Based Brain-computer Interface System Research Articles

A temporal–spectral fusion transformer with subject-specific adapter for enhancing RSVP-BCI decoding

The Rapid Serial Visual Presentation (RSVP)-based Brain–Computer Interface (BCI) is an efficient technology for target retrieval using electroencephalography (EEG) signals. The performance improvement of traditional decoding methods relies on a substantial amount of training data from new test subjects, which increases preparation time for BCI systems. Several studies introduce data from existing subjects to reduce the dependence of performance improvement on data from new subjects, but their optimization strategy based on adversarial learning with extensive data increases training time during the preparation procedure. Moreover, most previous methods only focus on the single-view information of EEG signals, but ignore the information from other views which may further improve performance. To enhance decoding performance while reducing preparation time, we propose a Temporal-Spectral fusion transformer with Subject-specific Adapter (TSformer-SA). Specifically, a cross-view interaction module is proposed to facilitate information transfer and extract common representations across two-view features extracted from EEG temporal signals and spectrogram images. Then, an attention-based fusion module fuses the features of two views to obtain comprehensive discriminative features for classification. Furthermore, a multi-view consistency loss is proposed to maximize the feature similarity between two views of the same EEG signal. Finally, we propose a subject-specific adapter to rapidly transfer the knowledge of the model trained on data from existing subjects to decode data from new subjects. Experimental results show that TSformer-SA significantly outperforms comparison methods and achieves outstanding performance with limited training data from new subjects. This facilitates efficient decoding and rapid deployment of BCI systems in practical use.

Attention-based CNN model for motor imagery classification from nonlinear EEG signals

Motor imagery (MI)-based brain-computer interface (BCI) provides a promising solution for the limb rehabilitation of stroke patients. For better rehabilitation performance, high-precision classification of MI-related EEG signals plays a critical role. However, this is still a challenging problem for multi-category MI signals. In this paper, we focus on four commonly used stroke rehabilitation actions, and propose a modular temporal-spatial attention-based CNN (MTSACNN) model for MI classification. In detail, we carry out the MI experiments and acquire the EEG signals related to imagining left/right fist clenching and left/right wrist dorsiflexion. MTSACNN model firstly extracts the low-order MI features through the temporal-spatial feature extraction module (TSFE module). Especially, a group attention mechanism is proposed for intra-group information interaction. Secondly, considering the short- and long-term working characteristics of brain, high-order temporal features are further extracted and fused by the multi-level feature fusion module (MLFF module). Finally, four auxiliary losses are arranged in the classification module (C module) to speed up the model optimization process. The experimental results show that MTSACNN model can achieve good performance in decoding rehabilitation-related MI brain intentions, achieving an average classification accuracy of 72.05% for fourteen subjects. This work is beneficial to promote the construction of high-performance stroke rehabilitation BCI system.

The Development of a Multicommand Tactile Event-Related Potential-Based Brain–Computer Interface Utilizing a Low-Cost Wearable Vibrotactile Stimulator

A tactile event-related potential (ERP)-based brain–computer interface (BCI) system is an alternative for enhancing the control and communication abilities of quadriplegic patients with visual or auditory impairments. Hence, in this study, we proposed a tactile stimulus pattern using a vibrotactile stimulator for a multicommand BCI system. Additionally, we observed a tactile ERP response to the target from random vibrotactile stimuli placed in the left and right wrist and elbow positions to create commands. An experiment was conducted to explore the location of the proposed vibrotactile stimulus and to verify the multicommand tactile ERP-based BCI system. Using the proposed features and conventional classification methods, we examined the classification efficiency of the four commands created from the selected EEG channels. The results show that the proposed vibrotactile stimulation with 15 stimulus trials produced a prominent ERP response in the Pz channels. The average classification accuracy ranged from 61.9% to 79.8% over 15 stimulus trials, requiring 36 s per command in offline processing. The P300 response in the parietal area yielded the highest average classification accuracy. The proposed method can guide the development of a brain–computer interface system for physically disabled people with visual or auditory impairments to control assistive and rehabilitative devices.

Comparative Study of Frequency Recognition Techniques for Steady-State Visual Evoked Potentials According to the Frequency Harmonics and Stimulus Number.

A key challenge in steady-state visual evoked potential (SSVEP)-based brain-computer interface (BCI) systems is to effectively recognize frequencies within a short time window. To address this challenge, the specific characteristics of the data are needed to select the frequency recognition method. These characteristics include factors, such as the number of stimulation targets and the presence of harmonic frequencies, resulting in optimizing the performance and accuracy of SSVEP-based BCI systems. The current study aimed to examine the effect of data characteristics on frequency recognition accuracy. In this analytical study, five commonly used frequency recognition methods were examined, used to various datasets containing different numbers of frequencies, including sub-data with and without frequency harmonics. The increase in the number of frequencies in the Multivariate Linear Regression (MLR) method has led to a decrease in frequency recognition accuracy by 9%. Additionally, the presence of harmonic frequencies resulted in an 8% decrease in accuracy for the MLR method. Frequency recognition using the MLR method reduces the effect of the number of different frequencies and harmonics of the stimulation frequencies on the frequency recognition accuracy.

High-Density Electroencephalogram Facilitates the Detection of Small Stimuli in Code-Modulated Visual Evoked Potential Brain-Computer Interfaces.

In recent years, there has been a considerable amount of research on visual evoked potential (VEP)-based brain-computer interfaces (BCIs). However, it remains a big challenge to detect VEPs elicited by small visual stimuli. To address this challenge, this study employed a 256-electrode high-density electroencephalogram (EEG) cap with 66 electrodes in the parietal and occipital lobes to record EEG signals. An online BCI system based on code-modulated VEP (C-VEP) was designed and implemented with thirty targets modulated by a time-shifted binary pseudo-random sequence. A task-discriminant component analysis (TDCA) algorithm was employed for feature extraction and classification. The offline and online experiments were designed to assess EEG responses and classification performance for comparison across four different stimulus sizes at visual angles of 0.5°, 1°, 2°, and 3°. By optimizing the data length for each subject in the online experiment, information transfer rates (ITRs) of 126.48 ± 14.14 bits/min, 221.73 ± 15.69 bits/min, 258.39 ± 9.28 bits/min, and 266.40 ± 6.52 bits/min were achieved for 0.5°, 1°, 2°, and 3°, respectively. This study further compared the EEG features and classification performance of the 66-electrode layout from the 256-electrode EEG cap, the 32-electrode layout from the 128-electrode EEG cap, and the 21-electrode layout from the 64-electrode EEG cap, elucidating the pivotal importance of a higher electrode density in enhancing the performance of C-VEP BCI systems using small stimuli.

Online continual decoding of streaming EEG signal with a balanced and informative memory buffer

Electroencephalography (EEG) based Brain Computer Interface (BCI) systems play a significant role in facilitating how individuals with neurological impairments effectively interact with their environment. In real world applications of BCI system for clinical assistance and rehabilitation training, the EEG classifier often needs to learn on sequentially arriving subjects in an online manner. As patterns of EEG signals can be significantly different for different subjects, the EEG classifier can easily erase knowledge of learnt subjects after learning on later ones as it performs decoding in online streaming scenario, namely catastrophic forgetting. In this work, we tackle this problem with a memory-based approach, which considers the following conditions: (1) subjects arrive sequentially in an online manner, with no large scale dataset available for joint training beforehand, (2) data volume from the different subjects could be imbalanced, (3) decoding difficulty of the sequential streaming signal vary, (4) continual classification for a long time is required. This online sequential EEG decoding problem is more challenging than classic cross subject EEG decoding as there is no large-scale training data from the different subjects available beforehand. The proposed model keeps a small balanced memory buffer during sequential learning, with memory data dynamically selected based on joint consideration of data volume and informativeness. Furthermore, for the more general scenarios where subject identity is unknown to the EEG decoder, aka. subject agnostic scenario, we propose a kernel based subject shift detection method that identifies underlying subject changes on the fly in a computationally efficient manner. We develop challenging benchmarks of streaming EEG data from sequentially arriving subjects with both balanced and imbalanced data volumes, and performed extensive experiments with a detailed ablation study on the proposed model. The results show the effectiveness of our proposed approach, enabling the decoder to maintain performance on all previously seen subjects over a long period of sequential decoding. The model demonstrates the potential for real-world applications.

A calibration-free c-VEP based BCI employing narrow-band random sequences

Objective. Code-modulated visual evoked potential (c-VEP) based brain–computer interfaces (BCIs) exhibit high encoding efficiency. Nevertheless, the majority of c-VEP based BCIs necessitate an initial training or calibration session, particularly when the number of targets expands, which impedes the practicality. To address this predicament, this study introduces a calibration-free c-VEP based BCI employing narrow-band random sequences. Approach. For the encoding method, a series of random sequences were generated within a specific frequency band. The c-VEP signals were subsequently elicited through the application of on-type grid flashes that were modulated by these sequences. For the calibration-free decoding algorithm, filter-bank canonical correlation analysis (FBCCA) was utilized with the reference templates generated from the original sequences. Thirty-five subjects participated into an online BCI experiment. The performances of c-VEP based BCIs utilizing narrow-band random sequences with frequency bands of 15–25 Hz (NBRS-15) and 8–16 Hz (NBRS-8) were compared with that of a steady-state visual evoked potential (SSVEP) based BCI within a frequency range of 8–15.8 Hz. Main results. The offline analysis results demonstrated a substantial correlation between the c-VEPs and the original narrow-band random sequences. After parameter optimization, the calibration-free system employing the NBRS-15 frequency band achieved an average information transfer rate (ITR) of 78.56 ± 37.03 bits/min, which exhibited no significant difference compared to the performance of the SSVEP based system when utilizing FBCCA. The proposed system achieved an average ITR of 102.1 ± 57.59 bits/min in a simulation of a 1000-target BCI system. Significance. This study introduces a novel calibration-free c-VEP based BCI system employing narrow-band random sequences and shows great potential of the proposed system in achieving a large number of targets and high ITR.

Applying Common Spatial Pattern and Convolutional Neural Network to Classify Movements via EEG Signals.

Developing an electroencephalography (EEG)-based brain-computer interface (BCI) system is crucial to enhancing the control of external prostheses by accurately distinguishing various movements through brain signals. This innovation can provide comfortable circumstances for the populace who have movement disabilities. This study combined the most prospering methods used in BCI systems, including one-versus-rest common spatial pattern (OVR-CSP) and convolutional neural network (CNN), to automatically extract features and classify eight different movements of the shoulder, wrist, and elbow via EEG signals. The number of subjects who participated in the experiment was 10, and their EEG signals were recorded while performing movements at fast and slow speeds. We used preprocessing techniques before transforming EEG signals into another space by OVR-CSP, followed by sending signals into the CNN architecture consisting of four convolutional layers. Moreover, we extracted feature vectors after applying OVR-CSP and considered them as inputs to KNN, SVM, and MLP classifiers. Then, the performance of these classifiers was compared with the CNN method. The results demonstrated that the classification of eight movements using the proposed CNN architecture obtained an average accuracy of 97.65% for slow movements and 96.25% for fast movements in the subject-independent model. This method outperformed other classifiers with a substantial difference; ergo, it can be useful in improving BCI systems for better control of prostheses.

Emotion recognition with EEG-based brain-computer interfaces: a systematic literature review

Electroencephalography (EEG)-based Brain-Computer Interface (BCI) systems for emotion recognition have the potential to assist the enrichment of human–computer interaction with implicit information since they can enable understanding of the cognitive and emotional activities of humans. Therefore, these systems have become an important research topic today. This study aims to present trends and gaps on this topic by performing a systematic literature review based on the 216 published scientific literature gathered from various databases including ACM, IEEE Xplore, PubMed, Science Direct, and Web of Science from 2016 to 2020. This review gives an overview of all the components of EEG based BCI system from the signal stimulus module which includes the employed device, signal stimuli, and data processing modality, to the signal processing module which includes signal acquisition, pre-processing, feature extraction, feature selection, classification algorithms, and performance evaluation. Thus, this study provides an overview of all components of an EEG-based BCI system for emotion recognition and examines the available evidence in a clear, concise, and systematic way. In addition, the findings are aimed to inform researchers about the issues on what are research trends and the gaps in this field and guide them in their research directions.

Comparison of recognition methods for an asynchronous (un-cued) BCI system: an investigation with 40-class SSVEP dataset.

Steady-state visual evoked potential (SSVEP)-based brain-computer Interface (BCI) has demonstrated the potential to manage multi-command targets to achieve high-speed communication. Recent studies on multi-class SSVEP-based BCI have focused on synchronous systems, which rely on predefined time and task indicators; thus, these systems that use passive approaches may be less suitable for practical applications. Asynchronous systems recognize the user's intention (whether or not the user is willing to use systems) from brain activity; then, after recognizing the user's willingness, they begin to operate by switching swiftly for real-time control. Consequently, various methodologies have been proposed to capture the user's intention. However, in-depth investigation of recognition methods in asynchronous BCI system is lacking. Thus, in this work, three recognition methods (power spectral density analysis, canonical correlation analysis (CCA), and support vector machine (SVM)) used widely in asynchronous SSVEP BCI systems were explored to compare their performance. Further, we categorized asynchronous systems into two approaches (1-stage and 2-stage) based upon the recognition process's design, and compared their performance. To do so, a 40-class SSVEP dataset collected from 40 subjects was introduced. Finally, we found that the CCA-based method in the 2-stage approach demonstrated statistically significantly higher performance with a sensitivity of 97.62±02.06%, specificity of 76.50±23.50%, and accuracy of 75.59±10.09%. Thus, it is expected that the 2-stage approach together with CCA-based recognition and FB-CCA classification have good potential to be implemented in practical asynchronous SSVEP BCI systems.

An open dataset for human SSVEPs in the frequency range of 1-60 Hz

A steady-state visual evoked potential (SSVEP)-based brain-computer interface (BCI) system relies on the photic driving response to effectively elicit characteristic electroencephalogram (EEG) signals. However, traditional visual stimuli mainly adopt high-contrast black-and-white flickering stimulations, which are easy to cause visual fatigue. This paper presents an SSVEP dataset acquired at a wide frequency range from 1 to 60 Hz with an interval of 1 Hz using flickering stimuli under two different modulation depths. This dataset contains 64-channel EEG data from 30 healthy subjects when they fixated on a single flickering stimulus. The stimulus was rendered on an LCD display with a refresh rate of 240 Hz. Initially, the dataset was rigorously validated through comprehensive data analysis to investigate SSVEP responses and user experiences. Subsequently, BCI performance was evaluated through offline simulations of frequency-coded and phase-coded BCI paradigms. This dataset provides comprehensive and high-quality data for studying and developing SSVEP-based BCI systems.

An Adaptive Hybrid Brain Computer Interface for Hand Function Rehabilitation of Stroke Patients.

Motor imagery (MI) based brain computer interface (BCI) has been extensively studied to improve motor recovery for stroke patients by inducing neuroplasticity. However, due to the lower spatial resolution and signal-to-noise ratio (SNR) of electroencephalograph (EEG), MI based BCI system that involves decoding hand movements within the same limb remains lower classification accuracy and poorer practicality. To overcome the limitations, an adaptive hybrid BCI system combining MI and steady-state visually evoked potential (SSVEP) is developed to improve decoding accuracy while enhancing neural engagement. On the one hand, the SSVEP evoked by visual stimuli based on action-state flickering coding approach significantly improves the recognition accuracy compared to the pure MI based BCI. On the other hand, to reduce the impact of SSVEP on MI due to the dual-task interference effect, the event-related desynchronization (ERD) based neural engagement is monitored and employed for feedback in real-time to ensure the effective execution of MI tasks. Eight healthy subjects and six post-stroke patients were recruited to verify the effectiveness of the system. The results showed that the four-class gesture recognition accuracies of healthy individuals and patients could be improved to 94.37 ± 4.77% and 79.38 ± 6.26%, respectively. Moreover, the designed hybrid BCI could maintain the same degree of neural engagement as observed when subjects solely performed MI tasks. These phenomena demonstrated the interactivity and clinical utility of the developed system for the rehabilitation of hand function in stroke patients.

Optimizing Visual Stimulation Paradigms for User-Friendly SSVEP-Based BCIs.

In steady-state visual evoked potential (SSVEP)-based brain-computer interface (BCI) systems, traditional flickering stimulation patterns face challenges in achieving a trade-off in both BCI performance and visual comfort across various frequency bands. To investigate the optimal stimulation paradigms with high performance and high comfort for each frequency band, this study systematically compared the characteristics of SSVEP and user experience of different stimulation paradigms with a wide stimulation frequency range of 1-60 Hz. The findings suggest that, for a better balance between system performance and user experience, ON and OFF grid stimuli with a Weber contrast of 50% can be utilized as alternatives to traditional flickering stimulation paradigms in the frequency band of 1-25 Hz. In the 25-35 Hz range, uniform flicker stimuli with the same 50% contrast are more suitable. In the higher frequency band, traditional uniform flicker stimuli with a high 300% contrast are preferred. These results are significant for developing high performance and user-friendly SSVEP-based BCI systems.

A Gait Imagery-Based Brain-Computer Interface with Visual feedback for Spinal Cord Injury Rehabilitation on Lokomat.

Motor Imagery (MI)-based Brain-Computer Interfaces (BCIs) have been proposed for the rehabilitation of people with disabilities, being a big challenge their successful application to restore motor functions in individuals with Spinal Cord Injury (SCI). This work proposes an Electroencephalography (EEG) gait imagery-based BCI to promote motor recovery on the Lokomat platform, in order to allow a clinical intervention by acting simultaneously on both central and peripheral nervous mechanisms. As a novelty, our BCI system accurately discriminates gait imagery tasks during walking and further provides a multi-channel EEG-based Visual Neurofeedback (VNFB) linked to μ (8-12 Hz) and β (15-20 Hz) rhythms around Cz. VNFB is carried out through a cluster analysis strategy-based Euclidean distance, where the weighted mean MI feature vector is used as a reference to teach individuals with SCI to modulate their cortical rhythms. The developed BCI reached an average classification accuracy of 74.4%. In addition, feature analysis demonstrated a reduction in cluster variance after several sessions, whereas metrics associated with self-modulation indicated a greater distance between both classes: passive walking with gait MI and passive walking without MI. The results suggest that intervention with a gait MI-based BCI with VNFB may allow the individuals to appropriately modulate their rhythms of interest around Cz. This work contributes to the development of advanced systems for gait rehabilitation by integrating Machine Learning and neurofeedback techniques, to restore lower-limb functions of SCI individuals.

Optimized CNN‐Bi‐LSTM–Based BCI System for Imagined Speech Recognition Using FOA‐DWT

Speech imagery is emerging as a significant neuro‐paradigm for designing an electroencephalography (EEG)‐based brain–computer interface (BCI) system for the purpose of rehabilitation, medical neurology, and to aid people with disabilities in interacting with their surroundings. Neural correlates of speech imagery EEG signals are variable and weak as compared to the vocal state; hence, it is challenging to interpret them using machine learning (ML)–based classifiers. The applicability of modern deep learning methods such as convolutional neural networks (CNNs) and bidirectional long short‐term memory (Bi‐LSTM) networks has seen substantial advances in complex EEG signal analysis as compared to ML‐based methods. The objective of this article is to design a firefly‐optimized discrete wavelet transform (DWT) and CNN‐Bi‐LSTM–based imagined speech recognition (ISR) system to interpret imagined speech EEG signals. This study utilizes two publicly available datasets. EEG signal is enhanced using firefly optimization algorithm (FOA)–based optimized soft thresholding of high‐frequency detail components obtained by DWT decomposition. The enhanced EEG signal is augmented using sliding window data augmentation to increase the training data. Frequency‐domain features like power spectral density (PSD), frequency band power (FBP), band ratios, peak frequency, mean frequency, median frequency, spectral entropy, and relative power are extracted from augmented EEG segments. The extracted feature vector is fed to the designed CNN‐Bi‐LSTM classifier such that the EEG data are classified into two‐class, three‐class, and four‐class categories. To achieve optimal performance, the CNN‐Bi‐LSTM model was optimized using the Keras tuner library. The designed CNN consists of one‐dimensional (1‐D) convolutional layers and max pooling layers for familiarizing local associations along with mining hierarchical connections, and the Bi‐LSTM network acquires long‐term dependencies from the features learned by the former CNN. Bi‐LSTM network improves the performance and acquires potentially more affluent representations by looking at the sequence in both forward and reverse ways to capture representations that might be left unexploited by the sequential‐order kind alone. The performance of the designed FOA‐DWT‐CNN‐Bi‐LSTM–based ISR system is assessed using four evaluation measures: accuracy, F1 score, recall, and precision. It is found that the proposed system achieves the highest classification accuracy of 99.43 ± 2.5%, 94.41 ± 3.31%, and 89.57 ± 4.3% for two‐class, three‐class, and four‐class categories, respectively.

Variance characteristic preserving common spatial pattern for motor imagery BCI.

The common spatial patterns (CSP) algorithm is the most popular technique for extracting electroencephalogram (EEG) features in motor imagery based brain-computer interface (BCI) systems. CSP algorithm embeds the dimensionality of multichannel EEG data to extract features of motor imagery tasks. Most previous studies focused on the optimization of the time domain and the spectrum domain of EEG signal to improve the effectiveness of CSP, whereas ignoring the constraint on the projected feature space. This study proposed a variance characteristic preserving CSP (VPCSP) that is modified by a regularization item based on graph theory. Specifically, we calculated the loss of abnormalities of the projected data while preserving the variance characteristic locally. Then the loss could be rewritten as a matrix with the introduction of the Laplace matrix, which turned it into a generalized eigenvalue problem equivalent to CSP. This study evaluated the proposed method on two public EEG datasets from the BCI competition. The modified method could extract robust and distinguishable features that provided higher classification performance. Experimental results showed that the proposed regularization improved the effectiveness of CSP significantly and achieved superior performance compared with reported modified CSP algorithms significantly. The classification accuracy of the proposed method achieved 87.88 %, 90.07 %, and 76.06 % on public dataset IV part I, III part IVa and the self-collected dataset, respectively. Comparative experiments are conducted on two public datasets and one self-collected dataset. Results showed that the proposed method outperformed the reported algorithm. The proposed method can extract robust features to increase the performance of BCI systems. And the proposal still has expandability. These results show that our proposal is a promising candidate for the performance improvement of MI-BCI.

Quantification of event related brain patterns for the motor imagery tasks using inter-trial variance technique

Quantification of event-related (de) synchronization (ERD/ERS) patterns is a challenging task in the field of motor imagery (MI)-based brain–computer interface (BCI). Accurately determining the optimal time and frequency band for localizing the ERD/ERS brain patterns is crucial in designing a robust MI-based BCI. To address above issue, this study proposes an inter-trial variance (IV) technique that focuses on localizing the ERD/ERS brain patterns and classifying the left and right hand imaginations of the subjects. The effectiveness of the proposed technique is validated using the BCI Competition-IV, Dataset-2b, which includes raw EEG signals from nine healthy subjects performing both left and right hand MI movements. In this technique, the sensorimotor frequency band (8–30 Hz) and its ERD/ERS brain patterns related to the left and right hand MI movements are derived from the signals. The obtained brain patterns are fed into various ML models, and the efficiency of the models is assessed using the classification accuracy (%CA) and Cohen’s kappa coefficient (K). The outcomes show that the proposed technique enhances the performance of the BCI system, classifying both left and right hand imaginations of the subjects with higher %CA (86.11%) and K (0.72), and outperforming the state-of-the-art techniques. This concludes that the ERD and ERS brain patterns extracted from the proposed technique are significant features in designing the MI-based BCI system.

A high-frequency SSVEP-BCI system based on a 360 Hz refresh rate.

Objective. Steady-state visual evoked potential (SSVEP) based brain-computer interfaces (BCIs) often struggle to balance user experience and system performance. To address this challenge, this study employed stimuli in the 55-62.8 Hz frequency range to implement a 40-target BCI speller that offered both high-performance and user-friendliness.Approach. This study proposed a method that presents stable multi-target stimuli on a monitor with a 360 Hz refresh rate. Real-time generation of stimulus matrix and stimulus rendering was used to ensure stable presentation while reducing the computational load. The 40 targets were encoded using the joint frequency and phase modulation method, offline and online BCI experiments were conducted on 16 subjects using the task discriminant component analysis algorithm for feature extraction and classification.Main results. The online BCI system achieved an average accuracy of 88.87% ± 3.05% and an information transfer rate of 51.83 ± 2.77 bits min-1under the low flickering perception condition.Significance. These findings suggest the feasibility and significant practical value of the proposed high-frequency SSVEP BCI system in advancing the visual BCI technology.

Subject-Invariant Deep Neural Networks based on Baseline Correction for EEG Motor Imagery BCI.

Electroencephalography (EEG)-based brain-computer interface (BCI) systems have been extensively used in various applications, such as communication, control, and rehabilitation. However, individual anatomical and physiological differences cause subject-specific variability of EEG signals for the same task, and BCI systems thus require a calibration procedure that adjusts system parameters to each subject. To overcome this problem, we propose a subject-invariant deep neural network (DNN) using baseline-EEG signals that can be recorded from subjects resting in comfortable states. We first modeled the deep features of EEG signals as a decomposition of subject-invariant and subject-variant features corrupted by anatomical/physiological characteristics. Subject-variant features were then removed from the deep features by learning the network with a baseline correction module (BCM) using the underlying individual information in baseline-EEG signals. The subject-invariant loss forces the BCM to assemble subject-invariant features that have the same class, irrespective of the subject. Using 1-min baseline-EEG signals of the new subject, our algorithm can eliminate subject-variant components from test data without the calibration process. The experimental results show that our subject-invariant DNN framework significantly increases decoding accuracies of the conventional DNN methods for BCI systems. Furthermore, feature visualizations illustrate that the proposed BCM extracts subject-invariant features that are close to each other in the same class.

Implicit Robot Control Using Error-Related Potential-Based Brain–Computer Interface

This article investigates the application of using error-related potential (ErrP)-based brain–computer interface (BCI) paradigm to control robot movements with implicit commands. ErrP is a neural signal that is automatically evoked when the machine’s behavior deviates from the observer’s expectations. By continuously monitoring the presence of ErrP, the system infers the observer’s reaction toward robot movements and automatically translates them into control commands, allowing the implicit control of robot movements without interfering the observer’s other tasks. However, ErrP-based BCI has a major limitation: the ErrP is evoked after the robot has committed an error, which might be costly or dangerous in contexts, such as assembly line or autonomous driving. To address these limitations, we propose a novel robotic design for ErrP-based BCI that allows humans to continuously evaluate the robot’s intentions and intervene earlier, if necessary before the robot commits an error. We evaluate the proposed robotic design and BCI system via an experiment where a ground robot performs a binary target-reaching task. The high classification accuracy (77.57%) demonstrated that the proposed ErrP-based BCI is feasible for human–robot intention communication before the robot commits an error and has the potential to broaden the range of applications for ErrP-based BCIs.