (p = 0.025 and p < 0.001, respectively); greater during medium and fast compared to slow Tetris speed (p < 0.001, respectively); not different between medium and fast Tetris speeds. Additionally, a common linear relationship was observed for perceived and estimated engagement (r _rm = 0.44, p < 0.001). Finally, theta and alpha band powers were investigated, which respectively increased and decreased during more engaging states. Significance. This study proposes a task-specific EEG engagement estimation model with cross-task capabilities, offering a framework for real-world applications.

The present study introduces a brain–computer interface designed and prototyped to be wearable and usable in daily life. Eight dry electroencephalographic sensors were adopted to acquire the brain activity associated with motor imagery. Multimodal feedback in extended reality was exploited to improve the online detection of neurological phenomena. Twenty-seven healthy subjects used the proposed system in five sessions to investigate the effects of feedback on motor imagery. The sample was divided into two equal-sized groups: a “neurofeedback” group, which performed motor imagery while receiving feedback, and a “control” group, which performed motor imagery with no feedback. Questionnaires were administered to participants aiming to investigate the usability of the proposed system and an individual’s ability to imagine movements. The highest mean classification accuracy across the subjects of the control group was about 62% with 3% associated type A uncertainty, and it was 69% with 3% uncertainty for the neurofeedback group. Moreover, the results in some cases were significantly higher for the neurofeedback group. The perceived usability by all participants was high. Overall, the study aimed at highlighting the advantages and the pitfalls of using a wearable brain–computer interface with dry sensors. Notably, this technology can be adopted for safe and economically viable tele-rehabilitation.

Objective. A wearable brain–computer interface is proposed and validated experimentally in relation to the real-time control of an endless runner game by self-paced motor imagery(MI). Approach. Electroencephalographic signals were recorded via eight wet electrodes. The processing pipeline involved a filter-bank common spatial pattern approach and the combination of three binary classifiers exploiting linear discriminant analysis. This enabled the discrimination between imagining left-hand, right-hand, and no movement. Each mental task corresponded to an avatar horizontal motion within the game. Twenty-three healthy subjects participated to the experiments and their data are made publicly available. A custom metric was proposed to assess avatar control performance during the gaming phase. The game consisted of two levels, and after each, participants completed a questionnaire to self-assess their engagement and gaming experience. Main results. The mean classification accuracies resulted 73%, 73%, and 67% for left-rest, right-rest, and left-right discrimination, respectively. In the gaming phase, subjects with higher accuracies for left-rest and right-rest pair exhibited higher performance in terms of the custom metric. Correlation of the offline and real-time performance was investigated. The left-right MI did not correlate to the gaming phase performance due to the poor mean accuracy of the calibration. Finally, the engagement questionnaires revealed that level 1 and level 2 were not perceived as frustrating, despite the increasing difficulty. Significance. The work contributes to the development of wearable and self-paced interfaces for real-time control. These enhance user experience by guaranteeing a more natural interaction with respect to synchronous neural interfaces. Moving beyond benchmark datasets, the work paves the way to future applications on mobile devices for everyday use.

A hybrid method is proposed for removing artifacts from electroencephalographic (EEG) signals. This relies on the integration of artifact subspace reconstruction (ASR) with multivariate empirical mode decomposition. The method can be applied when few EEG sensors are available, a condition in which existing techniques are not effective, and it was tested with two public datasets: (i) semi-synthetic data, and (ii) experimental data with artifacts. One to four EEG sensors were taken into account and the proposal was compared to both ASR and MEMD alone. The proposed method efficiently removed muscular, ocular, or eye-blink artifacts on both semi-synthetic and experimental data. Unexpectedly, the ASR alone also showed compatible performance on semi-synthetic data. However, ASR did not work properly when experimental data were considered. Finally, MEMD was found less effective than both ASR and MEMD-ASR.

The aim of this study is to characterize the acquisition delay in wireless EEG instruments and evaluate its impact on the detection of time-locked neural phenomena, such as P300 and movement-related cortical potentials (MRCP). Accurate timing is critical for both research and clinical applications, especially for real-time brain-computer interfaces (BCI). A measurement setup was thus developed to assess acquisition delays and their uncertainty. Delays were measured at both the start and stop of a reference signal generation to investigate the consistency and reliability of the devices. BCI experiments were also performed to evaluate the impact of the measured delay on the detection of the time-locked phenomena. Statistical tests confirmed significant differences in delays across devices and configurations (e.g., from few tens to a hundred ms). These delays directly impacted P300 and MRCP detection, raising concerns about potential misclassification. Nonetheless, the correction of the measured acquisition delay proved beneficial, especially with regard to the P300 latency measured through low-cost instrumentation.