brain-computer interface

The brain-computer interface (BCI) technology has emerged as a groundbreaking innovation with profound implications across diverse domains, particularly in health care. By establishing a direct communication pathway between the human brain and external devices, BCI systems offer unprecedented opportunities for diagnosis, treatment, and rehabilitation, thereby reshaping the landscape of medical practice. However, despite its immense potential, the widespread adoption of BCI technology in clinical settings faces several challenges. These include the need for robust signal acquisition and processing techniques and optimizing user training and adaptation. Overcoming these challenges is crucial to unleashing the complete potential of BCI technology in health care and realizing its promise of personalized, patient-centric care. This review work underscores the transformative potential of BCI technology in revolutionizing medical practice. This paper offers a comprehensive analysis of medical-oriented BCI applications by exploring the various uses of BCI technology and its potential to transform patient care.

Brain-Computer Interfaces (BCI) are advanced systems that enable a direct neural pathway between the human brain and external devices. The importance of BCI is underscored by its profound implications for medical therapeutics, particularly in neurorehabilitation.

This study developed an algorithm to detect 8 motion commands for a robot using individuals' EEG signals (Electroencephalogram). These signals were recorded during imagined and expressed commands. The research aimed to identify optimal features for extracting and classifying EEG signals for robot commands and to pinpoint the best EEG channels for a cost-effective, efficient signal acquisition system. Four categories of features, including temporal, frequency, wavelet, and combined features were extracted from the EEG signals. The Imperialist Competitive Algorithm (ICA) and Cuckoo Optimization Algorithm (COA) were utilized for feature selection.

Findings revealed that wavelet features are most effective for analyzing and classifying EEGs. For imagined commands, optimal features from all channels achieved a 96.3% classification accuracy, while expressed commands reached 96.5%. The frontal and parietal lobes were identified as the prime EEG channels for command detection, achieving accuracies of 91.5% and 86.9% for imagined commands, and 92.7% and 86.1% for expressed commands, respectively. The result also indicated that the brain's midline and left hemisphere (containing the Broca area) outperformed the right hemisphere in classification.

By focusing on the optimal EEG channels, a more cost-effective hardware system can be designed, surpassing the traditional 21-channel system and requiring only 14 electrodes in the frontal and parietal regions.

In recent years, the use of Steady-State Visual Evoked Potentials (SSVEPs) in Brain-Computer Interface (BCI) systems has dramatically increased across several fields, such as rehabilitation, cognitive impairment, and brain disease or disorder detection, as well as artificial limbs, wheelchairs, and biomechanical systems. In this study, a novel method is proposed to help scientists develop more efficient BCI systems for Machine Learning Operations (MLOps). This study proposed a state-of-the-art method for detecting SSVEP-based stimulation frequencies with statistical models to design an optimal BCI system.

In this study, the Canonical Correlation Analysis (CCA) method has been implemented to extract features from the accessible-to-the-public Tsinghua University Benchmark dataset. A limited number of subjects are being studied. After completing feature selection methods and selecting the best subset of features using a specified feature selection method, the classification of the best features using machine learning-based classification methods has been completed. Furthermore, it is assumed that scientists will design and implement a system specifically for subjects. Models work for subjects independently. However, because model training is subject-specific, we must execute the proposed methods on each subject separately.

The findings indicate that the novel suggested BCI system achieves an average accuracy of 83±9% in stimulation detection, which is higher than that of the traditional CCA approach with an accuracy of 80±11% (p<0.05).

Based on the findings, we demonstrated an increase in accuracy with the novel method. It was also discovered that by using the proposed techniques, it is possible to keep MLOps systems as an advantage.

Applying efficient feature extraction and selection methods is essential in improving the performance of machine learning algorithms employed in brain-computer interface (BCI) systems.

The current study aims to enhance the performance of a motor imagery-based BCI by improving the feature extraction and selection stages of the machine-learning algorithm applied to classify the different imagined movements.

In this study, a multi-rate system for spectral decomposition of the signal is designed, and then the spatial and temporal features are extracted from each sub-band. To maximize the classification accuracy while simplifying the model and using the smallest set of features, the feature selection stage is treated as a multiobjective optimization problem, and the Pareto optimal solutions of these two conflicting objectives are obtained. For the feature selection stage, non-dominated sorting genetic algorithm II (NSGA-II), an evolutionary-based algorithm, is used wrapper-based, and its effect on the BCI performance is explored. The proposed method is
implemented on a public dataset known as BCI competition III dataset IVa.

Extracting the spatial and temporal features from different sub-bands and selecting the features with an evolutionary optimization approach in this study led to an improved classification accuracy of 92.19% which has a higher value compared to the state of the art.

The results show that the proposed improved classification accuracy could achieve a high-performance subject-specific BCI system.

Utilizing Electroencephalogram (EEG) is more than at any time in history, therefore we have introduced an open-source MATLAB function to provide simulated EEG which is as equivalent as viable to empirical EEG in a user-friendly way with ground truth that is not accessible in real EEG records. This function should be versatile due to the requirements such as the number and orientation of sources, various noises, mode of activation function, and different anatomical structures.

We indicate all phases, modes, and formulas which constitute EEGg, EEG generator. This function supports selecting main sources locations and orientation, choosing SNR with white Gaussian noise, electrode numbers, and mode of activation functions. Also, users have the option to use automatic or partly automatic, or fully automatic EEG construction in EEGg. This function is ready to use at https://github.com/Avayekta/EEG.

EEGg is designed with several parameters that users have chosen. Hence, users can choose different variables to inspect the time and frequency aspects of synthetic EEG.

EEGg is a multi-purpose and comprehensive function to mimic EEG but with ground-truth EEG data and adjustable parameters.

Brain-Computer Interface (BCI) systems are a new channel of communication between human thoughts and machines without the aid of neuromuscular systems. Although BCI systems exhibit several advantages, they yet have a long road ahead to reach a flawless state. For example, error occurrence is one of the problems in these systems, leading to Error-Related Potentials (ErRP) in the brain signal. In this study, Electroencephalogram (EEG) signals in the condition of system error occurrence are investigated. Since local information on the EEG signal channels alone cannot reveal the secrets of the brain, functional connectivity was used as a feature in this research.

In this research, 32 channel EEG signals with a sampling frequency of 256 Hz were recorded from 18 participants while interacting with a BCI system which has an interaction error. Two types of stimulus were used, including visual and tactile ones. Moreover, the Inter-Stimulus-Interval (ISI) was changed during the task. After pre-processing, brain functional connectivity was calculated between all channel pairs in four groups (visual, tactile, combined visual-tactile (ISI=3.5), and combined visual-tactile (ISI=2)) using Magnitude-Squared Coherence (MSC) measure.

The results showed a significant difference in frontal-right temporal connectivity between correct and error classes in tactile stimulation, in visual stimulation significant differences in frontal-occipital connectivity, in visual-tactile (ISI=3.5) stimulation significant differences in left temporal-occipital connectivity (P-value< 0.001), and in visual-tactile (ISI=2) stimulation significant differences in central-occipital connectivity were seen (P-value< 0.01).

This study shows that using brain functional connectivity features along with local features can improve the performance of BCI systems.

Distinguishing P300 signals from other components of the EEG is one of the mostchallenging issues in Brain Computer Interface (BCI) applications, and machine learningmethods have vastly been utilized as effective tools to perform such separation. Althoughin recent years deep neural networks have significantly improved the quality of the abovedetection, the significant similarity between P300 and other components of EEG in parallelwith their unrepeatable nature have led to P300 detection, which are still an open problemin BCI domain. In this study, a novel architecture is proposed in order to detect P300 signalamong EEG, in which the temporal learning concept is engaged as a new substructureinside the main Convolutional Neural Network (CNN). The above Temporal ConvolutionalNetwork (TCN) may better address the problem of P300 detection, thanks to its potentialin involving time sequence properties in modelling of these signals. The performance ofthe proposed method is evaluated on the EPFL BCI dataset, and the obtained results arecompared in two inter-subject and intra-subject scenarios with the results of classical CNNin which temporal properties of input are not considered. Increased True Positive Rate ofthe proposed method (an average of 4 percent) and its accuracy (an average of 2.9 percent)in parallel with the decrease in its False Positive Rate (averagely 3.1 percent) shows theeffectiveness of the TCN structure in promoting the detection procedure of P300 signals inBCI applications

Brain Computer Interface (BCI) has provided a novel way of communication that can significantly revolutionize life of people suffering from disabilities. Motor Imagery (MI) EEG BCI is one of the most promising solutions to address. The main phases of such systems include signal acquisition, pre-processing, feature extraction, classification and the intended interface. The challenging obstacles in such systems are to detect and extract efficient features that present reliability and robustness alongside promising classification accuracy. In this paper it is endeavored to present a robust method for a two-class MI BCI that results in high accuracy.

For this purpose, the dataset 2b from BCI competition 2008, consisting of three channels (C3, C and Cz), was utilized. Firstly, the signals were bandpass filtered. Secondly, Common Spatial Pattern (CSP) was employed and then a number of features, including non-linear chaotic features were extracted from channels C3 and C4. After feature selection phase the number of features were reduced to 38 and 47. Finally, these features were fed into two classifiers, namely Support Vector Machine classifier (SVM) and Bagging to evaluate the performance of the system.

Classification accuracy and Cohen’s Kappa coefficient of the proposed method for two MI EEG channels are 96.40% and 0.92, respectively.

These results indicate the high accuracy and stability of our method in comparison with similar studies. Therefore, it can be a promising approach in two-class MI BCI systems.

Brain-Computer Interface (BCI) systems are able to understand and execute commands through processing brain signals. It has numerous applications in the field of biomedical engineering such as rehabilitation, biometric and entertainment. A BCI system consists of four major parts: signal acquisition, signal pre-processing, feature extraction and classification. Steady State Visually Evoked Potentials (SSVEP) is one of the most common paradigms in BCI systems, which is generally a response to visual stimuli with the frequency between 5 to 60 Hz.

In this study, we suggest a Convolutional Neural Network (CNN) based model for the classification of EEG signal during SSVEP task. For the evaluation, the model was tested with different channels and electrodes.

Results show that channels number 138 and 139 have the great potential to appropriately classify EEG signal.

Using the suggested model and the mentioned channels, the accuracy of 73.74% could be achieved in this study.

A simple data collection approach based on electroencephalogram (EEG) measurements has been proposed in this study to implement a brain–computer interface, i.e., thought-controlled wheelchair navigation system with communication assistance.

The EEG signals are recorded for seven simple tasks using the designed data acquisition procedure. These seven tasks are conceivably used to control wheelchair movement and interact with others using any odd-ball paradigm. The proposed system records EEG signals from 10 individuals at eight-channel locations, during which the individual executes seven different mental tasks. The acquired brainwave patterns have been processed to eliminate noise, including artifacts and powerline noise, and are then partitioned into six different frequency bands. The proposed cross-correlation procedure then employs the segmented frequency bands from each channel to extract features. The cross‑correlation procedure was used to obtain the coefficients in the frequency domain from consecutive frame samples. Then, the statistical measures (“minimum,” “mean,” “maximum,” and “standard deviation”) were derived from the cross‑correlated signals. Finally, the extracted feature sets were validated through online sequential-extreme learning machine algorithm. Results and

The results of the classification networks were compared with each set of features, and the results indicated that μ (r) feature set based on cross-correlation signals had the best performance with a recognition rate of 91.93%.

This article summarizes the first and second Iranian brain–computer interface competitions held in 2017 and 2018 by the National Brain Mapping Lab. Two 64‑channel electroencephalography (EEG) datasets were contributed, including motor imagery as well as motor execution by three limbs. The competitors were asked to classify the type of motor imagination or execution based on EEG signals in the first competition and the type of executed motion as well as the movement onset in the second competition. Here, we provide an overview of the datasets, the tasks, the evaluation criteria, and the methods proposed by the top‑ranked teams. We also report the results achieved with the submitted algorithms and discuss the organizational strategies for future campaigns.

P300 speller is a kind of Brain-Computer Interface (BCI) system in which the user may type words by using the responses obtained from human focus on different characters. The high sensitivity of brain signals against noise in parallel with the similarity of responses obtained from the user focus on different characters makes it difficult to classify the characters based on their respective P300 wave. On the other hand, all areas of the brain does not carry useful P300 information.

In this study, a new method is proposed to improve the performance of speller system which is based on selecting optimal P300 channels. In the proposed method, recursive elimination algorithm is presented for channel optimization, which utilizes deep learning concept (e.g. Convolutional Neural Network) as its cost function. The proposed method is examined on a data set from EEG signals recorded in a P300 speller system, including 64 different channels of responses to 29 characters. Then, its performance is compared with some existing methods.

The obtained results showed the ability of the proposed method in recognizing the characters in such way that it could accurately (i.e. 97.34%) detect 29 characters by using only 24 out of all 64 electrodes.

Applying the proposed method in speller systems led to considerable improvement in classification of characters compared to its alternatives. Several experiments proved that utilizing the proposed scheme may increases the accuracy almost 12.9 percent compared to non-optimized case in parallel with reduction of the number of involved channels by approximately 1/3. Based on these results, the proposed method may be considered as an effective choice for application in P300 speller systems, thanks to reduction of the complexity of the system which is caused by the reduced number of channels and, on the other hand, due to its potential in increasing the accuracy of character recognition.

Brain-Computer Interface (BCI) offers a non-muscle way between the human brain and the outside world to make a better life for disabled people. In BCI applications P300 signal has an effective role; therefore, distinguishing P300 and non-P300 components in EEG signal (i.e. P300 detection) becomes a vital problem in BCI applications. Recently, Convolutional Neural Networks (CNNs) have had a significant application in detection of P300 signals in the field of BCIs. The P300 signal has low Signal to Noise Ratio (SNR). On the other hand, the CNN detection rate is so sensitive to SNR; therefore, CNN detection rate drops dramatically when it is faces with P300 data. In this study, a novel structure is proposed to improve the performance of CNN in P300 signal detection by means of improving its performance against low SNR signals. In the proposed structure, Sparse Representation-based Classification (SRC) was used as the first substructure. This block is responsible for prediction of the expected P300 signal among artifacts and noise. The second substructure performed P300 classification with Adadelta algorithm. Thanks to such SNR improvement scheme; the proposed structure i able to increase the rate of accuracy in the field of P300 signal detection. To evaluate the performance of the proposed structure, we applied it on EPFL dataset for P300 detection, and then the achieved results were compared with those obtained from the basic CNN structure. The comparisons revealed the superiority of the proposed structure against its alternative, so that its True Positive Rate (TPR) was promoted about 19.66%. Such improvements for false detections and accuracy parameters were 1.93% and 10.46%, respectively, which show the effectiveness of applying the proposed structure in detecting P300 signals. The better accuracy of the proposed algorithm compared to basic CNN, in parallel with its more robustness, showed that the Sparse Representation-based Classification (SRC) had a considerable potential to be used as an improving idea in CNN-based P300 detection.

Brain–computer interfaces enable users to control devices with electroencephalographic (EEG) activity from the scalp or with single‑neuron activity from within the brain. One of the most challenging issues in this regard is the balance between the accuracy of brain signals from patients and the speed of interpreting them into machine language. The main objective of this paper is to analyze different approaches to achieve the balance more quickly and in a better way. To reduce the ocular artifacts, the symmetric prewhitening independent component analysis (ICA) algorithm has been evaluated, which has the lowest runtime and lowest signal‑to‑interference (SIR) index, without destroying the original signal. After quick elimination of all undesirable signals, two successful feature extractors – the log‑band power algorithm and common spatial patterns (CSPs) – are used to extract features. The emphasis is on identifying discriminative properties of the feature sets representing EEG trials recorded during the imagination of the tongue, feet, and left right‑hand movement. Finally, three well‑known classifiers are evaluated, where the ridge regression classifier and CSPs as feature extractor have the highest accuracy classification rate about 83.06% with a standard deviation of 1.22%, counterposing the recent studies.

Many of the current brain-computer interface systems rely on the patient`s ability to control voluntary eye movements. Some diseases can lead to defects in the visual system. Due to the intactness of these patients` auditory system, researchers moved towards the auditory paradigms. Attention can modulate the power of auditory steady-state response. As a result, this response is useful in an auditory brain-computer interface.
As humans intrinsically enjoy listening to rhythmic sounds, this project was carried out with the aim of extraction and classification of the EEG signal patterns in response to simple and rhythmic auditory stimuli to investigate the possibility of using the rhythmic stimuli in brain-computer interface systems.
Two three-membered simple and rhythmic groups of auditory sinusoidally amplitude-modulated tones were generated as the stimuli. Corresponding EEG signals were recorded and classified by means of five-fold cross-validated naïve Bayes classifier on the basis of power spectral density at message frequencies.
There was no significant difference between the classification performances of the responses to each group of the stimuli. All the classification accuracies, even without any noise reduction and artifact rejection, was greater than the acceptable value for being used in brain-computer interface systems (70%).
Like the common sinusoidally amplitude-modulated tones, the novel proposed rhythmic stimuli in this project have a promising discrimination for being used in brain-computer interface systems. In addition, Power spectral density has provided an appropriate discrimination for within- and between-subject EEG classification.