Analysis of Physiological Response of Attention and Stress States in Teleoperation Performance of Social Tasks.

Some studies addressed monitoring mental states by physiological responses analysis in robots' teleoperation in traditional applications such as inspection and exploration; however, no study analyzed the physiological response during teleoperated social tasks to the best of our knowledge. We analyzed the physiological response of attention and stress mental states by computing the correlation between multimodal biomarkers and performance, pleasure-arousal scale, and workload. Physiological data were recorded during simulated teleoperated social tasks to induce mental states, such as normal, attention, and stress. The results showed that task performance and workload subscales achieved moderate correlations with some multimodal biomarkers. The correlations depended on the induced state. The cognitive workload was related to brain biomarkers of attention in the frontal and frontal-central regions. These regions were close to the frontopolar region, which is commonly reported in attentional studies. Thus, some multimodal biomarkers of attention and stress mental states could monitor or predict metrics related to the performance in teleoperation of social tasks.

Effects of visual-electrotactile stimulation feedback on brain functional connectivity during motor imagery practice.

The use of neurofeedback is an important aspect of effective motor rehabilitation as it offers real-time sensory information to promote neuroplasticity. However, there is still limited knowledge about how the brain's functional networks reorganize in response to such feedback. To address this gap, this study investigates the reorganization of the brain network during motor imagery tasks when subject to visual stimulation or visual-electrotactile stimulation feedback. This study can provide healthcare professionals with a deeper understanding of the changes in the brain network and help develop successful treatment approaches for brain-computer interface-based motor rehabilitation applications. We examine individual edges, nodes, and the entire network, and use the minimum spanning tree algorithm to construct a brain network representation using a functional connectivity matrix. Furthermore, graph analysis is used to detect significant features in the brain network that might arise in response to the feedback. Additionally, we investigate the power distribution of brain activation patterns using power spectral analysis and evaluate the motor imagery performance based on the classification accuracy. The results showed that the visual and visual-electrotactile stimulation feedback induced subject-specific changes in brain activation patterns and network reorganization in the [Formula: see text] band. Thus, the visual-electrotactile stimulation feedback significantly improved the integration of information flow between brain regions associated with motor-related commands and higher-level cognitive functions, while reducing cognitive workload in the sensory areas of the brain and promoting positive emotions. Despite these promising results, neither neurofeedback modality resulted in a significant improvement in classification accuracy, compared with the absence of feedback. These findings indicate that multimodal neurofeedback can modulate imagery-mediated rehabilitation by enhancing motor-cognitive communication and reducing cognitive effort. In future interventions, incorporating this technique to ease cognitive demands for participants could be crucial for maintaining their motivation to engage in rehabilitation.

Multibranch convolutional neural network with contrastive representation learning for decoding same limb motor imagery tasks.

Introduction: Emerging deep learning approaches to decode motor imagery (MI) tasks have significantly boosted the performance of brain-computer interfaces. Although recent studies have produced satisfactory results in decoding MI tasks of different body parts, the classification of such tasks within the same limb remains challenging due to the activation of overlapping brain regions. A single deep learning model may be insufficient to effectively learn discriminative features among tasks. Methods: The present study proposes a framework to enhance the decoding of multiple hand-MI tasks from the same limb using a multi-branch convolutional neural network. The CNN framework utilizes feature extractors from established deep learning models, as well as contrastive representation learning, to derive meaningful feature representations for classification. Results: The experimental results suggest that the proposed method outperforms several state-of-the-art methods by obtaining a classification accuracy of 62.98% with six MI classes and 76.15 % with four MI classes on the Tohoku University MI-BCI and BCI Competition IV datasets IIa, respectively. Discussion: Despite requiring heavy data augmentation and multiple optimization steps, resulting in a relatively long training time, this scheme is still suitable for online use. However, the trade-of between the number of base learners, training time, prediction time, and system performance should be carefully considered.

Riemann-Based Algorithms Assessment for Single- and Multiple-Trial P300 Classification in Non-Optimal Environments.

The P300 wave is commonly used in Brain-Computer Interface technology due to its higher bit rates when compared to other BCI paradigms. P300 classification pipelines based on Riemannian Geometry provide accuracies on par with state-of-the-art pipelines, without having the need for spatial filters, and also possess the ability to be calibrated with little data. In this study, five different P300 detection pipelines are compared, with three of them using Riemannian Geometry as either feature extraction or classification algorithms. The goal of this study is to assess the viability of Riemannian Geometry-based methods in non-optimal environments with sudden background noise changes, rather than maximizing classification accuracy values. For fifteen subjects, the average single-trial accuracy obtained for each pipeline was: 56.06% for Linear Discriminant Analysis (LDA), 72.13% for Bayesian Linear Discriminant Analysis (BLDA), 63.56% for Riemannian Minimum Distance to Mean (MDM), 69.22% for Riemannian Tangent Space with Logistic Regression (TS-LogR), and 63.30% for Riemannian Tangent Space with Support Vector Machine (TS-SVM). The results are higher for the pipelines based on BLDA and TS-LogR, suggesting that they could be viable methods for the detection of the P300 component when maximizing the bit rate is needed. For multiple-trial classification, the BLDA pipeline converged faster towards higher average values, closely followed by the TS-LogR pipeline. The two remaining Riemannian methods' accuracy also increases with the number of trials, but towards a lower value compared to the aforementioned ones. Single-stimulus detection metrics revealed that the TS-LogR pipeline can be a viable classification method, as its results are only slightly lower than those obtained with BLDA. P300 waveforms were also analyzed to check for evidence of the component being elicited. Finally, a questionnaire was used to retrieve the most intuitive focusing methods employed by the subjects.

A Novel EEG-Based Four-Class Linguistic BCI.

In this work, we present a novel EEG-based Linguistic BCI, which uses the four phonemic structures "BA", "FO", "LE", and "RY" as covert speech task classes. Six neurologically healthy volunteers with the age range of 19-37 participated in this experiment. Participants were asked to covertly speak a phonemic structure when they heard an auditory cue. EEG was recorded with 64 electrodes at 2048 samples/s. The duration of each trial is 312ms starting with the cue. The BCI was trained using a mixed randomized recording run containing 15 trials per class. The BCI is tested by playing a simple game of "Wack a mole" containing 5 trials per class presented in random order. The average classification accuracy for the 6 users is 82.5%. The most valuable features emerge after Auditory cue recognition (~100ms post onset), and within the 70-128 Hz frequency range. The most significant identified brain regions were the Prefrontal Cortex (linked to stimulus driven executive control), Wernicke's area (linked to Phonological code retrieval), the right IFG, and Broca's area (linked to syllabification). In this work, we have only scratched the surface of using Linguistic tasks for BCIs and the potential for creating much more capable systems in the future using this approach exists.

Covert Speech vs. Motor Imagery: a comparative study of class separability in identical environments.

In this study a single experimental protocol and analysis pipeline is used: once for MI tasks, and once for covert speech tasks. The goal of this study is not to maximizing classification accuracy; rather the main objective is to provide an identical environment for both paradigms, while identifying the most important activities related to the most class dependent features. Four volunteers participated in this experiment. With four classes, the average classification accuracy for covert speech tasks is 82.5%, and for motor imagery is 77.2%. The average performance is significantly higher than chance level for both paradigms, suggesting that the results are meaningful, despite being imperfect. For motor imagery tasks the most important activities are the execution of imagined movements, and goal driven executive control for suppression of overt movements, which also occur for covert speech tasks. However, the most important activity for covert speech tasks is the linguistic processing stages of word production prior to articulation, which does not occur in motor imagery. These high-Gamma linguistic processes are extremely class dependent, which contribute to the higher performance of covert speech tasks, compared to motor imagery in an otherwise identical environment.

Implication of N400 and P600 waves in the Linguistic Code Change in Monolinguals and Bilinguals.

There is evidence of the importance of N400 and P600 waves in linguistic processes, theses brain waves are related to syntax. This work proposes to evaluate learning process through the analysis of responses generated when formulation of word is requested, an artificial grammar test (AGT) is developed and N400 and P600 peaks are taken as indicators of performance; and two different groups of subjects took the AGT, 5 monolinguals and 5 bilinguals.The AGT is composed by 30 hybrids, each hybrid defines rules to formulate words; then if this word accomplished the rules, it is considered as grammatical. The N400 and P600 waves are computed by each word letter, and the mean for all 30 hybrids is compared between both two groups by electrode.Greater amplitudes for N400 and P600 peaks was found for monolinguals in comparison with bilinguals.

Performance predictors of motor imagery brain-computer interface based on spatial abilities for upper limb rehabilitation.

Motor Imagery based BCIs (MI-BCIs) allow the control of devices and communication by imagining different mental tasks. Despite many years of research, BCIs are still not the most accurate systems to control applications, due to two main factors: signal processing with classification, and users. It is admitted that BCI control involves certain characteristics and abilities in its users for optimal results. In this study, spatial abilities are evaluated in relation to MI-BCI control regarding flexion and extension mental tasks. Results show considerable correlation (r=0.49) between block design test (visual motor execution and spatial visualization) and extension-rest tasks. Additionally, rotation test (mental rotation task) presents significant correlation (r=0.56) to flexion-rest tasks.