Brain-computer Interface System Research Articles

A Combined Virtual Electrode-Based ESA and CNN Method for MI-EEG Signal Feature Extraction and Classification.

A Brain-Computer Interface (BCI) is a medium for communication between the human brain and computers, which does not rely on other human neural tissues, but only decodes Electroencephalography (EEG) signals and converts them into commands to control external devices. Motor Imagery (MI) is an important BCI paradigm that generates a spontaneous EEG signal without external stimulation by imagining limb movements to strengthen the brain's compensatory function, and it has a promising future in the field of computer-aided diagnosis and rehabilitation technology for brain diseases. However, there are a series of technical difficulties in the research of motor imagery-based brain-computer interface (MI-BCI) systems, such as: large individual differences in subjects and poor performance of the cross-subject classification model; a low signal-to-noise ratio of EEG signals and poor classification accuracy; and the poor online performance of the MI-BCI system. To address the above problems, this paper proposed a combined virtual electrode-based EEG Source Analysis (ESA) and Convolutional Neural Network (CNN) method for MI-EEG signal feature extraction and classification. The outcomes reveal that the online MI-BCI system developed based on this method can improve the decoding ability of multi-task MI-EEG after training, it can learn generalized features from multiple subjects in cross-subject experiments and has some adaptability to the individual differences of new subjects, and it can decode the EEG intent online and realize the brain control function of the intelligent cart, which provides a new idea for the research of an online MI-BCI system.

Editorial: The application of artificial intelligence in brain-computer interface and neural system rehabilitation

Editorial: The application of artificial intelligence in brain-computer interface and neural system rehabilitation

Stable Decoding from a Speech BCI Enables Control for an Individual with ALS without Recalibration for 3 Months.

Brain-computer interfaces (BCIs) can be used to control assistive devices by patients with neurological disorders like amyotrophic lateral sclerosis (ALS) that limit speech and movement. For assistive control, it is desirable for BCI systems to be accurate and reliable, preferably with minimal setup time. In this study, a participant with severe dysarthria due to ALS operates computer applications with six intuitive speech commands via a chronic electrocorticographic (ECoG) implant over the ventral sensorimotor cortex. Speech commands are accurately detected and decoded (median accuracy: 90.59%) throughout a 3-month study period without model retraining or recalibration. Use of the BCI does not require exogenous timing cues, enabling the participant to issue self-paced commands at will. These results demonstrate that a chronically implanted ECoG-based speech BCI can reliably control assistive devices over long time periods with only initial model training and calibration, supporting the feasibility of unassisted home use.

EEG-BCI Features Discrimination between Executed and Imagined Movements Based on FastICA, Hjorth Parameters, and SVM

Brain–Computer Interfaces (BCIs) communicate between a given user and their nearest environment through brain signals. In the case of device handling, an accurate control-based BCI depends essentially on how the user performs corresponding mental tasks. In the BCI illiteracy-related literature, one subject could perform a defined paradigm better than another. Therefore, this work aims to identify recorded Electroencephalogram (EEG) signal segments related to the executed and imagined motor tasks for BCI system applications. The proposed approach implements pass-band filters and the Fast Independent Component Analysis (FastICA) algorithm to separate independent sources from raw EEG signals. Next, EEG features of selected channels are extracted using Hjorth parameters. Finally, a Support Vector Machines (SVMs)-based classifier identifies executed and imagined motor features. Concretely, the Physionet dataset, related to executed and imagined motor EEG signals, provided training, testing, and validating data. The numerical results let us discriminate between executed and imagined motor tasks accurately. Therefore, the proposed method offers a reliable alternative to extract EEG features for BCI based on executed and imagined movements.

Farklı performans ölçümleri kullanılarak kararlı durum görsel uyarılmış potansiyel kontrollü quadcopter yolunun değerlendirilmesi

This study focuses on controlling a quadcopter system using a steady-state visual evoked potential (SSVEP)-based brain-computer interface system. In the literature, researchers report the accuracy and information transfer rate. However, these measures do not provide sufficient information about the predicted and target path similarity. The drone is expected to follow a certain square-shaped path and return to its starting position. We calculated the final and mean distances as additional outcome measures using several classifiers. The results emphasize the importance of having a balanced confusion matrix in the performance of quadcopter control and provide a more complete picture in the evaluation of the quadcopter’s performance. Focusing on the relationship between classification accuracy and spatial deviation might create a new perspective for BCI-based control systems.

Classifying human emotions in HRI: applying global optimization model to EEG brain signals.

Significant efforts have been made in the past decade to humanize both the form and function of social robots to increase their acceptance among humans. To this end, social robots have recently been combined with brain-computer interface (BCI) systems in an attempt to give them an understanding of human mental states, particularly emotions. However, emotion recognition using BCIs poses several challenges, such as subjectivity of emotions, contextual dependency, and a lack of reliable neuro-metrics for real-time processing of emotions. Furthermore, the use of BCI systems introduces its own set of limitations, such as the bias-variance trade-off, dimensionality, and noise in the input data space. In this study, we sought to address some of these challenges by detecting human emotional states from EEG brain activity during human-robot interaction (HRI). EEG signals were collected from 10 participants who interacted with a Pepper robot that demonstrated either a positive or negative personality. Using emotion valence and arousal measures derived from frontal brain asymmetry (FBA), several machine learning models were trained to classify human's mental states in response to the robot personality. To improve classification accuracy, all proposed classifiers were subjected to a Global Optimization Model (GOM) based on feature selection and hyperparameter optimization techniques. The results showed that it is possible to classify a user's emotional responses to the robot's behavior from the EEG signals with an accuracy of up to 92%. The outcome of the current study contributes to the first level of the Theory of Mind (ToM) in Human-Robot Interaction, enabling robots to comprehend users' emotional responses and attribute mental states to them. Our work advances the field of social and assistive robotics by paving the way for the development of more empathetic and responsive HRI in the future.

A hybrid BCI combining SSVEP and EOG and its application for continuous wheelchair control

Brain-computer interfaces (BCIs) have emerged as one of the most promising techniques for individuals with motor disabilities to control external devices directly without peripheral pathways. While the discrete control strategy is widely adopted in BCI systems, the continuous control strategy provides intuitive and fluent control of robotic devices. However, the steady-state visual evoked potential (SSVEP)-based BCI is still far from practical applications of continuous control. One of the existing challenges is the long erroneous transition time, i.e., the duration from when the subject switches towards a new target to when the BCI system recognizes this new target. Therefore, this study proposed a hybrid BCI combining SSVEP and electrooculography (EOG). First, the prior probability distribution of the intended target was obtained by the SSVEP detection method. Different from directly picking the one with the maximum probability as the conventional SSVEP-based BCI did, the captured saccade event in the EOG signal served as an additional event to optimize this probability distribution, and the target was then extrapolated and outputted. An offline experiment simulating the target switching process and an online experiment of virtual wheelchair control were designed and conducted. The proposed hybrid BCI significantly outperformed the conventional SSVEP-based BCI in both the offline experiment (continuous accuracy:64.99 ± 3.44 % vs. 55.76 ± 3.67 %, transition time: 1.19 ± 0.073 s vs. 1.65 ± 0.08 s) and the online wheelchair control experiment (success rate: 81.67 ± 5.75 % vs. 16.67 %± 3.76 %; collision times with the dynamic obstacle: 1.50 ± 0.50 vs. 8.25 ± 0.37; minimum distance to dynamic obstacle: 1.41 ± 0.13 m vs. 0.31 ± 0.08 m). The results revealed that by combining the SSVEP and EOG signals, the proposed hybrid BCI can significantly diminish the transition time in SSVEP-based BCI and achieve continuous, fluent control. The present study provides a novel framework for integrating the SSVEP and EOG, and promotes the potential applications of continuous brain-actuated robotic devices.

Research on emotion recognition of bimodal bioelectrical features based on D-S evidence theory

As the pace of life becomes faster and faster, people with weaker mental capacity are prone to a range of negative emotions in certain environments, such as mania and anxiety, and these negative emotions can interfere with normal learning and life, and even affect physical and mental health. Therefore, it is more and more important to accurately analyze people's emotional state.In this paper, based on the bimodal signals of EEG and EMG, we combine the broad learning network and D-S evidence theory to do an emotion recognition analysis of bioelectrical signals evoked by visual stimuli. Firstly, a suitable experimental paradigm is designed to acquire EEG signals and EMG signals through emotion evocation, followed by pre-processing, decomposing the signals using a wavelet decomposition algorithm, extracting signal components significantly affected by emotional states, and calculating the corresponding differential entropy as well as power spectrum features; after that, EMG features in time and frequency domains are extracted, and different features are fused and analyzed; BLS is used for classification, and finally, the BLS classification The results are fused with the introduced D-S evidence theory at the decision level. The method can recognize emotions effectively with an accuracy of 85.2% in triple classification scenarios. The proposed emotion recognition model is expected to provide a new technical tool for emotional cognitive science research and emotional brain-computer interface systems.

Silent EEG classification using cross-fusion adaptive graph convolution network for multilingual neurolinguistic signal decoding

Brain–computer interface (BCI) based multilingual silent reading electroencephalography (EEG) decoding technology provides a convenient and fast communication method for multilingual patients with language disorders. Developing a silent reading EEG signals decoding method that can be applied to multiple languages, it is necessary not only to select the appropriate feature channels for each language but also to distinguish the spatial and temporal relationships between each channel. The existing graph convolution network that learns the characteristics and connections of each node on a fixed graph is inadequate to capture both the temporal and spatial relationships between each channel. Therefore, we use a feature matrix and its adaptive graph to represent each EEG signal and propose a Cross-fusion Adaptive Graph Convolution Network (CFA-GCN) for decoding. We collect novel EEG signal datasets of a subject who silently read 7 Chinese and 9 English words over 26 days, which can be used for further research and development of BCI systems. The proposed method achieves state-of-the-art performance with 45.30% and 47.62% decoding accuracy for silent reading EEG signals of English and Chinese words, respectively. This work demonstrates the feasibility of decoding silent reading EEG signals from bilingual words. The CFA-GCN demonstrates the potential of utilizing Brain–computer Interface (BCI) systems to facilitate effective communication for patients with multilingual impairments.

Antioxidant Dimethyl Fumarate Temporarily but Not Chronically Improves Intracortical Microelectrode Performance.

Intracortical microelectrode arrays (MEAs) can be used in a range of applications, from basic neuroscience research to providing an intimate interface with the brain as part of a brain-computer interface (BCI) system aimed at restoring function for people living with neurological disorders or injuries. Unfortunately, MEAs tend to fail prematurely, leading to a loss in functionality for many applications. An important contributing factor in MEA failure is oxidative stress resulting from chronically inflammatory-activated microglia and macrophages releasing reactive oxygen species (ROS) around the implant site. Antioxidants offer a means for mitigating oxidative stress and improving tissue health and MEA performance. Here, we investigate using the clinically available antioxidant dimethyl fumarate (DMF) to reduce the neuroinflammatory response and improve MEA performance in a rat MEA model. Daily treatment of DMF for 16 weeks resulted in a significant improvement in the recording capabilities of MEA devices during the sub-chronic (Weeks 5-11) phase (42% active electrode yield vs. 35% for control). However, these sub-chronic improvements were lost in the chronic implantation phase, as a more exacerbated neuroinflammatory response occurs in DMF-treated animals by 16 weeks post-implantation. Yet, neuroinflammation was indiscriminate between treatment and control groups during the sub-chronic phase. Although worse for chronic use, a temporary improvement (<12 weeks) in MEA performance is meaningful. Providing short-term improvement to MEA devices using DMF can allow for improved use for limited-duration studies. Further efforts should be taken to explore the mechanism behind a worsened neuroinflammatory response at the 16-week time point for DMF-treated animals and assess its usefulness for specific applications.

UAV Target Detection for IoT via Enhancing ERP Component by Brain–Computer Interface System

The increasing popularity of Internet of Things (IoT) devices provides a huge data source for intelligent identification. Images captured by unmanned aerial vehicle (UAV) are often exploited in target detection missions for search, rescue and fire prevention. However, without sufficient training samples, the machine learning method is usually difficult to meet application requirements. To solve the problem, a brain-computer interface (BCI) real-time system is applied to UAV target detection. In this study, a novel rapid serial visual presentation (RSVP) paradigm was formulated to present images, enhancing the ability for wide-area target detection. Since there is spatial correlation in captured images, joint decision for identical target can improve the recognition efficiency. To suppress interfering components and improve event-related potential (ERP) detection efficiency, an enhancing ERP component (EEC) algorithm is proposed. Both decision method and EEC algorithm are based on strictly statistical theory. RSVP task was performed by 12 subjects. The interference components and noise correlation were significantly reduced by EEC algorithm. The target detection rate online was 86.6% while the false alarm rate was less than 5%. Besides, the joint decision strategy raised the area under curve (AUC) value from 0.876 to 0.963. The proposed BCI real-time system realizes the complementarity of human intelligence and IoT, ushering UAV target detection into the era of hybrid intelligence.

Multimodal Social Data Analytics on the Design and Implementation of an EEG-Mechatronic System Interface

The devices that can read Electroencephalography (EEG) signals have been widely used for Brain-Computer Interfaces (BCIs). Popularity in the field of BCIs has increased in recent years with the development of several consumer-grade EEG devices that can detect human cognitive states in real-time and deliver feedback to enhance human performance. Several previous studies have been conducted to understand the fundamentals and essential aspects of EEG in BCIs. However, the significant issue of how consumer-grade EEG devices can be used to control mechatronic systems effectively has been given less attention. In this article, we have designed and implemented an EEG BCI system using the OpenBCI Cyton headset and a user interface running a game to explore the concept of streamlining the interaction between humans and mechatronic systems with a BCI EEG-mechatronic system interface. Big Multimodal Social Data (BMSD) analytics can be applied to the high-frequency and high-volume EEG data, allowing us to explore aspects of data acquisition, data processing, and data validation and evaluate the Quality of Experience (QoE) of our system. We employ real-world participants to play a game to gather training data that was later put into multiple machine learning models, including a linear discriminant analysis (LDA), k-nearest neighbours (KNN), and a convolutional neural network (CNN). After training the machine learning models, a validation phase of the experiment took place where participants tried to play the same game but without direct control, utilising the outputs of the machine learning models to determine how the game moved. We find that a CNN trained to the specific user was able to control the game and performed with the highest activation accuracy from the machine learning models tested, along with the highest user-rated QoE, which gives us significant insight for future implementation with a mechatronic system.

Effectiveness of motor and prefrontal cortical areas for brain-controlled functional electrical stimulation neuromodulation

Objective. Brain-computer interface (BCI)-controlled functional electrical stimulation (FES) could excite the central nervous system to enhance upper limb motor recovery. Our current study assessed the effectiveness of motor and prefrontal cortical activity-based BCI-FES to help elucidate the underlying neuromodulation mechanisms of this neurorehabilitation approach. Approach. The primary motor cortex (M1) and prefrontal cortex (PFC) BCI-FES interventions were performed for 25 min on separate days with twelve non-disabled participants. During the interventions, a single electrode from the contralateral M1 or PFC was used to detect event-related desynchronization (ERD) in the calibrated frequency range. If the BCI system detected ERD within 15 s of motor imagery, FES activated wrist extensor muscles. Otherwise, if the BCI system did not detect ERD within 15 s, a subsequent trial was initiated without FES. To evaluate neuromodulation effects, corticospinal excitability was assessed using single-pulse transcranial magnetic stimulation, and cortical excitability was assessed by motor imagery ERD and resting-state functional connectivity before, immediately, 30 min, and 60 min after each intervention. Main results. M1 and PFC BCI-FES interventions had similar success rates of approximately 80%, while the M1 intervention was faster in detecting ERD activity. Consequently, only the M1 intervention effectively elicited corticospinal excitability changes for at least 60 min around the targeted cortical area in the M1, suggesting a degree of spatial localization. However, cortical excitability measures did not indicate changes after either M1 or PFC BCI-FES. Significance. Neural mechanisms underlying the effectiveness of BCI-FES neuromodulation may be attributed to the M1 direct corticospinal projections and/or the closer timing between ERD detection and FES, which likely enhanced Hebbian-like plasticity by synchronizing cortical activation detected by the BCI system with the sensory nerve activation and movement related reafference elicited by FES.

Cross-Subject EEG Channel Selection Method for Lower Limb Brain-Computer Interface

Article Cross-Subject EEG Channel Selection Method for Lower Limb Brain-Computer Interface Mingnan Wei 1,2, Mengjie Huang 3,*, and Jiaying Ni 3 1 School of Advanced Technology, Xi'an Jiaotong-Liverpool University, Suzhou, 215123, China 2 Department of Computer Science, University of Liverpool, Liverpool, L69 3BX, United Kingdom 3 Design School, Xi'an Jiaotong-Liverpool University, Suzhou, 215123, China * Correspondence: Mengjie.Huang@xjtlu.edu.cn Received: 27 April 2023 Accepted: 30 June 2023 Published: 26 September 2023 Abstract: Lower limb motor imagery (MI) classification is a challenging research topic in the area of brain-computer interfaces (BCIs), and entails numerous signal channels to provide sufficient information about the background neural activity. However, practical applications often lack the environment to accommodate excessive channels due to the time-consuming setup process, inconvenient movement, and restricted application scenarios. The existing channel selection algorithms (designed for the individual subject) place a great deal of focus on the classified performance comparisons, whereas the significance of actual locations and neural functions of brain regions is disregarded. Although these algorithms require significant computation resources, their selected solutions cannot be re-used for other subjects to realize the cross-subject channel selection and improve the reusability of model due to poor interpretability and inapplicability. To date, there have been no investigations about the cross-subject channel selection problem for the lower limb MI stepping tasks. This study proposes an optimal cross-subject lower limb channel selection that selectively retains significant channels, narrows the computation scope of the selection, and obtains the optimal selection solutions. Through stepping-based MI experiments, the proposed optimal channel selection enables effective recognition in low-channel settings, thereby contributing a lot to the development of generic and convenient lower limb BCI systems. Additionally, statistical analysis reveals a significant difference in energy spectrum between left and right stepping-based MI tasks in the and bands of the frontal lobe channels, providing new evidence that the frontal lobe dramatically affects lower limb MI tasks.

Brain-Computer Integration: A Framework for the Design of Brain-Computer Interfaces from an Integrations Perspective

Brain-computer interface (BCI) systems hold the potential to foster human flourishing and self-actualization. However, we believe contemporary BCI system design approaches unnecessarily limit these potentialities as they are approached from a traditional interaction perspective, producing command-response experiences. This article proposes to go beyond “interaction” and toward a paradigm of human-computer integration. The potential of this paradigm is demonstrated through three prototypes: Inter-Dream, a system that integrates with the brain's autonomic physiological processes to drive users toward healthy sleep states; Neo-Noumena, a system that integrates with the user's affective neurophysiology to augment the interpersonal communication of emotion; and PsiNet, a system that integrates interpersonal brain activity to amplify human connection. Studies of these prototypes demonstrate the benefits of the integration paradigm in realizing the multifaceted benefits of BCI systems, and this work presents the brain-computer integration framework to help guide designers of future BCI integrations.

Driving risk cognition of passengers in highly automated driving based on the prefrontal cortex activity via fNIRS

For high-level automated vehicles, the human being acts as the passenger instead of the driver and does not need to operate vehicles, it makes the brain–computer interface system of high-level automated vehicles depend on the brain state of passengers rather than that of drivers. Particularly when confronting challenging driving situations, how to implement the mental states of passengers into safe driving is a vital choice in the future. Quantifying the cognition of the driving risk of the passenger is a basic step in achieving this goal. In this paper, the passengers’ mental activities in low-risk episode and high-risk episode were compared, the influences on passengers’ mental activities caused by driving scenario risk was first explored via fNIRS. The results showed that the mental activities of passengers caused by driving scenario risk in the Brodmann area 10 are very active, which was verified by examining the real-driving data collected in corresponding challenging experiments, and there is a positive correlation between the cerebral oxygen and the driving risk field. This initial finding provides a possible solution to design a human-centred intelligent system to promise safe driving for high-level automated vehicles using passengers’ driving risk cognition.

EEG-FMCNN: A fusion multi-branch 1D convolutional neural network for EEG-based motor imagery classification.

Motor imagery (MI) electroencephalogram (EEG) signal is recognized as a promising paradigm for brain-computer interface (BCI) systems and has been extensively employed in various BCI applications, including assisting disabled individuals, controlling devices and environments, and enhancing human capabilities. The high-performance decoding capability of MI-EEG signals is a key issue that impacts the development of the industry. However, decoding MI-EEG signals is challenging due to the low signal-to-noise ratio and inter-subject variability. In response to the aforementioned core problems, this paper proposes a novel end-to-end network, a fusion multi-branch 1D convolutional neural network (EEG-FMCNN), to decode MI-EEG signals without pre-processing. The utilization of multi-branch 1D convolution not only exhibits a certain level of noise tolerance but also addresses the issue of inter-subject variability to some extent. This is attributed to the ability of multi-branch architectures to capture information from different frequency bands, enabling the establishment of optimal convolutional scales and depths. Furthermore, we incorporate 1D squeeze-and-excitation (SE) blocks and shortcut connections at appropriate locations to further enhance the generalization and robustness of the network. In the BCI Competition IV-2a dataset, our proposed model has obtained good experimental results, achieving accuracies of 78.82% and 68.41% for subject-dependent and subject-independent modes, respectively. In addition, extensive ablative experiments and fine-tuning experiments were conducted, resulting in a notable 7% improvement in the average performance of the network, which holds significant implications for the generalization and application of the network.

Multi-objective squirrel search algorithm for EEG feature selection

Feature selection plays a critical role in the application of Brain Computer Interface (BCI) systems. Many methods have been used to solve the feature selection problem, but they model it as a single-objective problem, considering only classification accuracy or number of features. To close this critical gap, we improve the squirrel search algorithm by combining it with the grid method, and propose a Multi-Objective Squirrel Search Algorithm (MOSSA) to solve the feature selection problem in BCI. We conduct experiments on three publicly available motion imagery datasets, and the experimental results reveal the best classification results of the method on dataset 1. The average classification accuracy of dataset 2 is 96.71%, with the number of selected features reduced to 18 on average. The highest classification accuracy of dataset 3 is 83.57% on the training set and 82.86% on the test set. In addition, we compare MOSSA with other algorithms and the results show the superiority of our proposed method in solving the feature selection problem. Finally, we combine MOSSA with an online application of BCI, where subjects visualize controlling the robot to perform the corresponding actions by the left and right hand movements. The average recognition rate of the three subjects is approximately 70%. In summary, the MOSSA is an effective method for solving the feature selection problem and is useful for the development of online applications of BCI.

Closed loop BCI system for Cybathlon 2020

ABSTRACT We developed a Brain-Computer Interface (BCI) System for the BCI discipline of Cybathlon 2020 competition, where participants with tetraplegia (pilots) control a computer game with mental commands. To extract features from one-second-long electroencephalographic (EEG) signals, we calculated the absolute of the Fast-Fourier Transformation amplitude (FFTabs) and introduced two methods: Feature Average and Feature Range. The former calculates the average of the FFTabs for a specific frequency band, while the later generates multiple Feature Averages for non-overlapping 2 Hz wide frequency bins. The resulting features were fed to a Support Vector Machine classifier and tested on the PhysioNet database and our dataset containing 16 offline experiments recorded with the help of 2 pilots. 27 gameplay trials (out of 59) with our pilots reached the 240-second qualification time limit, which demonstrates the usability of our system in real-time circumstances. We critically compared the Feature Average of canonical frequency bands (alpha, beta, gamma, and theta) with our suggested range30 and range40 methods. On the PhysioNet dataset, the range40 method combined with an ensemble SVM classifier significantly reached the highest accuracy level (0.4607), with a 4-class classification; moreover, it outperformed the state-of-the-art EEGNet.

Ensemble Wavelet Decomposition-Based Detection of Mental States Using Electroencephalography Signals.

Technological advancements in healthcare, production, automobile, and aviation industries have shifted working styles from manual to automatic. This automation requires smart, intellectual, and safe machinery to develop an accurate and efficient brain-computer interface (BCI) system. However, developing such BCI systems requires effective processing and analysis of human physiology. Electroencephalography (EEG) is one such technique that provides a low-cost, portable, non-invasive, and safe solution for BCI systems. However, the non-stationary and nonlinear nature of EEG signals makes it difficult for experts to perform accurate subjective analyses. Hence, there is an urgent need for the development of automatic mental state detection. This paper presents the classification of three mental states using an ensemble of the tunable Q wavelet transform, the multilevel discrete wavelet transform, and the flexible analytic wavelet transform. Various features are extracted from the subbands of EEG signals during focused, unfocused, and drowsy states. Separate and fused features from ensemble decomposition are classified using an optimized ensemble classifier. Our analysis shows that the fusion of features results in a dimensionality reduction. The proposed model obtained the highest accuracies of 92.45% and 97.8% with ten-fold cross-validation and the iterative majority voting technique. The proposed method is suitable for real-time mental state detection to improve BCI systems.