Brain-computer Interface Accuracy Research Articles

Toward Assessment of Sound Localization in Disorders of Consciousness Using a Hybrid Audiovisual Brain-Computer Interface.

Behavioral assessment of sound localization in the Coma Recovery Scale-Revised (CRS-R) poses a significant challenge due to motor disability in patients with disorders of consciousness (DOC). Brain-computer interfaces (BCIs), which can directly detect brain activities related to external stimuli, may thus provide an approach to assess DOC patients without the need for any physical behavior. In this study, a novel audiovisual BCI system was developed to simulate sound localization evaluation in CRS-R. Specifically, there were two alternatively flashed buttons on the left and right sides of the graphical user interface, one of which was randomly chosen as the target. The auditory stimuli of bell sounds were simultaneously presented by the ipsilateral loudspeaker during the flashing of the target button, which prompted patients to selectively attend to the target button. The recorded electroencephalography data were analyzed in real time to detect event-related potentials evoked by the target and further to determine whether the target was attended to or not. A significant BCI accuracy for a patient implied that he/she had sound localization. Among eighteen patients, eleven and four showed sound localization in the BCI and CRS-R, respectively. Furthermore, all patients showing sound localization in the CRS-R were among those detected by our BCI. The other seven patients who had no sound localization behavior in CRS-R were identified by the BCI assessment, and three of them showed improvements in the second CRS-R assessment after the BCI experiment. Thus, the proposed BCI system is promising for assisting the assessment of sound localization and improving the clinical diagnosis of DOC patients.

Ten-Hour Stable Noninvasive Brain-Computer Interface Realized by Semidry Hydrogel-Based Electrodes.

Noninvasive brain-computer interface (BCI) has been extensively studied from many aspects in the past decade. In order to broaden the practical applications of BCI technique, it is essential to develop electrodes for electroencephalogram (EEG) collection with advanced characteristics such as high conductivity, long-term effectiveness, and biocompatibility. In this study, we developed a silver-nanowire/PVA hydrogel/melamine sponge (AgPHMS) semidry EEG electrode for long-lasting monitoring of EEG signal. Benefiting from the water storage capacity of PVA hydrogel, the electrolyte solution can be continuously released to the scalp-electrode interface during used. The electrolyte solution can infiltrate the stratum corneum and reduce the scalp-electrode impedance to 10 kΩ-15 kΩ. The flexible structure enables the electrode with mechanical stability, increases the wearing comfort, and reduces the scalp-electrode gap to reduce contact impedance. As a result, a long-term BCI application based on measurements of motion-onset visual evoked potentials (mVEPs) shows that the 3-hour BCI accuracy of the new electrode (77% to 100%) is approximately the same as that of conventional electrodes supported by a conductive gel during the first hour. Furthermore, the BCI system based on the new electrode can retain low contact impedance for 10 hours on scalp, which greatly improved the ability of BCI technique.

The Differences Between Motor Attempt and Motor Imagery in Brain-Computer Interface Accuracy and Event-Related Desynchronization of Patients With Hemiplegia.

Background: Motor attempt and motor imagery (MI) are two common motor tasks used in brain-computer interface (BCI). They are widely researched for motor rehabilitation in patients with hemiplegia. The differences between the motor attempt (MA) and MI tasks of patients with hemiplegia can be used to promote BCI application. This study aimed to explore the accuracy of BCI and event-related desynchronization (ERD) between the two tasks.Materials and Methods: We recruited 13 patients with stroke and 3 patients with traumatic brain injury, to perform MA and MI tasks in a self-control design. The BCI accuracies from the bilateral, ipsilesional, and contralesional hemispheres were analyzed and compared between different tasks. The cortical activation patterns were evaluated with ERD and laterality index (LI).Results: The study showed that the BCI accuracies of MA were significantly (p < 0.05) higher than MI in the bilateral, ipsilesional, and contralesional hemispheres in the alpha-beta (8–30 Hz) frequency bands. There was no significant difference in ERD and LI between the MA and MI tasks in the 8–30 Hz frequency bands. However, in the MA task, there was a negative correlation between the ERD values in the channel CP1 and ipsilesional hemispheric BCI accuracies (r = −0.552, p = 0.041, n = 14) and a negative correlation between the ERD values in channel CP2 and bilateral hemispheric BCI accuracies (r = −0.543, p = 0.045, n = 14). While in the MI task, there were negative correlations between the ERD values in channel C4 and bilateral hemispheric BCI accuracies (r = −0.582, p = 0.029, n = 14) as well as the contralesional hemispheric BCI accuracies (r = −0.657, p = 0.011, n = 14). As for motor dysfunction, there was a significant positive correlation between the ipsilesional BCI accuracies and FMA scores of the hand part in 8–13 Hz (r = 0.565, p = 0.035, n = 14) in the MA task and a significant positive correlation between the ipsilesional BCI accuracies and FMA scores of the hand part in 13–30 Hz (r = 0.558, p = 0.038, n = 14) in the MI task.Conclusion: The MA task may achieve better BCI accuracy but have similar cortical activations with the MI task. Cortical activation (ERD) may influence the BCI accuracy, which should be carefully considered in the BCI motor rehabilitation of patients with hemiplegia.

Multi-Domain Convolutional Neural Networks for Lower-Limb Motor Imagery Using Dry vs. Wet Electrodes.

Motor imagery (MI) brain–computer interfaces (BCIs) have been used for a wide variety of applications due to their intuitive matching between the user’s intentions and the performance of tasks. Applying dry electroencephalography (EEG) electrodes to MI BCI applications can resolve many constraints and achieve practicality. In this study, we propose a multi-domain convolutional neural networks (MD-CNN) model that learns subject-specific and electrode-dependent EEG features using a multi-domain structure to improve the classification accuracy of dry electrode MI BCIs. The proposed MD-CNN model is composed of learning layers for three domain representations (time, spatial, and phase). We first evaluated the proposed MD-CNN model using a public dataset to confirm 78.96% classification accuracy for multi-class classification (chance level accuracy: 30%). After that, 10 healthy subjects participated and performed three classes of MI tasks related to lower-limb movement (gait, sitting down, and resting) over two sessions (dry and wet electrodes). Consequently, the proposed MD-CNN model achieved the highest classification accuracy (dry: 58.44%; wet: 58.66%; chance level accuracy: 43.33%) with a three-class classifier and the lowest difference in accuracy between the two electrode types (0.22%, d = 0.0292) compared with the conventional classifiers (FBCSP, EEGNet, ShallowConvNet, and DeepConvNet) that used only a single domain. We expect that the proposed MD-CNN model could be applied for developing robust MI BCI systems with dry electrodes.

Brain-computer interface with rapid serial multimodal presentation using artificial facial images and voice.

Electroencephalography (EEG) signals elicited by multimodal stimuli can drive brain-computer interfaces (BCIs), and research has demonstrated that visual and auditory stimuli can be employed simultaneously to improve BCI performance. However, no studies have investigated the effect of multimodal stimuli in rapid serial visual presentation (RSVP) BCIs. The present study proposed a rapid serial multimodal presentation (RSMP) BCI that incorporates artificial facial images and artificial voice stimuli. To clarify the effect of audiovisual stimuli on the RSMP BCI, scrambled images and masked sounds were applied instead of visual and auditory stimuli, respectively. The findings indicated that the audiovisual stimuli improved performance of the RSMP BCI, and that P300 at Pz contributed to classification accuracy. Online accuracy of the BCI reached 85.7±11.5%. Taken together, these findings may aid in the development of better gaze-independent BCI systems.

Neurofeedback Training of the Control Network in Children Improves Brain Computer Interface Performance

In the past 20 years, neural engineering has made unprecedented progress in the interpretation of brain information (e.g., brain-computer interfaces) and in neuromodulation (e.g., electromagnetic stimulation and neurofeedback). However, there has been little research aiming to improve the performance of brain-computer interfaces (BCIs) using neuromodulation. The present study presents a novel design for a neurofeedback training (NFT) method to improve the operation of a steady-state visual evoked potential (SSVEP)-based BCI and further explores its underlying mechanisms. The use of NFT to upregulate alpha-band power in the user’s parietal lobe is presented in this study as a new neuromodulation method to improve SSVEP-based BCI in this study. After users completed this NFT intervention, the signal-to-noise ratio (SNR), accuracy, and information transfer rate (ITR) of the SSVEP-based BCI were increased by 5.8%, 4.7%, and 15.6%, respectively. However, no improvement was observed in the control group in which the subjects did not participate in NFT. Moreover, a general reinforcement of the information flow from the parietal lobe to the occipital lobe was observed. Evidence from a network analysis and an attention test further indicates that NFT improves attention by developing the control capacity of the parietal lobe and then enhances the above SSVEP indicators. Upregulating the amplitude of parietal alpha oscillations using NFT significantly improves the SSVEP-based BCI performance by modulating the control network. The study validates an effective neuromodulation method and possibly contributes to explaining the function of the parietal lobe in the control network.

Improving motor imagery classification during induced motor perturbations

Objective. Motor imagery is the mental simulation of movements. It is a common paradigm to design brain-computer interfaces (BCIs) that elicits the modulation of brain oscillatory activity similar to real, passive and induced movements. In this study, we used peripheral stimulation to provoke movements of one limb during the performance of motor imagery tasks. Unlike other works, in which induced movements are used to support the BCI operation, our goal was to test and improve the robustness of motor imagery based BCI systems to perturbations caused by artificially generated movements. Approach. We performed a BCI session with ten participants who carried out motor imagery of three limbs. In some of the trials, one of the arms was moved by neuromuscular stimulation. We analysed 2-class motor imagery classifications with and without movement perturbations. We investigated the performance decrease produced by these disturbances and designed different computational strategies to attenuate the observed classification accuracy drop. Main results. When the movement was induced in a limb not coincident with the motor imagery classes, extracting oscillatory sources of the movement imagination tasks resulted in BCI performance being similar to the control (undisturbed) condition; when the movement was induced in a limb also involved in the motor imagery tasks, the performance drop was significantly alleviated by spatially filtering out the neural noise caused by the stimulation. We also show that the loss of BCI accuracy was accompanied by weaker power of the sensorimotor rhythm. Importantly, this residual power could be used to predict whether a BCI user will perform with sufficient accuracy under the movement disturbances. Significance. We provide methods to ameliorate and even eliminate motor related afferent disturbances during the performance of motor imagery tasks. This can help improving the reliability of current motor imagery based BCI systems.

Group ensemble learning enhances the accuracy and convenience of SSVEP-based BCIs via exploiting inter-subject information

Over the past years, Steady-state visual evoked potential (SSVEP) is widely used in brain–computer interfaces (BCIs) due to its high efficiency, robustness and convenience. Although the ensemble task-related component analysis (eTRCA) is a state-of-the-art signal processing algorithm for SSVEP signals, the tedious training process restricts its extensive application. In this study, a novel hybrid framework is proposed to conquer this problem by reusing the validation data recorded previously. Additionally, a new group ensemble learning method is also proposed to combine a filter bank canonical correlation analysis (FBCCA) detector and several eTRCA detectors to achieve a high-performance SSVEP detector. The offline analysis, which used a four-class SSVEP dataset recorded from 9 subjects in four days, demonstrates that the proposed method outperforms the FBCCA method and almost achieves the performance of the eTRCA method. The proposed method provides a good trade-off between performance and training cost, which is more suitable for application in real life.

How to build a fast and accurate code-modulated brain-computer interface

Objective. In the last decade, the advent of code-modulated brain-computer interfaces (BCIs) has allowed the implementation of systems with high information transfer rates (ITRs) and increased the possible practicality of such interfaces. In this paper, we evaluate the effect of different numbers of targets in the stimulus display, modulation sequences generators, and signal processing algorithms on the accuracy and ITR of code-modulated BCIs. Approach. We use both real and simulated electroencephalographic (EEG) data, to evaluate these parameters and methods. Then, we compared numerous different setups to assess their performance and identify the best configurations. We also evaluated the dependability of our simulated evaluation approach. Main results. Our results show that Golay, almost perfect, and deBruijn sequence-based visual stimulus modulations provide the best results, significantly outperforming the commonly used m-sequences in all cases. We conclude that artificial neural network processing algorithms offer the best processing pipeline for this type of BCI, achieving a maximum classification accuracy of 94.7% on real EEG data while obtaining a maximum ITR of 127.2 bits min−1 in a simulated 64-target system. Significance. We used a simulated framework that demonstrated previously unattainable flexibility and convenience while staying reasonably realistic. Furthermore, our findings suggest several new considerations which can be used to guide further code-based BCI development.

Effect of Static Posture on Online Performance of P300-Based BCIs for TV Control.

To implement a practical brain–computer interface (BCI) for daily use, continuing changes in postures while performing daily tasks must be considered in the design of BCIs. To examine whether the performance of a BCI could depend on postures, we compared the online performance of P300-based BCIs built to select TV channels when subjects took sitting, recline, supine, and right lateral recumbent postures during BCI use. Subjects self-reported the degrees of interference, comfort, and familiarity after BCI control in each posture. We found no significant difference in the BCI performance as well as the amplitude and latency of P300 and N200 among the four postures. However, when we compared BCI accuracy outcomes normalized within individuals between two cases where subjects reported relatively more positively or more negatively about using the BCI in a particular posture, we found higher BCI accuracy in those postures for which individual subjects reported more positively. As a result, although the change of postures did not affect the overall performance of P300-based BCIs, the BCI performance varied depending on the degree of postural comfort felt by individual subjects. Our results suggest considering the postural comfort felt by individual BCI users when using a P300-based BCI at home.

Enhancement of Event-Related Desynchronization in Motor Imagery Based on Transcranial Electrical Stimulation.

Due to the individual differences controlling brain-computer interfaces (BCIs), the applicability and accuracy of BCIs based on motor imagery (MI-BCIs) are limited. To improve the performance of BCIs, this article examined the effect of transcranial electrical stimulation (tES) on brain activity during MI. This article designed an experimental paradigm that combines tES and MI and examined the effects of tES based on the measurements of electroencephalogram (EEG) features in MI processing, including the power spectral density (PSD) and dynamic event-related desynchronization (ERD). Finally, we investigated the effect of tES on the accuracy of MI classification using linear discriminant analysis (LDA). The results showed that the ERD of the μ and β rhythms in the left-hand MI task was enhanced after electrical stimulation with a significant effect in the tDCS group. The average classification accuracy of the transcranial alternating current stimulation (tACS) group and transcranial direct current stimulation (tDCS) group (88.19% and 89.93% respectively) were improved significantly compared to the pre-and pseudo stimulation groups. These findings indicated that tES can improve the performance and applicability of BCI and that tDCS was a potential approach in regulating brain activity and enhancing valid features during noninvasive MI-BCI processing.

Influence of iTBS on the Acute Neuroplastic Change After BCI Training.

Objective: Brain-computer interface (BCI) training is becoming increasingly popular in neurorehabilitation. However, around one third subjects have difficulties in controlling BCI devices effectively, which limits the application of BCI training. Furthermore, the effectiveness of BCI training is not satisfactory in stroke rehabilitation. Intermittent theta burst stimulation (iTBS) is a powerful neural modulatory approach with strong facilitatory effects. Here, we investigated whether iTBS would improve BCI accuracy and boost the neuroplastic changes induced by BCI training.Methods: Eight right-handed healthy subjects (four males, age: 20–24) participated in this two-session study (BCI-only session and iTBS+BCI session in random order). Neuroplastic changes were measured by functional near-infrared spectroscopy (fNIRS) and single-pulse transcranial magnetic stimulation (TMS). In BCI-only session, fNIRS was measured at baseline and immediately after BCI training. In iTBS+BCI session, BCI training was followed by iTBS delivered on the right primary motor cortex (M1). Single-pulse TMS was measured at baseline and immediately after iTBS. fNIRS was measured at baseline, immediately after iTBS, and immediately after BCI training. Paired-sample t-tests were used to compare amplitudes of motor-evoked potentials, cortical silent period duration, oxygenated hemoglobin (HbO2) concentration and functional connectivity across time points, and BCI accuracy between sessions.Results: No significant difference in BCI accuracy was detected between sessions (p > 0.05). In BCI-only session, functional connectivity matrices between motor cortex and prefrontal cortex were significantly increased after BCI training (p's < 0.05). In iTBS+BCI session, amplitudes of motor-evoked potentials were significantly increased after iTBS (p's < 0.05), but no change in HbO2 concentration or functional connectivity was observed throughout the whole session (p's > 0.05).Conclusions: To our knowledge, this is the first study that investigated how iTBS targeted on M1 influences BCI accuracy and the acute neuroplastic changes after BCI training. Our results revealed that iTBS targeted on M1 did not influence BCI accuracy or facilitate the neuroplastic changes after BCI training. Therefore, M1 might not be an effective stimulation target of iTBS for the purpose of improving BCI accuracy or facilitate its effectiveness; other brain regions (i.e., prefrontal cortex) are needed to be further investigated as potentially effective stimulation targets.

A Comparison of Mobile VR Display Running on an Ordinary Smartphone With Standard PC Display for P300-BCI Stimulus Presentation

A brain-computer interface (BCI) based on electroencephalography (EEG) is a promising technology for enhancing virtual reality (VR) applications-in particular, for gaming. We focus on the so-called P300-BCI, a stable and accurate BCI paradigm relying on the recognition of a positive event-related potential (ERP) occurring in the EEG about 300 ms post-stimulation. We implemented a basic version of such a BCI displayed on an ordinary and affordable smartphone-based head-mounted VR device: that is, a mobile and passive VR system (with no electronic components beyond the smartphone). The mobile phone performed the stimuli presentation, EEG synchronization (tagging) and feedback display. We compared the ERPs and the accuracy of the BCI on the VR device with a traditional BCI running on a personal computer (PC). We also evaluated the impact of subjective factors on the accuracy. The study was within-subjects, with 21 participants and one session in each modality. No significant difference in BCI accuracy was found between the PC and VR systems, although the P200 ERP was significantly wider and larger in the VR system as compared to the PC system.

EEG-Inception: A Novel Deep Convolutional Neural Network for Assistive ERP-Based Brain-Computer Interfaces.

In recent years, deep-learning models gained attention for electroencephalography (EEG) classification tasks due to their excellent performance and ability to extract complex features from raw data. In particular, convolutional neural networks (CNN) showed adequate results in brain-computer interfaces (BCI) based on different control signals, including event-related potentials (ERP). In this study, we propose a novel CNN, called EEG-Inception, that improves the accuracy and calibration time of assistive ERP-based BCIs. To the best of our knowledge, EEG-Inception is the first model to integrate Inception modules for ERP detection, which combined efficiently with other structures in a light architecture, improved the performance of our approach. The model was validated in a population of 73 subjects, of which 31 present motor disabilities. Results show that EEG-Inception outperforms 5 previous approaches, yielding significant improvements for command decoding accuracy up to 16.0%, 10.7%, 7.2%, 5.7% and 5.1% in comparison to rLDA, xDAWN + Riemannian geometry, CNN-BLSTM, DeepConvNet and EEGNet, respectively. Moreover, EEG-Inception requires very few calibration trials to achieve state-of-the-art performances taking advantage of a novel training strategy that combines cross-subject transfer learning and fine-tuning to increase the feasibility of this approach for practical use in assistive applications.

A Comparison of Classification Techniques to Predict Brain-Computer Interfaces Accuracy Using Classifier-Based Latency Estimation.

P300-based Brain-Computer Interface (BCI) performance is vulnerable to latency jitter. To investigate the role of latency jitter on BCI system performance, we proposed the classifier-based latency estimation (CBLE) method. In our previous study, CBLE was based on least-squares (LS) and stepwise linear discriminant analysis (SWLDA) classifiers. Here, we aim to extend the CBLE method using sparse autoencoders (SAE) to compare the SAE-based CBLE method with LS- and SWLDA-based CBLE. The newly-developed SAE-based CBLE and previously used methods are also applied to a newly-collected dataset to reduce the possibility of spurious correlations. Our results showed a significant () negative correlation between BCI accuracy and estimated latency jitter. Furthermore, we also examined the effect of the number of electrodes on each classification technique. Our results showed that on the whole, CBLE worked regardless of the classification method and electrode count; by contrast the effect of the number of electrodes on BCI performance was classifier dependent.

Реабилитация больных с детским церебральным параличом с помощью экзоскелета кисти, управляемого интерфейсом «мозг–компьютер»

Cerebral palsy (CP) is one of the most severe central nervous system diseases in childhood associated with motor impairment. The study was aimed to assess the efficiency of the complex comprising brain-computer interface (BCI) and hand exoskeleton as an instrument for the motor function recovery in patients with CP complementing the essential therapy. The Fugl-Meyer Assessment scale, ARAT test and Jebsen–Taylor function test were used in 14 children and adolescents for the motor function improvement assessment after the therapy complemented by 7–10 BCI-exoskeleton based procedures. The EEG mu-rhythm sources properties during the motor imagery BCI control were studied. After the procedures completion, the significant improvement of the Fugl-Meyer Assessment scale score (7 (2; 11) for hand active movements; 4.5 (1; 6) for proximal arm and 2.5 (0; 5) for hand), ARAT test score (7.5 (1; 31) for total score, 1.5 (0; 12) for grasp movement and 1.5 (0; 8) for grip movement), as well as significantly different from the zero execution time reduction in three out of seven Jabsen–Taylor function test items (–1 (–4.13; 0.25) for simulated feeding; –1 (–2; 0) for moving light and heavy cans) were identified. The average BCI detection level was 0.51 (0.45; 0.54) (max = 0.70). In most EEG recordings the mu-rhythm sources were detected, both for intact and affected hemispheres. The mu-rhythm desynchronization associated with motor imagery was observed, significantly affecting the BCI accuracy. The results obtained indicate that the use of BCI-exoskeleton complex effectively complements the standard rehabilitation methods for children with CP, and suggest that its clinical effectiveness in individuals with CP may be proven by enrollment of more patients.

Study of the Functional Brain Connectivity and Lower-Limb Motor Imagery Performance After Transcranial Direct Current Stimulation.

The use of transcranial direct current stimulation (tDCS) has been related to the improvement of motor and learning tasks. The current research studies the effects of an asymmetric tDCS setup over brain connectivity, when the subject is performing a motor imagery (MI) task during five consecutive days. A brain-computer interface (BCI) based on electroencephalography is simulated in offline analysis to study the effect that tDCS has over different electrode configurations for the BCI. This way, the BCI performance is used as a validation index of the effect of the tDCS setup by the analysis of the classifier accuracy of the experimental sessions. In addition, the relationship between the brain connectivity and the BCI accuracy performance is analyzed. Results indicate that tDCS group, in comparison to the placebo sham group, shows a higher significant number of connectivity interactions in the motor electrodes during MI tasks and an increasing BCI accuracy over the days. However, the asymmetric tDCS setup does not improve the BCI performance of the electrodes in the intended hemisphere.

SSVEP Stimulus Layout Effect on Accuracy of Brain-Computer Interfaces in Augmented Reality Glasses

Steady-state visual evoked potentials-based brain-computer interfaces (SSVEP-BCI) has the advantage of high information transfer rate (ITR) and little user training, and it has a high application value in the field of disability assistance and human-computer interaction. Generally SSVEP-BCI requires a personal computer screen (PC) to display several repetitive visual stimuli for inducing the SSVEP response, which reduces its portability and flexibility. Using augmented reality (AR) glasses worn on the head to display the repetitive visual stimuli could solve the above drawbacks, but whether it could achieve the same accuracy as PC screen in the case of reduced brightness and increased interference is unknown. In current study, we firstly designed 4 stimulus layouts and displayed them with Microsoft HoloLens (AR-SSVEP) glasses, comparison analysis showed that the classification accuracies are influenced by the stimulus layout when the stimulus duration is less than 3s. When the stimulus duration exceeds 3s, there is no significant accuracy difference between the 4 layouts. Then we designed a similar experimental paradigm on PC screen (PC-SSVEP) based on the best layout of AR. Classification results showed that AR-SSVEP achieved similar accuracy with PC-SSVEP when the stimulus duration is more than 3s, but when the stimulus duration is less than 2s, the accuracy of AR-SSVEP is lower than PC-SSVEP. Brain topological analysis indicated that the spatial distribution of SSVEP responses is similar, both of which are strongest in the occipital region. Current study indicated that stimulus layout is a key factor when building SSVEP-BCI with AR glasses, especially when the stimulation time is short.

Development of a ternary hybrid fNIRS-EEG brain–computer interface based on imagined speech

ABSTRACTThere is increasing interest in developing intuitive brain-computer interfaces (BCIs) to differentiate intuitive mental tasks such as imagined speech. Both electroencephalography (EEG) and functional near-infrared spectroscopy (fNIRS) have been used for this purpose. However, the classification accuracy and number of commands in such BCIs have been limited. The use of multi-modal BCIs to address these issues has been proposed for some common BCI tasks, but not for imagined speech. Here, we propose a multi-class hybrid fNIRS-EEG BCI based on imagined speech. Eleven participants performed multiple iterations of three tasks: mentally repeating ‘yes’ or ‘no’ for 15 s or an equivalent duration of unconstrained rest. We achieved an average ternary classification accuracy of 70.45 ± 19.19% which is significantly better than that attained with each modality alone (p < 0.05). Our findings suggest that concurrent measurements of EEG and fNIRS can improve classification accuracy of BCIs based on imagined speech.

A Flexible, Robust, and Gel-Free Electroencephalogram Electrode for Noninvasive Brain-Computer Interfaces.

Brain-computer interfaces (BCIs) enable direct and near-instant communication between the brain and electronic devices. One of the biggest remaining challenges is to develop an effective noninvasive BCI that allows the recording electrodes to avoid hair on human skin without the inconveniences and complications of using a conductive gel. In this study, we developed a cost-effective, easily manufacturable, flexible, robust, and gel-free silver nanowire/polyvinyl butyral (PVB)/melamine sponge (AgPMS) electroencephalogram (EEG) electrode that circumvents problems with hair. Because of surface metallization by the silver nanowires (AgNWs), the sponge has a high conductivity of 917 S/m while its weight remains the same. The flexible sponge framework and self-locking AgNWs combine to give the new electrode remarkable mechanical stability (the conductivity remains unchanged after 10 000 cycles at 10% compression) and the ability to bypass hair. A BCI application based on steady-state visual evoked potential (SSVEP) measurements on hairless skin shows that the BCI accuracy of the new electrode (86%) is approximately the same as that of conventional electrodes supported by a conductive gel (88%). Most importantly, the performance of the AgPMS on hairy skin is not significantly reduced, which indicates that the new electrode can replace conventional electrodes for both hairless and hairy skin BCIs and other EEG applications.