Real-time estimation of EEG-based engagement in different tasks

IntroductionThe application of motor imagery in human–computer interaction and rehabilitative medicine has attracted growing attention due to recent advances in brain–computer interface technologies. However, traditional EEG decoding paradigms based on fixed frequency–band segmentation often exhibit limited performance because they fail to capture individual variability in brain rhythms.MethodsThis work proposes an adaptive method that integrates the sparrow search algorithm (SSA) with Filter Bank Common Spatial Pattern (FBCSP) to optimize sub–band segmentation for motor imagery EEG decoding. SSA adaptively searches for optimal sub–band boundaries, enabling individualized frequency–band selection.ResultsExperiments on the BCI Competition IV 2a dataset under a cross–session evaluation protocol (training on session T, testing on session E) demonstrated that SSA–FBCSP effectively improves frequency–band adaptability. The SSA–FBCSP approach was further combined with Support Vector Machine (SVM), Linear Discriminant Analysis (LDA), and k–Nearest Neighbor (KNN) classifiers to evaluate the influence of different downstream classifiers.ConclusionAmong them, SSA–FBCSP–LDA achieved the best performance, outperforming the conventional uniform sub–band approach by 21.76% and reaching an average accuracy of 89.92%. The adaptively selected sub–bands closely matched the ERD/ERS distribution, confirming the method’s effectiveness in frequency–band optimization. Compared with recent deep–learning–based MI–EEG models, the proposed technique offers a balance of accuracy, interpretability, and computational efficiency, providing a promising direction for personalized brain–computer interface systems.

Brain-computer interfaces (BCIs) were initially created to help individuals with disabilities control devices and communicate without muscle movement. Today, BCIs are used for prosthetic control, cognitive enhancement, and neurological rehabilitation. The BCI system depends on analyzing electroencephalogram (EEG) signals captured from the brain. Decoding these EEG signals is a complex process that combines multiple algorithms to extract meaningful information from these intricate and noisy signals. One of the most popular techniques is the Common Spatial Patterns (CSP), which helps preserve useful and sensitive information. This paper presents an optimized extension of the CSP model for extracting EEG data features in a multiclass setting using Riemannian geometry-based weighting. The use of weighting based on Riemannian geometry enhances the robustness of covariance matrix computation, thereby decreasing the influence of noise that can significantly distort the mean of covariance matrices in the traditional CSP method. The proposed approach is also extended by the integration of a multi-band filter bank, providing a more detailed examination of EEG signals. Three classifiers, Linear Discriminant Analysis (LDA), Random Forest Classifier (RFC), and Multi-Layer Perceptron (MLP), are employed to differentiate features across four motor imagery tasks. LDA achieves an accuracy of 80.40%, while MLP and RFC reach 80.02% and 80.90%, respectively. The results obtained using a majority vote combining the decisions of the three classifiers are 81.83% for accuracy and Recall, 82.74% for precision, and 81.87% for F1-score. The proposed architecture is evaluated using the BCI Competition IV set 2a dataset, proving its effectiveness in EEG signal classification for BCI applications.

Stroke is a life-changing event that can affect the survivors' physical, cognitive and emotional state. Stroke care focuses on helping the survivors to regain their strength; recover as much functionality as possible and return to independent living through rehabilitation therapies. Automated training protocols have been reported to improve the efficiency of the rehabilitation process. These protocols also decrease the dependency of the process on a professional trainer. Brain-Computer Interface (BCI) based systems are examples of such systems where they make use of the motor imagery (MI) based electroencephalogram (EEG) signals to drive the rehabilitation protocols. In this paper, we have proposed the use of well-known machine learning (ML) algorithms, such as, the decision tree (DT), Naive Bayesian (NB), linear discriminant analysis (LDA), support vector machine (SVM), ensemble learning classifier (ELC), and artificial neural network (ANN) for MI wrist dorsiflexion prediction in a BCI assisted stroke rehabilitation study conducted on eleven stroke survivors with either the left or right paresis. The doubling sub-band selection filter bank common spatial pattern (DSBS-FBCSP) has been proposed as feature extractor and it is observed that the ANN based classifier produces the best results.

In brain-computer interface (BCI), feature extraction is the key to the accuracy of recognition. There is important local structural information in the EEG signals, which is effective for classification; and this locality of EEG features not only exists in the spatial channel position but also exists in the frequency domain. In order to retain sufficient spatial structure and frequency information, we use one-versus-rest filter bank common spatial patterns (OVR-FBCSP) to preprocess the data and extract preliminary features. On this basis, we conduct research and discussion on feature extraction methods. One-dimensional feature extraction methods like linear discriminant analysis (LDA) may destroy this kind of structural information. Traditional manifold learning methods or two-dimensional feature extraction methods cannot extract both types of information at the same time. We introduced the bilinear structure and matrix-variate Gaussian model into two-dimensional discriminant locality preserving projection (2DDLPP) algorithm and decompose EEG signals into spatial and spectral parts. Afterwards, the most discriminative features were selected through a weight calculation method. We tested the method on BCI competition data sets 2a, data sets IIIa, and data sets collected by our laboratory, and the results were expressed in terms of recognition accuracy. The cross-validation results were 75.69%, 70.46%, and 54.49%, respectively. The average recognition accuracy of new method is improved by 7.14%, 7.38%, 4.86%, and 3.8% compared to those of LDA, two-dimensional linear discriminant analysis (2DLDA), discriminant locality property projections (DLPP), and 2DDLPP, respectively. Therefore, we consider that the proposed method is effective for EEG classification.

Traditional common spatial pattern (CSP) algorithms for upper limb neural rehabilitation face inherent challenges of overlapping cortical representations and frequency sensitivity, which hinder the decoding performance of motor imagery (MI) electroencephalogram (EEG) signals. To address these issues, this study adopts an improved discriminative filter bank CSP (DFBCSP) framework and applies it to the decoding of upper limb MI-EEG signals, achieving remarkable classification performance. EEG data were acquired from sixteen participants performing two-class (left upper limb flexion-extension vs. relaxing) and three-class (left upper limb flexion vs. right upper limb extension vs. relaxing) MI tasks. The acquired EEG data were then decomposed into nine distinct sub-bands, followed by the adoption of a mutual information-based feature selection strategy to optimize the feature sets. These optimized feature sets were subsequently input into three classification models, namely multilayer perceptron (MLP), support vector machine (SVM), and linear discriminant analysis (LDA), for MI task classification. Experimental results demonstrate that the DFBCSP + MLP method significantly outperforms the traditional CSP approach. Specifically, it achieves an accuracy of 94.83% (Kappa coefficient: 0.890) in two-class MI tasks and 86.20% (Kappa coefficient: 0.775) in three-class MI tasks. The DFBCSP + MLP framework exhibits high robustness and provides a potential technical framework and theoretical basis for future research on the rehabilitation of patients with upper limb motor dysfunction.

Electroencephalogram (EEG) based motor imagery (MI) brain-computer interface (BCI) has emerged as a promising tool for communication and control. Most MI classification methods use fixed-length time windows to intercept signals and perform subsequent analyses. However, the fixed-length time window interception method can not achieve optimal performance due to significant differences in the multiple imagining tasks of the same subject. In this paper, we present a novel interception method using long and short windows (LSWs). This method takes advantage of the subject’s motor imaginary strength at different times of the task to select specific time windows corresponding to the most salient features. The features corresponding to the selected time windows are used for the final MI classification. We compare the proposed LSW interception method with the fixed-length time window method on a public EEG dataset (BCI competition IV dataset 1) and a self-collected dataset. The results show that the classification accuracies are improved with the LSW interception method on both datasets. When using the support vector machine (SVM) classifier, the classification accuracy of common spatial pattern with the LSW method achieves 2.57% and 1.12% improvement on two datasets, respectively, and the classification accuracy of filter bank common spatial pattern (FBCSP) with the LSW method achieves 0.93% and 1.48% improvement, respectively. Among them, the classification accuracy of the LSW method with FBCSP and SVM is the highest, which is 93.43% and 91.12%, respectively. Compared with the traditional methods, this method significantly increases the classification accuracy and provides a new idea for researching the MI classification method in BCI.

Event-related potentials (ERPs) are one of the most popular control signals for brain-computer interfaces (BCIs). However, they are very weak and sensitive to the experimental settings including paradigms, stimulation parameters and even surrounding environments, resulting in a diversity of ERP patterns across different BCI experiments. It's still a challenge to develop a general decoding algorithm that can adapt to the ERP diversities of different BCI datasets with small training sets. This study compared a recently developed algorithm, i.e., discriminative canonical pattern matching (DCPM), with seven ERP-BCI classification methods, i.e., linear discriminant analysis (LDA), stepwise LDA, bayesian LDA, shrinkage LDA, spatial-temporal discriminant analysis (STDA), xDAWN and EEGNet for the single-trial classification of two private EEG datasets and three public EEG datasets with small training sets. The feature ERPs of the five datasets included P300, motion visual evoked potential (mVEP), and miniature asymmetric visual evoked potential (aVEP). Study results showed that the DCPM outperformed other classifiers for all of the tested datasets, suggesting the DCPM is a robust classification algorithm for assessing a wide range of ERP components.

Objective. A visual stimulator plays a vital part in brain–computer interfaces (BCIs) based on steady-state visual evoked potential (SSVEP). The properties of visual stimulation, such as frequency, color, and waveform, will influence SSVEP-based BCI performance to some extent. Recently, the computer monitor serves as a visual stimulator that is widespread in SSVEP-based BCIs because of its great flexibility in generating visual stimuli. However, stimulation properties based on a computer monitor have received very little attention. For a better comprehension of SSVEPs, this study explored the stimulation effects of waveforms and frequencies, when evoking SSVEPs through a computer monitor. Approach. This study utilized the approximation methods to realize sine- and square-wave temporal modulations at 18 stimulation frequencies ranging from 6 to 40 Hz on a conventional 120 Hz LCD screen. We collected electroencephalogram (EEG) datasets from 12 healthy subjects and compared the signal-to-noise ratios (SNRs), amplitudes, and topographic mapping of SSVEPs evoked by these two temporal modulation flickers (sine- and square-wave). In addition, a BCI experiment with two nine-target BCIs (i.e. low-frequency BCI and high-frequency BCI) was implemented to compare the two stimulation waveforms in terms of BCI performance. Main results. For both sine- and square-wave stimulation conditions, strong SSVEPs over the occipital area were observed for each stimulation frequency. SSVEP amplitudes at the stimulation frequency exhibited a global peak in the low-frequency band. The second harmonic SSVEP frequency-response functions showed the largest amplitude at 6 Hz and fell sharply for higher frequencies. In the BCI experiment, the classification performance of the square-wave stimuli was notably higher than that of the sine-wave stimuli when using shorter data lengths. Significance. These results suggested that the square-wave flicker was more efficient at implementing high-speed BCIs based on SSVEP when using a computer monitor as a visual stimulator.

The performance of an EEG-based brain-computer interface (BCI) system is highly dependent on signal preprocessing. This manuscript presents a filtering method to improve the feature classification algorithms typically used in BCI. A graph Laplacian quadratic form using the Phase Locking Value (PLV) is applied to generate a new filtered signal in the preprocessing stage. The accuracy of the classification algorithms improved significantly (up to 27.18% in the BCI Competition IV dataset, and up to 42.56% with records made with an Emotiv EPOC+). In addition, the proposed filtering algorithm has similar or better results when compared with the Filter Bank Common Spatial Pattern (FBCSP), which has disadvantages in a multiclass classification. This paper shows how our PLV-based filtering between EEG channels could improve the performance of a BCI.

The notion of developing thought controlled devices (games, robots, cars etc.) is becoming increasingly popular with the introduction of low cost commercial headsets that record neuroelectric activity and the extensive research in the area of Brain Computer Interfaces (BCIs). In this paper, we study the feasibility of using a commercial low cost EEG amplifier which has only limited number of electrodes, to develop a motor control BCI system. The objective is to extract brain activity responsible for direction specific imagined and executed motor activity, which can be used to identify the motor task performed by the user using the simultaneously recorded EEG. An experiment is conducted to engage the user in bi-directional horizontal movement execution and imagination of the dominant hand. The analysis includes investigation of the time-frequency bins of the recorded EEG that provides maximum discrimination of directional movement. Further, the features are extracted using Filter Bank Common Spatial Pattern (FBCSP), followed by Fisher Linear Discriminant (FLD) for classification. The classification performance at various time instants of each trial are considered, and a control strategy was introduced at the classifier output to enhance performance. The performance in terms of average classification accuracy over five subjects is obtained as 81.3 % (movement execution) and 82.4 % (movement imagination). The results indicate the applicability of this EEG-BCI system to provide directional motor control to an interfaced device such as a robotic arm or a game element.

Brain-computer interface (BCI) systems are proposed as a means of communication for locked-in patients. One common BCI paradigm is motor imagery in which the user controls a BCI by imagining movements of different body parts. It is known that imagining different body parts results in event-related desynchronization (ERD) in various frequency bands. Existing methods such as common spatial patterns (CSP) and its refinement filterbank common spatial patterns (FB-CSP) aim at finding features that are informative for classification of the motor imagery class. Our proposed method is a temporally adaptive common spatial patterns implementation of the commonly used filter-bank common spatial patterns method using convolutional neural networks; hence it is called TA-CSPNN. With this method we aim to: (1) make the feature extraction and classification end-to-end, (2) base it on the way CSP/FBCSP extracts relevant features, and finally, (3) reduce the number of trainable parameters compared to existing deep learning methods to improve generalizability in noisy data such as EEG. More importantly, we show that this reduction in parameters does not affect performance and in fact the trained network generalizes better for data from some participants. We show our results on two datasets, one publicly available from BCI Competition IV, dataset 2a and another in-house motor imagery dataset.

Brain–computer interface (BCI) is an active domain which has attracted attention of the research community in recent years. It offers huge potential as a technology which can estimate the intention of a user by analysis of brain signals and establish a communication channel directly between a human brain and an external device. Electroencephalography (EEG) is the most popular signal acquisition technique due to its ease of use and simplicity. In EEG-based BCI systems, electrodes are placed on specific positions on the scalp of the subject to record electrical activity. The BCI system consists of sequential stages of signal acquisition, its preprocessing, feature extraction and feature classification. It is an active research area which has a focus on improving classification accuracy in motor imagery-based BCI systems. The first stage in a BCI system is to acquire EEG signals from different positions of the scalp of the human subject. The acquired brain signals are preprocessed to remove artifacts before these are fed to feature the extraction stage. In this paper, independent component analysis (ICA) technique is used to remove artifacts from acquired signals. Filter bank common spatial pattern (FBCSP) technique is then used for feature extraction and feature selection. A feature classification approach based on support vector machine (SVM) is proposed in this work and its performance is enhanced by optimizing its polynomial kernel parameters. Selection of kernel parameters is done by grid search method using the fivefold cross-validation procedure. The proposed approach is then executed on publicly available data set 2a of BCI Competition IV. Results show that the proposed approach offers higher classification accuracy and lower misclassification rate as compared to other methods executed on the same dataset, as reported in literature.

Brain-computer interface is a framework which provides a communicating pathway between the human brain and neuroprosthetic devices. In this work, we have performed signal smoothing to fix unregulated electroencephalogram (EEG) fluctuations and to effectively collect hidden patterns in corresponding EEG spectra. To do it, we have applied a Savitzky Golay function because of its ability to preserve spectral properties without distorting it much. For feature selection, we have applied the Filter Bank Common Spatial Pattern (FBCSP) algorithm with the Principle Component Analysis (PCA). FBCSP creates 11352 features from EEG signals and PCA gradually reduces the features to 185 most significant features. These features are utilized in the classification process by the eXtreme Gradient Boosting (XGBoost) algorithm with suitable node split criteria to manage optimal tree height. A five-fold cross-validation approach concludes the superior performance of XGBoost in terms of minimizing execution time (3.7 times faster in the training phase) and providing improved accuracy as compared to existing results. Our approach enhances classification accuracy (88.80%) by approximately 10% over regularized common spatial patterns (78.01% accuracy), 15% over shift variance approximation (73.84% accuracy) and 15% over Riemannian approach (74.77% accuracy). It also concludes that the pre-consideration of the noise level in EEG spectra provides a better approximation.

Neuroadaptive technologies are a type of passive Brain-computer interface (pBCI) that aim to incorporate implicit user-state information into human-machine interactions by monitoring neurophysiological signals. Evaluating machine learning and signal processing approaches represents a core aspect of research into neuroadaptive technologies. These evaluations are often conducted under controlled laboratory settings and offline, where exhaustive analyses are possible. However, the manner in which classifiers are evaluated offline has been shown to impact reported accuracy levels, possibly biasing conclusions. In the current study, we investigated one of these sources of bias, the choice of cross-validation scheme, which is often not reported in sufficient detail. Across three independent electroencephalography (EEG) n-back datasets and 74 participants, we show how metrics and conclusions based on the same data can diverge with different cross-validation choices. A comparison of cross-validation schemes in which train and test subset boundaries either respect the block-structure of the data collection or not, illustrated how the relative performance of classifiers varies significantly with the evaluation method used. By computing bootstrapped 95% confidence intervals of differences across datasets, we showed that classification accuracies of Riemannian minimum distance (RMDM) classifiers may differ by up to 12.7% while those of a Filter Bank Common Spatial Pattern (FBCSP) based linear discriminant analysis (LDA) may differ by up to 30.4%. These differences across cross-validation implementations may impact the conclusions presented in research papers, which can complicate efforts to foster reproducibility. Our results exemplify why detailed reporting on data splitting procedures should become common practice.

A brain-computer interface (BCI) is a system that enables control of devices or communication with other persons, only through cerebral activity, without using muscles. The main application for BCIs is assistive technology for disabled persons. Examples for devices that can be controlled by BCIs are artificial limbs, spelling devices, or environment control systems. BCI research has seen renewed interest in recent years, and it has been convincingly shown that communication via a BCI is in principle feasible. However, present day systems still have shortcomings that prevent their widespread application. In part, these shortcomings are caused by limitations in the functionality of the pattern recognition algorithms used for discriminating brain signals in BCIs. Moreover, BCIs are often tested exclusively with able-bodied persons instead of conducting tests with the target user group, namely disabled persons. The goal of this thesis is to extend the functionality of pattern recognition algorithms for BCI systems and to move towards systems that are helpful for disabled users. We discuss extensions of linear discriminant analysis (LDA), which is a simple but efficient method for pattern recognition. In particular, a framework from Bayesian machine learning, the so-called evidence framework, is applied to LDA. An algorithm is obtained that learns classifiers quickly, robustly, and fully automatically. An extension of this algorithm allows to automatically reduce the number of sensors needed for acquisition of brain signals. More specifically, the algorithm allows to perform electrode selection. The algorithm for electrode selection is based on a concept known as automatic relevance determination (ARD) in Bayesian machine learning. The last part of the algorithmic development in this thesis concerns methods for computing accurate estimates of class probabilities in LDA-like classifiers. These probabilities are used to build a BCI that dynamically adapts the amount of acquired data, so that a preset, approximate bound on the probability of misclassifications is not exceeded. To test the algorithms described in this thesis, a BCI specifically tailored for disabled persons is introduced. The system uses electroencephalogram (EEG) signals and is based on the P300 evoked potential. Datasets recorded from five disabled and four able-bodied subjects are used to show that the Bayesian version of LDA outperforms plain LDA in terms of classification accuracy. Also, the impact of different static electrode configurations on classification accuracy is tested. In addition, experiments with the same datasets demonstrate that the algorithm for electrode selection is computationally efficient, yields physiologically plausible results, and improves classification accuracy over static electrode configurations. The classification accuracy is further improved by dynamically adapting the amount of acquired data. Besides the datasets recorded from disabled and able-bodied subjects, benchmark datasets from BCI competitions are used to show that the algorithms discussed in this thesis are competitive with state-of-the-art electroencephalogram (EEG) classification algorithms. While the experiments in this thesis are uniquely performed with P300 datasets, the presented algorithms might also be useful for other types of BCI systems based on the EEG. This is the case because functionalities such as robust and automatic computation of classifiers, electrode selection, and estimation of class probabilities are useful in many BCI systems. Seen from a more general point of view, many applications that rely on the classification of cerebral activity could possibly benefit from the methods developed in this thesis. Among the potential applications are interrogative polygraphy ("lie detection") and clinical applications, for example coma outcome prognosis and depth of anesthesia monitoring.