Search

When learning to use a brain-machine interface (BMI), the brain modulates neuronal activity patterns, exploring and exploiting the state space defined by their neural manifold. Neurons directly involved in BMI control (i.e., direct neurons) can display marked changes in their firing patterns during BMI learning. However, the extent of firing pattern changes in neurons not directly involved in BMI control (i.e., indirect neurons) remains unclear. To clarify this issue, we localized direct and indirect neurons to separate hemispheres in a task designed to bilaterally engage these hemispheres while animals learned to control the position of a platform with their neural signals. Animals that learned to control the platform and improve their performance in the task shifted from a global strategy, where both direct and indirect neurons modified their firing patterns, to a local strategy, where only direct neurons modified their firing rate, as animals became expert in the task. Animals that did not learn the BMI task did not shift from utilizing a global to a local strategy. These results provide important insights into what differentiates successful and unsuccessful BMI learning and the computational mechanisms adopted by the neurons.

This study is intended to improve the motor imagery classification performance of two-class data points using newly developed covariance decentering eigenface analysis (CDC-EFA). When extracting the classification for the given data points, it is necessary to precisely distinguish the classes because the left and right features are difficult to differentiate. However, when centering is performed, the unique average data of each feature are lost, making them difficult to distinguish. CDC-EFA reverses the centering method to enhance data characteristics, making it possible to assign weights to data with a high correlation with other data. In experiments with the BCI dataset, the proposed CDC-EFA method was used after preprocessing by filtering and selecting the electroencephalogram data. The decentering process was then performed on the covariance matrix calculated when acquiring the unique face. Subsequently, we verified the classification improvement performance via simulations using several BCI competition datasets. Several signal processing methods were applied to compare the accuracy results of the motor imagery classification. The proposed CDC-EFA method yielded an average accuracy result of 98.89%. Thus, it showed improved accuracy compared with the other methods and stable performance with a low standard deviation. [ABSTRACT FROM AUTHOR]

In the field of neuroscience, a significant challenge lies in extracting essential features from biological signals like Electroencephalography (EEG). Utilized as a non-invasive method, EEG records brain activities through metal electrodes on the scalp. The analysis of EEG data finds applications in various domains, including concealed information tests, aimed at detecting deception. This paper introduces the Spatial Spiking Neural Network, a supervised approach for classifying EEG data collected during concealed information tests. Temporal EEG data undergoes filtration using a Finite Impulse Response (FIR) filter, while Common Spatial Pattern (CSP) is employed to extract spatial components. Binary classification is achieved through an integrate-and-fire neuron model, where the frequency of spike generation determines the classification. Spiking Neural Networks (SNNs) offers advantages in terms of temporal precision, event-driven processing, and low power consumption. Their spike-based communication allows for efficient handling of sparse data and recognition of temporal patterns, contributing to robustness and energy efficiency. The proposed model is applied separately to each subject's EEG data, and the results are compared with traditional classification algorithms. The proposed approach attains a peak accuracy of 90.15%, showcasing superior performance compared to alternative methods. [ABSTRACT FROM AUTHOR]

AbstractElectroencephalogram (EEG) signals, which objectively reflect the state of the brain, are widely favored in emotion recognition research. However, the presence of cross-session and cross-subject variation in EEG signals has hindered the practical implementation of EEG-based emotion recognition technologies. In this article, we propose a multi-source domain transfer method based on subdomain adaptation and minimum class confusion (MS-SAMCC) in response to the addressed issue. First, we introduce the mix-up data augmentation technique to generate augmented samples. Next, we propose a minimum class confusion subdomain adaptation method (MCCSA) as a sub-module of the multi-source domain adaptation module. This approach enables global alignment between each source domain and the target domain, while also achieving alignment among individual subdomains within them. Additionally, we employ minimum class confusion (MCC) as a regularizer for this sub-module. We performed experiments on SEED, SEED IV, and FACED datasets. In the cross-subject experiments, our method achieved mean classification accuracies of 87.14% on SEED, 63.24% on SEED IV, and 42.07% on FACED. In the cross-session experiments, our approach obtained average classification accuracies of 94.20% on SEED and 71.66% on SEED IV. These results demonstrate that the MS-SAMCC approach proposed in this study can effectively address EEG-based emotion recognition tasks. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Zhejiang University: Science B is the property of Springer Nature and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

A brain-computer interface (BCI) based on an electroencephalograph (EEG) establishes a new channel of communication between the human brain and a computer. Redundant, noisy, and irrelevant channels lead to high computational costs and poor classification accuracy. Therefore, an effective feature selection technique for determining the optimal number of channels can improve BCI's performance. However, existing meta-heuristic algorithms are prone to get trapped in local optimum due to high dimensional dataset. Thus, to reduce dimension, solve inter subject variation and choose an optimal subset of channels, a novel framework called Component Loading followed by Clustering and Classification (CLCC) is proposed in this paper. This novel framework is further divided into two experiment configurations-CLCC with Feature Selection (CLCC-FS) and CLCC without Feature Selection (CLCC-WFS). All these frameworks have been implemented on a motor imagery (MI) EEG dataset of 10 subjects in order to choose the best subset of channels. Further, seven different classifiers have been employed to assess the performance. Experimental outcomes show that on comparing various feature selection techniques, our proposed algorithm i.e., CLCC-FS Opposition-Based Whale Optimization Algorithm (CLCC-FS(OBWOA)) performed substantially better than the other feature selection techniques. We demonstrate that the proposed algorithm is able to achieve 99.6% accuracy by using only few channels and can improve the practicality of the BCI system by reducing the computation cost. [ABSTRACT FROM AUTHOR]

Copyright of Przegląd Elektrotechniczny is the property of Przeglad Elektrotechniczny and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Objective To explore a motor-related brain computer interface (BCI) technology based on the decoding of six precise hand movements. Methods Based on the analysis of the mechanisms and response characteristics of six common types of fine motor electroencephalography (EEG) in the hand, a BCI paradigm for fine motor execution was designed. A motion related EEG signal decoding model based on convolutional neural networks was implemented, and a BCI system based on fine motor was built. Six types of fine motor gesture EEG signals from eight healthy subjects and two patients with significant motor dysfunction due to lesions involving the parietal lobe were classified. Results The classification accuracy of EEG signals in 10 subjects under the BCI system based on fine hand movements was (79.20±6.05)%. Conclusions The BCI method based on decoding six types of fine hand movements has certain effectiveness and generalization ability. [ABSTRACT FROM AUTHOR]

Personal authentication using electroencephalographic (EEG) signals, is one of the important applications in brain computer interface (BCI). In this work we investigate the use of EEG signals as a biometric trait. Multidimensional EEG signals were represented as symmetric positive-definite (SPD) matrices on a Riemannian manifold. Two experiments are performed in the first; we use minimum distance to Riemannian mean (MDRM) as a classifier. In the second; SPD matrices are vectorized, and the generated vectors are used to train various machine learning (ML) classifiers. MDRM classifier achieved a correct recognition rate (CRR) of 96.92%, while ML classifiers achieved CRR from 95.39% to 99.45%. [ABSTRACT FROM AUTHOR]

The brain-computer interface (BCI) is a direct pathway of communication between the electrical activity of the brain and an external device. The present paper was aimed to investigate directed connectivity between different areas of the brain during motor imagery (MI)-based BCI. For this purpose, two methods were implemented including, Limited Penetrable Horizontal Visibility Graph (LPHVG) and Direct Lingam. The visibility graph (VG) is a robust algorithm for analyzing complex systems such as the brain. Direct Lingam uses a non-Gaussian model to extract causal links which is appropriate for analyzing large-scale connectivity. First, LPHVG map MI-EEG (electroencephalogram) signals into networks. After extracting the topological features of the networks, a support vector machine classifier was applied to categorize multi-classes MI. The network of all classes was found to be different from one another, and the kappa value of classification was 0.68. The degree sequence of LPHVG was calculated for each channel in order to obtain the direction of brain information flow. Transfer entropy (TE) is used to compute the relations of the channel degree sequence. Therefore, the directed graph between channels was formed. This method is called LPHVG_TE directed graph. The Bayesian network, also known as the Direct LiNGAM model, was implemented for the second method. Finally, images of the LPHVG and Direct Lingam were classified by convolutional neural network (CNN). In this study, Data sets 2a of BCI competition IV was used. The outcomes reveal that the brain network developed by LPHVG (92.7%) might be more effective to distinguish 4 classes of MI than the Direct Lingam (90.6%) and it was shown that graph theory has the potential to get better efficiency of BCI. [ABSTRACT FROM AUTHOR]

The article delves into enhancing Relevance Feedback (RF) using brain signals alongside pseudo-relevance and implicit signals. Topics include the challenges of RF using traditional methods, the integration of brain signals to improve RF accuracy, and the framework's effectiveness in diverse search scenarios.

Steady-state visually evoked potential is one of the active explorations in the brain-computer interface research. Electroencephalogram based brain computer interface studies have been widely applied to perceive solutions for real-world problems in the healthcare domain. The classification of externally bestowed visual stimuli of different frequencies on a human was experimented to identify the need of paralytic people. Although many classifiers are at the fingertip of machine learning technology, recent research has proven that ensemble learning is more efficacious than individual classifiers. Despite its efficiency, ensemble learning technology exhibits certain drawbacks like taking more time on selecting the optimal classifier subset. This research article utilizes the Harris Hawk Optimization algorithm to select the best classifier subset from the given set of classifiers. The objective of the research is to develop an efficient multi-classifier model for electroencephalogram signal classification. The proposed model utilizes the Boruta Feature Selection algorithm to select the prominent features for classification. Thus selected prominent features are fed into the multi-classifier subset which has been generated by the Harris Hawk Optimization algorithm. The results of the multi-classifier ensemble model are aggregated using Stacking, Bagging, Boosting, and Voting. The proposed model is evaluated against the acquired dataset and produces a promising accuracy of 96.1%, 98.7%, 91.91%, and 99.01% with the ensemble techniques respectively. The proposed model is also validated with other performance metrics such as sensitivity, specificity, and F1-Score. The experimental results show that the proposed model proves its supremacy in segregating the multi-class classification problem with high accuracy. [ABSTRACT FROM AUTHOR]

Copyright of Jordanian Journal of Computers & Information Technology is the property of Jordanian Journal of Computers & Information Technology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Abstract Nervous system diseases are among the most common diseases globally, posing a severe threat to patients' quality of life and placing a considerable burden on families and society. With improvements in miniaturization, intelligence, and the safety of biosensors, the combination of machinery and organisms is becoming increasingly common. In neuroscience research, biosensors of different macroscopic dimensions have been uniquely utilized to harness their relevant properties. One‐dimensional (1D) biosensors can achieve in situ real‐time monitoring of neural markers at the subcellular, single‐cell, ex vivo, and in vivo levels, with reduced impacts on organisms. Two‐dimensional (2D) biosensors can monitor the chemical behavior of cells and the neural activity of living animals. They are helpful for objectively identifying the characteristics of cells in response to external stimuli and studying the neural circuits of living animals. Three‐dimensional (3D) biosensors have shown unique advantages in point‐of‐care testing, liquid biopsy, drug screening, and mechanistic research. In clinical practice, brain‐computer interfaces (BCIs) and wearable devices have become important tools for monitoring and treatment. To date, there has been widespread adoption of BCIs in clinical practice. BCIs not only exhibit good efficacy in severe neurological and mental diseases but also provide a method for early diagnosis and treatment of these diseases. Wearable sensor devices can accurately assess the symptoms of movement disorders and play an active role in rehabilitation and treatment. In this review, we summarize the application of advanced biosensors in neuroscience research and clinical practice. The challenges and prospects of biosensors as applied to nervous system diseases under interdisciplinary promotion are also discussed in depth.

Objective: To evaluate the feasibility, safety, and potential health benefits of an 8-week home-based neurofeedback intervention. Design: Single-group preliminary study. Setting: Community-based. Participants: Nine community dwelling adults with chronic neuropathic pain, 6 women and 3 men, with an average age of 51.9 years (range, 19-78 years) and with a 7-day average minimum pain score of 4 of 10 on the visual analog pain scale. Interventions: A minimum of 5 neurofeedback sessions per week (40min/session) for 8 consecutive weeks was undertaken with a 12-week follow-up baseline electroencephalography recording period. Main Outcome Measures: Primary feasibility outcomes: accessibility, tolerability, safety (adverse events and resolution), and human and information technology (IT) resources required. Secondary outcomes: pain, sensitization, catastrophization, anxiety, depression, sleep, health-related quality of life, electroencephalographic activity, and simple participant feedback. Results: Of the 23 people screened, 11 were eligible for recruitment. One withdrew and another completed insufficient sessions for analysis, which resulted in 9 datasets analyzed. Three participants withdrew from the follow-up baselines, leaving 6 who completed the entire trial protocol. Thirteen adverse events were recorded and resolved: 1 was treatment-related, 4 were equipment-related, and 8 were administrative-related (eg, courier communication issues). The human and IT resources necessary for trial implementation were identified. There were also significant improvements in pain levels, depression, and anxiety. Six of 9 participants perceived minimal improvement or no change in symptoms after the trial, and 5 of 9 participants were satisfied with the treatment received. Conclusions: It is feasible and safe to conduct a home-based trial of a neurofeedback intervention for people with chronic neuropathic pain, when the human and IT resources are provided and relevant governance processes are followed. Improvements in secondary outcomes merit investigation with a randomized controlled trial.

IntroductionBi-directional brain-computer interfaces (BD-BCI) to restore movement and sensation must achieve concurrent operation of recording and decoding of motor commands from the brain and stimulating the brain with somatosensory feedback.MethodsA custom programmable direct cortical stimulator (DCS) capable of eliciting artificial sensorimotor response was integrated into an embedded BCI system to form a safe, independent, wireless, and battery powered testbed to explore BD-BCI concepts at a low cost. The BD-BCI stimulator output was tested in phantom brain tissue by assessing its ability to deliver electrical stimulation equivalent to an FDA-approved commercial electrical cortical stimulator. Subsequently, the stimulator was tested in an epilepsy patient with subcortical electrocorticographic (ECoG) implants covering the sensorimotor cortex to assess its ability to elicit equivalent responses as the FDA-approved counterpart. Additional safety features (impedance monitoring, artifact mitigation, and passive and active charge balancing mechanisms) were also implemeneted and tested in phantom brain tissue. Finally, concurrent operation with interleaved stimulation and BCI decoding was tested in a phantom brain as a proof-of-concept operation of BD-BCI system.ResultsThe benchtop prototype BD-BCI stimulator's basic output features (current amplitude, pulse frequency, pulse width, train duration) were validated by demonstrating the output-equivalency to an FDA-approved commercial cortical electrical stimulator (R 2 > 0.99). Charge-neutral stimulation was demonstrated with pulse-width modulation-based correction algorithm preventing steady state voltage deviation. Artifact mitigation achieved a 64.5% peak voltage reduction. Highly accurate impedance monitoring was achieved with R 2 > 0.99 between measured and actual impedance, which in-turn enabled accurate charge density monitoring. An online BCI decoding accuracy of 93.2% between instructional cues and decoded states was achieved while delivering interleaved stimulation. The brain stimulation mapping via ECoG grids in an epilepsy patient showed that the two stimulators elicit equivalent responses.SignificanceThis study demonstrates clinical validation of a fully-programmable electrical stimulator, integrated into an embedded BCI system. This low-cost BD-BCI system is safe and readily applicable as a testbed for BD-BCI research. In particular, it provides an all-inclusive hardware platform that approximates the limitations in a near-future implantable BD-BCI. This successful benchtop/human validation of the programmable electrical stimulator in a BD-BCI system is a critical milestone toward fully-implantable BD-BCI systems.

This paper devised a novel Christmas‐tree structure for flexible neural probes, which features recording sites on side‐branches that can be folded along the shank of the probe by temporary encapsulation before implantation. This design reduces the size of the implant and minimizes the surgical footprint. Upon implantation, the temporary encapsulation dissolves in vivo, leading to self‐stretching of the branches, and an expansion of the lateral detecting range of the probe. We conducted in vitro experiment with our probe in 0.6% agar that mimics the brain tissue environment. The results demonstrate that the neural probe we have developed exhibits self‐stretching ability and provides an increased lateral recording range without causing additional damage to the brain tissue. © 2024 Institute of Electrical Engineer of Japan and Wiley Periodicals LLC. [ABSTRACT FROM AUTHOR]

We proposed a brain‐to‐brain interface (B2BI) that enabled effective control of mouse turning behavior by human mind using an implantable, ultra‐flexible neural probe. The neural probe was capable of writing in neural signals to the mouse brain, with effective electrical stimulation observed at a low current of 5 μA. Additionally, a wireless electroencephalogram (EEG) device was developed for the remote transmission of human brain signals, which were decoded by the canonical correlation analysis (CCA) method with an accuracy rate of up to 98.6%. These results demonstrate the potential of B2BI technology to enable communication and control between humans and animals. © 2024 Institute of Electrical Engineer of Japan and Wiley Periodicals LLC. [ABSTRACT FROM AUTHOR]

BACKGROUND: The stability criterion approach is very important for estimating precise behavior before or after fabricating brain computer interface system applications. OBJECTIVE: A novel approach using the Routh-Hurwitz standard criterion method is proposed to easily determine and analyze the stability of brain computer interface system applications. Using this developed approach, we were able to easily test the stability of technical issue using simple programmed codes before or after brain computer interfaces fabrication applications. METHODS: Using a MATLAB simulation program package, we are able to provide two different special case examples such as a first zero element and a row of zeros to verify the capability of our proposed Routh-Hurwitz method. RESULTS: The MATLAB simulation program provided efficient Routh-Hurwitz standard criterion results by differentiating the highest coefficients of the s and a. CONCLUSION: This technical paper explains how to use our proposed new Routh-Hurwitz standard condition to simply ascertain and determine the brain computer interface system stability without customized commercial simulation tools. [ABSTRACT FROM AUTHOR]

When learning to use a brain-machine interface (BMI), the brain modulates neuronal activity patterns, exploring and exploiting the state space defined by their neural manifold. Neurons directly involved in BMI control (i.e., direct neurons) can display marked changes in their firing patterns during BMI learning. However, the extent of firing pattern changes in neurons not directly involved in BMI control (i.e., indirect neurons) remains unclear. To clarify this issue, we localized direct and indirect neurons to separate hemispheres in a task designed to bilaterally engage these hemispheres while animals learned to control the position of a platform with their neural signals. Animals that learned to control the platform and improve their performance in the task shifted from a global strategy, where both direct and indirect neurons modified their firing patterns, to a local strategy, where only direct neurons modified their firing rate, as animals became expert in the task. Animals that did not learn the BMI task did not shift from utilizing a global to a local strategy. These results provide important insights into what differentiates successful and unsuccessful BMI learning and the computational mechanisms adopted by the neurons. [ABSTRACT FROM AUTHOR]

Featured Application: Brain computer interface for communication with patients in the Completely Locked-In state. In a completely locked-in state (CLIS), often resulting from traumatic brain injury or neurodegenerative diseases like amyotrophic lateral sclerosis (ALS), patients lose voluntary muscle control, including eye movement, making communication impossible. Brain-computer interfaces (BCIs) offer hope for restoring communication, but achieving reliable communication with these patients remains a challenge. This study details the design, testing, and comparison of nine visuo-auditory P300-based BCIs (combining different visual and auditory stimuli and different visual layouts) with a CLIS patient over ten months. The aim was to evaluate the impact of these stimuli in achieving effective communication. While some interfaces showed promising progress, achieving up to 90% online accuracy in one session, replicating this success in subsequent sessions proved challenging, with the average online accuracy across all sessions being 56.4 ± 15.2%. The intertrial variability in EEG signals and the low discrimination between target and non-target events were the main challenge. Moreover, the lack of communication with the patient made BCI design a challenging blind trial-and-error process. Despite the inconsistency of the results, it was possible to infer that the combination of visual and auditory stimuli had a positive impact, and that there was an improvement over time. [ABSTRACT FROM AUTHOR]

Introduction: Brain computer interface-based action observation (BCI-AO) is a promising technique in detecting the user's cortical state of visual attention and providing feedback to assist rehabilitation. Peripheral nerve electrical stimulation (PES) is a conventional method used to enhance outcomes in upper extremity function by increasing activation in the motor cortex. In this study, we examined the effects of different pairings of peripheral nerve electrical stimulation (PES) during BCI-AO tasks and their impact on corticospinal plasticity. Materials and methods: Our innovative BCI-AO interventions decoded user's attentive watching during task completion. This process involved providing rewarding visual cues while simultaneously activating afferent pathways through PES. Fifteen stroke patients were included in the analysis. All patients underwent a 15min BCI-AO program under four different experimental conditions: BCI- AO without PES, BCI-AO with continuous PES, BCI-AO with triggered PES, and BCI-AO with reverse PES application. PES was applied at the ulnar nerve of the wrist at an intensity equivalent to 120% of the sensory threshold and a frequency of 50Hz. The experiment was conducted randomly at least 3 days apart. To assess corticospinal and peripheral nerve excitability, we compared pre and post-task (post 0, post 20min) parameters of motor evoked potential and F waves under the four conditions in the muscle of the affected hand. Results: The findings indicated that corticospinal excitability in the affected hemisphere was higher when PES was synchronously applied with AO training, using BCI during a state of attentive watching. In contrast, there was no effect on corticospinal activation when PES was applied continuously or in the reverse manner. This paradigm promoted corticospinal plasticity for up to 20min after task completion. Importantly, the effect was more evident in patients over 65 years of age. Conclusion: The results showed that task-driven corticospinal plasticity was higher when PES was applied synchronously with a highly attentive brain state during the action observation task, compared to continuous or asynchronous application. This study provides insight into how optimized BCI technologies dependent on brain state used in conjunction with other rehabilitation training could enhance treatment-induced neural plasticity. [ABSTRACT FROM AUTHOR]

This article uses the partition backlight of LCD to design a visual stimulator for SSVEP brain computer interface systems, and compares it with traditional LCD visual stimulators in experiments. The experimental results not only proved the feasibility of using partition backlight as a visual stimulator, but also found that the performance of partition backlight visual stimulators is superior to traditional visual stimulators when outputting high∐frequency stimuli. [ABSTRACT FROM AUTHOR]

Multi-class motor imagery Electroencephalography (EEG) activity decoding has always been challenging for the development of Brain Computer Interface (BCI) system. Deep learning has recently emerged as a powerful approach for BCI system development using EEG activity. However, the EEG activity analysis and classification should be robust, automated and accurate. Currently, available BCI systems perform well for binary task identification whereas, multi-class classification of EEG activity for BCI applications is still a challenging task. In this work, a hybrid residual attention ensemble voting classifier model is developed for EEG-based Motor Imagery-Brain Computer Interface (MI-BCI) task classification. The Time–Frequency Representation (TFR) of the multi-class EEG activity is generated using Transient Extracting Transform. The TFR spectrogram images are input to the designed residual attention ensemble voting classifier model for training and classification purposes. The model is evaluated using different fusion strategies viz. feature-level and score-level fusion of layers. The proposed model is evaluated on two MI-BCI datasets, BCI competition IV 2a and BCI competition III 3a, yielding the highest classification accuracies of 88.14% and 93.13%, respectively. The results obtained on a large multi-class MI-BCI dataset confirm that the proposed hybrid residual attention ensemble voting classifier model significantly outperforms the conventional algorithm and achieves significantly high classification accuracy for the feature-level fusion of layers. The developed framework aids in identifying different tasks for multi-class MI-BCI EEG activity. [ABSTRACT FROM AUTHOR]

This graphic shows the structure of our network. In the preprocessing section, we used the Beer-Lambert law to convert the optical signals into hemodynamic HbR and HbO. We used an end-to-end structure without much preprocessing of the raw fNIRS signal. We input the signal with the number of channels C = 24 and the number of samples T = 351. the original MI and MA signals are first passed through a convolution block. The convolution block consists of a 2D time convolution, a depth convolution, and a separable convolution, each followed by a Batch Normalization layer, an ELU activation function, an average pooling layer, and a dropout layer. Afterwards, spatio-temporal feature extraction is performed by spatial attention and temporal convolutional networks, capable of reducing overfitting. Finally, the fNIRS signal is classified as MI or MA. The results show that the method using only 3.23 K training parameters has an accuracy of 85.63% (HbO) and 86.21% (HbR) in the MI task and 96.84% (HbO) and 94.83% (HbR) in the MA task. [Display omitted] • fNIRS decoding performance improvement. • Using Convolutional Neural Networks for fNIRS Classification. • Spatial attention mechanisms can capture remote contextual information. • Temporal convolutional network outperforms most RNN in time-series tasks. Brain Computer Interface (BCI) is a highly promising human–computer interaction method that can utilize brain signals to control external devices. BCI based on functional near-infrared spectroscopy (fNIRS) is considered a relatively new and promising paradigm. fNIRS is a technique of measuring functional changes in cerebral hemodynamics. It detects changes in the hemodynamic activity of the cerebral cortex by measuring oxyhemoglobin and deoxyhemoglobin (HbR) concentrations and inversely predicts the neural activity of the brain. At the present time, Deep learning (DL) methods have not been widely used in fNIRS decoding, and there are fewer studies considering both spatial and temporal dimensions for fNIRS classification. To solve these problems, we proposed an end-to-end hybrid neural network for feature extraction of fNIRS. The method utilizes a spatial–temporal convolutional layer for automatic extraction of temporally valid information and uses a spatial attention mechanism to extract spatially localized information. A temporal convolutional network (TCN) is used to further utilize the temporal information of fNIRS before the fully connected layer. We validated our approach on a publicly available dataset including 29 subjects, including left-hand and right-hand motor imagery (MI), mental arithmetic (MA), and a baseline task. The results show that the method has few training parameters and high accuracy, providing a meaningful reference for BCI development. [ABSTRACT FROM AUTHOR]

Decoding visual information, such as visual imagery and perception, from EEG data can be used to improve understanding of the neural representation of visual information and to provide commands for BCI systems. The appeal of EEG as a neuroimaging tool lies in its high temporal resolution, cost-effectiveness, and portability. Nevertheless, the feasibility of using EEG for visual information decoding remains a subject of ongoing inquiry. In this review, we explore the neural correlates of this visual information, specifically focusing on visual features such as colour, shapes, texture, and also naturalistic whole objects. We begin to examine which visual features can be effectively measured using EEG, taking into account its inherent characteristics, such as its measurement depth, limited spatial resolution, and high temporal resolution. Using a systematic approach, the review provides an in-depth analysis of the current state-of-the-art in EEG-based decoding of visual features for BCI purposes. Finally, we address some potential methodological improvements that can be made to the experimental design in EEG visual information decoding studies, such as palette cleansing, augmentation to bolster dataset size, and fusion of neuroimaging techniques. [ABSTRACT FROM AUTHOR]

Decoding motor imagery (MI) using deep learning in cortical level has potential in brain computer interface based intelligent rehabilitation. However, a mass of dipoles is inconvenient to extract the personalized features and requires a more complex neural network. In consideration of the structural and functional similarity of the neurons in a neuroanatomical region, i.e., a region of interest (ROI), we propose that the comprehensive performance of each ROI may be reflected by a specific representative dipole (RD), and the time-frequency spectrums of all RDs are applied simultaneously to Random Forest algorithm to give a quantitative metric of each ROI importance (RI). Then, the more divided sub-band spectral powers are reinforced by RI, and they are interpolated to a 2-dimensional (2D) plane transformed from 3D space of all RDs, yielding an ensemble representation of RD feature image sequences (ERDFIS). Furthermore, a lightweight network, including 2D separable convolution and gated recurrent unit (2DSCG), is developed to extract and classify the frequency-spatial and temporal features from ERDFIS, forming a novel MI decoding method in cortical level (called ERDFIS-2DSCG). Based on two public datasets, the decoding accuracies of ten-fold cross-validation are 89.89% and 94.35%, respectively. The results suggest that RD can embody the overall property of ROI in time-frequency-space domains, and ROI importance is helpful to highlight the subject-based characteristics of MI-EEG. Meanwhile, 2DSCG is matched well with ERDFIS, jointly improving the decoding performance.

This study is intended to improve the motor imagery classification performance of two-class data points using newly developed covariance decentering eigenface analysis (CDC-EFA). When extracting the classification for the given data points, it is necessary to precisely distinguish the classes because the left and right features are difficult to differentiate. However, when centering is performed, the unique average data of each feature are lost, making them difficult to distinguish. CDC-EFA reverses the centering method to enhance data characteristics, making it possible to assign weights to data with a high correlation with other data. In experiments with the BCI dataset, the proposed CDC-EFA method was used after preprocessing by filtering and selecting the electroencephalogram data. The decentering process was then performed on the covariance matrix calculated when acquiring the unique face. Subsequently, we verified the classification improvement performance via simulations using several BCI competition datasets. Several signal processing methods were applied to compare the accuracy results of the motor imagery classification. The proposed CDC-EFA method yielded an average accuracy result of 98.89%. Thus, it showed improved accuracy compared with the other methods and stable performance with a low standard deviation.

Brain computer interface (BCI) based on motor imagery (MI) provides a communication channel between the brain and a computer or other communication devices. In BCI system, electroencephalogram (EEG) is the most widely used brain signals, which has the function of responding to the physiological and emotional information of the brain. The recognition of MI EEG signals is the core technology of MI-BCI system. In this study, semi-supervised learning strategy is adopted in model training, and semi-supervised classifier with projection graph embedding (SCPGE) is proposed for MI EEG recognition. SCPGE combines graph embedding projection and sparse constraint into semi-supervised least squares model to learn the discriminative structure of EEG data in projection space, and adaptively learns the similarity matrix and pseudo-label matrix based on manifold learning. Unlike the "two-step" strategy of constructing graph embedding and classifier, these two factors, together with subspace projection and pseudo-label estimation, are simultaneously considered in the objection function and optimized in the iteration process. In addition, SCPGE uses the class by class based ℓ2, 1-norm inter class sparsity constraint to exploit the correlation between samples, so as to obtain the discriminative projection matrix and classifier. Experiments on the publicly available MI EEG datasets show that SCPGE classifier can significantly improve the recognition accuracy. [ABSTRACT FROM AUTHOR]

In this study, a few-shot transfer learning approach was introduced to decode movement intention from electroencephalographic (EEG) signals, allowing to recognize new tasks with minimal adaptation. To this end, a dataset of EEG signals recorded during the preparation of complex sub-movements was created from a publicly available data collection. The dataset was divided into two parts: the source domain dataset (including 5 classes) and the support (target domain) dataset, (including 2 classes) with no overlap between the two datasets in terms of classes. The proposed methodology consists in projecting EEG signals into the space-frequency-time domain, in processing such projections (rearranged in channels × frequency frames) by means of a custom EEG-based deep neural network (denoted as EEGframeNET5), and then adapting the system to recognize new tasks through a few-shot transfer learning approach. The proposed method achieved an average accuracy of 72.45 ± 4.19% in the 5-way classification of samples from the source domain dataset, outperforming comparable studies in the literature. In the second phase of the study, a few-shot transfer learning approach was proposed to adapt the neural system and make it able to recognize new tasks in the support dataset. The results demonstrated the system's ability to adapt and recognize new tasks with an average accuracy of 80 ± 0.12% in discriminating hand opening/closing preparation and outperforming reported results in the literature. This study suggests the effectiveness of EEG in capturing information related to the motor preparation of complex movements, potentially paving the way for BCI systems based on motion planning decoding. The proposed methodology could be straightforwardly extended to advanced EEG signal processing in other scenarios, such as motor imagery or neural disorder classification. [ABSTRACT FROM AUTHOR]

The advent of intelligent technologies, notably Brain–Computer Interfaces (BCIs), has introduced novel privacy dilemmas. Ensuring judicious privacy transfer is imperative for the application of BCI technology and pivotal for fostering economic and technological progress. This study adopts privacy transfer as the research perspective and employs an ethical matrix as the research method. It establishes BCI users as the central core interests, with marketers, developers, and medical personnel as stakeholders. Departing from the binary opposition of public and private in traditional privacy theory, this article proposes ethical principles such as maximizing benefits, minimizing harm, and respecting independent decision-making power. It constructs a judgment matrix for the privacy transfer of BCIs, utilizing this matrix to identify ethical risks like privacy disclosure and hijacking. This study analyzes the reasons for risks, aiming to overcome dilemmas and construct an ethical matrix to explore privacy transfer boundary division methods suitable for BCI technology and tailored to different stakeholders. [ABSTRACT FROM AUTHOR]

Small availability of electroencephalograph (EEG) data makes the training of Brain-Computer Interface (BCI) significantly a difficult task. Recently, Deep Learning (DL) has shown tremendous performance in all domains but it requires an abundant amount of data for the training. Another challenging task is the non-stationary nature of EEG data. In this study, we illustrate a roadmap of various adversarial networks, review Transfer Learning (TL) methods, and give insights on the development route to generate and classify motor imagery (MI) EEG data. To make the use of BCI more practical, a Comprehensive review of Generative Adversarial Networks (GANs) and TL was performed to address the following questions: (1) Why GANs, rather than expansion on traditional data augmentation technique? (2) What input formulations have been used for generating brain signal data using GANs? (3) Are there particular GANs suitable for EEG data? (4) How can we solve the problem of data scarcity and the non-stationary nature of EEG? Comprehensive literature on data augmentation using GANs and feature transferring using advanced TL has been performed. The studies were examined based on different GAN architectures, various input formulations of EEG data, and different advanced TL techniques. For MI EEG data augmentation, signal input formulation is classified into five types and advanced TL techniques into seven types. For all these categories, the previous work from a technical point of view is discussed. Towards the end of the paper, a novelistic hybrid approach based on data augmentation and TL has been put forward for classifying MI EEG data with a short-term calibration process. To the best of our knowledge, no review article has completely discussed the various variants of GANs for augmenting brain signals. This review article will help the researchers in the deployment of BCI in future research. [ABSTRACT FROM AUTHOR]