Brain Computer Interface Signals Research Articles

Temporal-spatial cross attention network for recognizing imagined characters

Previous research has primarily employed deep learning models such as Convolutional Neural Networks (CNNs), and Recurrent Neural Networks (RNNs) for decoding imagined character signals. These approaches have treated the temporal and spatial features of the signals in a sequential, parallel, or single-feature manner. However, there has been limited research on the cross-relationships between temporal and spatial features, despite the inherent association between channels and sampling points in Brain-Computer Interface (BCI) signal acquisition, which holds significant information about brain activity. To address the limited research on the relationships between temporal and spatial features, we proposed a Temporal-Spatial Cross-Attention Network model, named TSCA-Net. The TSCA-Net is comprised of four modules: the Temporal Feature (TF), the Spatial Feature (SF), the Temporal-Spatial Cross (TSCross), and the Classifier. The TF combines LSTM and Transformer to extract temporal features from BCI signals, while the SF captures spatial features. The TSCross is introduced to learn the correlations between the temporal and spatial features. The Classifier predicts the label of BCI data based on its characteristics. We validated the TSCA-Net model using publicly available datasets of handwritten characters, which recorded the spiking activity from two micro-electrode arrays (MEAs). The results showed that our proposed TSCA-Net outperformed other comparison models (EEG-Net, EEG-TCNet, S3T, GRU, LSTM, R-Transformer, and ViT) in terms of accuracy, precision, recall, and F1 score, achieving 92.66%\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\%$$\\end{document}, 92.77%\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\%$$\\end{document}, 92.70%\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\%$$\\end{document}, and 92.58%\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\%$$\\end{document}, respectively. The TSCA-Net model demonstrated a 3.65%\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\%$$\\end{document} to 7.49%\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\%$$\\end{document} improvement in accuracy over the comparison models.

A systematic evaluation of Euclidean alignment with deep learning for EEG decoding

Objective: Electroencephalography signals are frequently used for various Brain–Computer interface (BCI) tasks. While deep learning (DL) techniques have shown promising results, they are hindered by the substantial data requirements. By leveraging data from multiple subjects, transfer learning enables more effective training of DL models. A technique that is gaining popularity is Euclidean alignment (EA) due to its ease of use, low computational complexity, and compatibility with DL models. However, few studies evaluate its impact on the training performance of shared and individual DL models. In this work, we systematically evaluate the effect of EA combined with DL for decoding BCI signals. Approach: We used EA as a pre-processing step to train shared DL models with data from multiple subjects and evaluated their transferability to new subjects. Main results: Our experimental results show that it improves decoding in the target subject by 4.33% and decreases convergence time by more than 70%. We also trained individual models for each subject to use as a majority-voting ensemble classifier. In this scenario, using EA improved the 3-model ensemble accuracy by 3.71%. However, when compared to the shared model with EA, the ensemble accuracy was 3.62% lower. Significance: EA succeeds in the task of improving transfer learning performance with DL models and, could be used as a standard pre-processing technique.

A hierarchical recursive feature elimination algorithm to develop brain computer interface application of user behavior for statistical reasoning and decision making

BackgroundWith the aid of a brain computer interface (BCI), users can communicate and receive signals wirelessly or over wired connections to operate smart devices. A BCI classifier's architecture is quite difficult since numerous elements should be combined. These elements are made up of brain signals, which also include high levels of weak sounds that could provide reliable participant recordings of daily activities. We must use computer vision techniques to create a model in order to control those information. The high dimension and volume of signals present the classification classifier with its primary obstacles. New methodDue to this, we extracted and classified the brain activity in this study, and we also presented a novel hierarchical recursive feature elimination method that we refer to as HRFE embracing noisy additions. HRFE makes a variety of categorization suggestions to eliminate bias in classifying BCI systems of different types. We put the HRFE to the test on two BCI signal data sets—specifically, dataset I and BCI contests III—using shallow and deep convolution network classification techniques. Just a grid of assets is used to create electrocorticography (ECoG) signals on the contralateral (right) motor cortex, and these signals are recorded in the BCI contests III database. ResultsUsing ECoG signals, we choose the top 20 features that have the biggest effects on distortion and classification selection. Comparison with existing methodsThe simulation findings show that HRFE has a significant computer vision enhancement when compared to comparable feature selection methods in the literature, particularly for ECoG signal, which achieves about 93% reliability.

Investigating the informative brain region in multiclass electroencephalography and near infrared spectroscopy based BCI system using band power based features

In recent years, various brain imaging techniques have been used as input signals for brain-computer interface (BCI) systems. Electroencephalography (EEG) and near-infrared spectroscopy (NIRS) are two prominent techniques in this field, each with its own advantages and limitations. As a result, there is a growing tendency to integrate these methods in a hybrid within BCI systems. The primary aim of this study is to identify highly functional brain regions within an EEG + NIRS-based BCI system. To achieve this, the research focused on identifying EEG electrodes positioned in different brain lobes and then investigating the functionality of each lobe. The methodology involved segmenting the EEG + NIRS dataset into 2.4 s time windows, and then extracting band-power based features from these segmented signals. A classification algorithm, specifically the k-nearest neighbor algorithm, was then used to classify the features. The result was a remarkable classification accuracy (CA) of 95.54%±1.31 when using the active brain region within the hybrid model. These results underline the effectiveness of the proposed approach, as it outperformed both standalone EEG and NIRS modalities in terms of CA by 5.19% and 40.90%, respectively. Furthermore, the results confirm the considerable potential of the method in classifying EEG + NIRS signals recorded during tasks such as reading text while scrolling in different directions, including right, left, up and down. This research heralds a promising step towards enhancing the capabilities of BCI systems by harnessing the synergistic power of EEG and NIRS technologies.

Combining Robotic Vision with Non-Invasive Brain-Computer Interfaces Development and Future Directions

The profound growth in brain-computer interface (BCI) technology has brought forth novel interdisciplinary applications, particularly in the realm of robotics. This review delves into the challenges of using non-invasive BCIs for precise robotic arm operations, with an emphasis on the transformative potential of integrating BCI with machine vision. Based on some problems in BCI applications, this paper emphasizes the use of machine vision combined with BCI signals to help non-invasive brain-computer interfaces improve the correctness and efficiency. Through detailed analysis, it is demonstrated how computer vision complements BCI, ameliorating issues like inherent noise and decoding inefficiencies associated with non-invasive BCIs. Moreover, the discussion touches upon the enhanced user experience offered by this integrated approach, and the potential it holds for addressing the compatibility challenges in BCIs. Although the combination of the two technologies can solve mutual problems, there are also certain limitations. For example, two different data may be more complex, so there are higher requirements for algorithms and processing methods. In addition, the development of a combination of two devices The system will have higher overhead, making it impossible for the average person to afford the cost of using it at the same time。As BCI technology continues its upward trajectory, this synthesis with robotic vision heralds a new era of harmonized human-machine interactions.

Detection of auditory hallucinations from electroencephalographic brain–computer interface signals

Schizophrenia is a chronic psychiatric disorder that is highly debilitating. One of the most frequent symptoms is the presence of auditory hallucinations (AH), which could be related to alterations in brain electrical activity measurable with electroencephalography (EEG). Although many previous works have recorded EEG signals of schizophrenia patients with medical EEG devices, the study of AH has never been developed by means of portable EEG measuring instruments. Therefore, the aim of this study is to detect AH in schizophrenia patients with a wireless EEG device. For that purpose, the spectral power from EEG recordings of periods with and without AH has been evaluated in a group of nine schizophrenia patients. Results reported that the main activation during hallucinations was found in right frontal locations, whereas the left hemisphere presented a stronger activation in hallucination-free periods. Furthermore, a generalized decrease of spectral power in hallucination with respect to hallucination-free episodes has been observed. Hence, this work demonstrates the possibility of detecting AH episodes with a wearable EEG device. In addition, the results obtained were compatible with the default model network, reporting a greater activation during no hallucination periods compared to hallucination moments.

A Comparative Performance Study on the Time Intervals of Hybrid Brain–Computer Interface Signals

A Comparative Performance Study on the Time Intervals of Hybrid Brain–Computer Interface Signals

Machine Learning-Based Classification of Hybrid BCI Signals using Mayfly-Optimized Multiclass Weighted Random Forest

The Brain-Computer Interface (BCI) technologies have excellent clinical and non-clinical uses. Among the most popular imaging methods adopted in BCI technologies is electroencephalography (EEG). But EEG signals are typically quite complicated, so analyzing them necessitates a significant amount of effort. With the help of machine learning (ML), this research investigates the feasibility of a BCI platform based on the motor imagery (MI) concept. The steps of pre-processing, feature extraction and classification are the underpinning of any conventional ML model. To train such a model, however, a large amount of data is needed. To address this gap, this work introduces a new mayfly-optimized multiclass weighted random forest (MFO-MWRF) technique that uses retrieved features as input to mitigate the need for this supplementary data. In this study, we gather a dataset of hybrid EEG and fNIRS motor imagery that can be pre-processed using a Wiener filter (WF) to filter out noisier signals without affecting the high-quality images. The characteristics are extracted using the discrete wavelet transform (DWT). The research results indicate that the proposed approach achieves the best performance compared to existing approaches for classifying motor movement images.

Comparison of Sub-Scalp EEG and Endovascular Stent-Electrode Array for Visual Evoked Potential Brain-Computer Interface.

Brain-computer interfaces (BCI) have the potential to improve the quality of life for persons with paralysis. Sub-scalp EEG provides an alternative BCI signal acquisition method that compromises between the limitations of traditional EEG systems and the risks associated with intracranial electrodes, and has shown promise in long-term seizure monitoring. However, sub-scalp EEG has not yet been assessed for suitability in BCI applications. This study presents a preliminary comparison of visual evoked potentials (VEPs) recorded using sub-scalp and endovascular stent electrodes in a sheep. Sub-scalp electrodes recorded comparable VEP amplitude, signal-to-noise ratio and bandwidth to the stent electrodes.Clinical relevance-This is the first study to report a comparision between sub-scalp and stent electrode array signals. The use of sub-scalp EEG electrodes may aid in the long-term use of brain-computer interfaces.

DeepQ Residue Analysis of Brain-Computer Classification and Prediction using Deep CNN

Purpose: During this article, we are going to consistently explore the kinds of brain signals for Brain Computer Interface (BCI) and discover the related ideas of the in-depth learning of brain signal analysis. We talk review recent machine Associate in Nursing deep learning approaches within the detection of two brain unwellness just like Alzheimer' disease (AD), brain tumor. In addition, a quick outline of the varied marker extraction techniques that want to characterize brain diseases is provided. Project work, the automated tool for tumor classification supported by image resonance information. It is given by various convolutional neural network (CNN) samples with ResNet Squeeze. Objectives: This paper is to analyse brain diseases classification and prediction using deep learning concepts. Deep learning is a group of machine learning in computer science that has networks capable of unattended learning from data that's unstructured or unlabelled. conjointly called deep neural learning could be a operation of Al that mimics however, the human brain works in process data to be used in object detection, speech recognition, language translation, and call making. Methodology: To test the result by measuring the semantics in the input sentence, the creation of embedded vectors with the same value is achieved. In this case, a sentence with a different meaning is used. Since it is difficult to collect a large amount of labelled data, it simulates the signal in different sentences. As you progress, teach for extra complicated capabilities with layers from the shared output of preceding layers. We examine forms of deep getting to know methods: LSTM Model with RNN, CNN results. CNN is a multi-layer feed-ahead neural community. The gadget weight is up to date via way of means of the Backpropagation Error procedure. TF-IDF of time period t in record d. Unlike traditional precis models, the ahead engineering feature is predicated on understanding of the required records area. In addition, this framework is related to synthetic abbreviations, which might be then used to put off the impact of guide function improvement and records labelling. Results: We will follow this option of 257 factors as vector enter category algorithms. It is a aggregate of the subsequent forms with enter layer, convolution layer, linear unit (ReLU) layer, pooling layer, absolutely coupled layer. A recurrent neural community (RNN) is a form of a neural community that defines connections among loop units. This creates an inner community country that allows. Feature choice is a extensively used approach that improves the overall performance of classifiers. Here, we examine the consequences of conventional magnificence fires with correlation-primarily based totally man or woman choice. Originality: Analysis of Brain Diseases with the approach of Computer Classification and Prediction using Deep CNN with ResNet Squeeze. Type of Paper: Conceptual research paper.

On the Influence of Aging on Classification Performance in the Visual EEG Oddball Paradigm Using Statistical and Temporal Features.

The utilization of a non-invasive electroencephalogram (EEG) as an input sensor is a common approach in the field of the brain-computer interfaces (BCI). However, the collected EEG data pose many challenges, one of which may be the age-related variability of event-related potentials (ERPs), which are often used as primary EEG BCI signal features. To assess the potential effects of aging, a sample of 27 young and 43 older healthy individuals participated in a visual oddball study, in which they passively viewed frequent stimuli among randomly occurring rare stimuli while being recorded with a 32-channel EEG set. Two types of EEG datasets were created to train the classifiers, one consisting of amplitude and spectral features in time and another with extracted time-independent statistical ERP features. Among the nine classifiers tested, linear classifiers performed best. Furthermore, we show that classification performance differs between dataset types. When temporal features were used, maximum individuals' performance scores were higher, had lower variance, and were less affected overall by within-class differences such as age. Finally, we found that the effect of aging on classification performance depends on the classifier and its internal feature ranking. Accordingly, performance will differ if the model favors features with large within-class differences. With this in mind, care must be taken in feature extraction and selection to find the correct features and consequently avoid potential age-related performance degradation in practice.

Enhancing DNN Models for EEG/ECoG BCI With a Novel Data-Driven Offline Optimization Method

A better understanding of ElectroEncephaloGraphy (EEG) and ElectroCorticoGram (ECoG) signals would get us closer to comprehending brain functionality, creating new avenues for treating brain abnormalities and developing novel Brain-Computer Interface (BCI)-related applications. Deep Neural Networks (DNN)s have lately been employed with remarkable success to decode EEG/ECoG signals for BCI. However, the optimal architectural/training parameter values in these DNN architectures have yet to receive much attention. In addition, new data-driven optimization methodologies that leverage significant advancements in Machine Learning, such as the Transformer model, have recently been proposed. Because an exhaustive search on all possible architectural/training parameter values of the state-of-the-art DNN model (our baseline model) decoding the motor imagery EEG and finger tension ECoG signals comprising the BCI IV 2a and 4 datasets, respectively, would require prohibitively much time, this paper proposes an offline model-based optimization technique based on the Transformer model for the discovery of the optimal architectural/training parameter values for that model. Our findings indicate that we could pick better values for the baseline model’s architectural/training parameters, enhancing the baseline model’s performance by up to 14.7% in the BCI IV 2a dataset and by up to 61.0% in the BCI IV 4 dataset.

Flexible coding scheme for robotic arm control driven by motor imagery decoding

Objective. Brain computer interface (BCI) technology is an innovative way of information exchange, which can effectively convert physiological signals into control instructions of machines. Due to its spontaneity and device independence, the motor imagery (MI) electroencephalography (EEG) signal is used as a common BCI signal source to achieve direct control of external devices. Several online MI EEG-based systems have shown potential for rehabilitation. However, the generalization ability of the current classification model of MI tasks is still limited and the real-time prototype is far from widespread in practice. Approach. To solve these problems, this paper proposes an optimized neural network architecture based on our previous work. Firstly, the artifact components in the MI-EEG signal are removed by using the threshold and threshold function related to the artifact removal evaluation index, and then the data is augmented by the empirical mode decomposition (EMD) algorithm. Furthermore, the ensemble learning (EL) method and fine-tuning strategy in transfer learning (TL) are used to optimize the classification model. Finally, combined with the flexible binary encoding strategy, the EEG signal recognition results are mapped to the control commands of the robotic arm, which realizes multiple degrees of freedom control of the robotic arm. Main results. The results show that EMD has an obvious data amount enhancement effect on a small dataset, and the EL and TL can improve intra-subject and inter-subject model evaluation performance, respectively. The use of a binary coding method realizes the expansion of control instructions, i.e. four kinds of MI-EEG signals are used to complete the control of 7 degrees of freedom of the robotic arm. Significance. Our work not only improves the classification accuracy of the subject and the generality of the classification model while also extending the BCI control instruction set.

A Novel Quick-Response Eigenface Analysis Scheme for Brain-Computer Interfaces.

The brain–computer interface (BCI) is used to understand brain activities and external bodies with the help of the motor imagery (MI). As of today, the classification results for EEG 4 class BCI competition dataset have been improved to provide better classification accuracy of the brain computer interface systems (BCIs). Based on this observation, a novel quick-response eigenface analysis (QR-EFA) scheme for motor imagery is proposed to improve the classification accuracy for BCIs. Thus, we considered BCI signals in standardized and sharable quick response (QR) image domain; then, we systematically combined EFA and a convolution neural network (CNN) to classify the neuro images. To overcome a non-stationary BCI dataset available and non-ergodic characteristics, we utilized an effective neuro data augmentation in the training phase. For the ultimate improvements in classification performance, QR-EFA maximizes the similarities existing in the domain-, trial-, and subject-wise directions. To validate and verify the proposed scheme, we performed an experiment on the BCI dataset. Specifically, the scheme is intended to provide a higher classification output in classification accuracy performance for the BCI competition 4 dataset 2a (C4D2a_4C) and BCI competition 3 dataset 3a (C3D3a_4C). The experimental results confirm that the newly proposed QR-EFA method outperforms the previous the published results, specifically from 85.4% to 97.87% ± 0.75 for C4D2a_4C and 88.21% ± 6.02 for C3D3a_4C. Therefore, the proposed QR-EFA could be a highly reliable and constructive framework for one of the MI classification solutions for BCI applications.

Stockwell transform and semi-supervised feature selection from deep features for classification of BCI signals

Over the past few years, the processing of motor imagery (MI) electroencephalography (EEG) signals has been attracted for developing brain-computer interface (BCI) applications, since feature extraction and classification of these signals are extremely difficult due to the inherent complexity and tendency to artifact properties of them. The BCI systems can provide a direct interaction pathway/channel between the brain and a peripheral device, hence the MI EEG-based BCI systems seem crucial to control external devices for patients suffering from motor disabilities. The current study presents a semi-supervised model based on three-stage feature extraction and machine learning algorithms for MI EEG signal classification in order to improve the classification accuracy with smaller number of deep features for distinguishing right- and left-hand MI tasks. Stockwell transform is employed at the first phase of the proposed feature extraction method to generate two-dimensional time–frequency maps (TFMs) from one-dimensional EEG signals. Next, the convolutional neural network (CNN) is applied to find deep feature sets from TFMs. Then, the semi-supervised discriminant analysis (SDA) is utilized to minimize the number of descriptors. Finally, the performance of five classifiers, including support vector machine, discriminant analysis, k-nearest neighbor, decision tree, random forest, and the fusion of them are compared. The hyperparameters of SDA and mentioned classifiers are optimized by Bayesian optimization to maximize the accuracy. The presented model is validated using BCI competition II dataset III and BCI competition IV dataset 2b. The performance metrics of the proposed method indicate its efficiency for classifying MI EEG signals.

Improved Brain-Computer Interface Signal Recognition Algorithm Based on Few-Channel Motor Imagery.

Common spatial pattern (CSP) is an effective algorithm for extracting electroencephalogram (EEG) features of motor imagery (MI); however, CSP mainly aims at multichannel EEG signals, and its effect in extracting EEG features with fewer channels is poor—even worse than before using CSP. To solve the above problem, a new combined feature extraction method has been proposed in this study. For EEG signals from fewer channels (three channels), wavelet packet transform, fast ensemble empirical mode decomposition, and local mean decomposition were used to decompose the band-pass filtered EEG into multiple time–frequency components, and the corresponding components were selected according to the frequency characteristics of MI or the correlation coefficient between its time–frequency components and the original EEG signal. Furthermore, phase space reconstruction (PSR) was performed on the selected components after the three time-frequency decompositions, the maximum Lyapunov index was calculated, and the features were reconstructed; then, CSP projection mapping was used for the reconstructed features. The support vector machine probability output model was trained by the obtained three mappings. Probability outputs by three different support vector machines were then obtained. Finally, the classification of test samples was determined by the fusion of the Dempster–Shafer evidence theory at the decision level. The results showed that the accuracy of the proposed method was 95.71% on data set III of BCI competition II (left- and right-hand MI), which was 2.88% higher than the existing methods. On data set IIb of BCI competition IV, the average accuracy was 86.60%, which was 2.3% higher than the existing methods. This study verified the effectiveness of the proposed method and provided an approach for the research and development of the MI-BCI system based on fewer channels.

AI Prediction of Brain Signals for Human Gait Using BCI Device and FBG Based Sensorial Platform for Plantar Pressure Measurements.

Artificial intelligence (AI) in developing modern solutions for biomedical problems such as the prediction of human gait for human rehabilitation is gaining ground. An attempt was made to use plantar pressure information through fiber Bragg grating (FBG) sensors mounted on an in-sole, in tandem with a brain-computer interface (BCI) device to predict brain signals corresponding to sitting, standing and walking postures of a person. Posture classification was attained with an accuracy range between 87–93% from FBG and BCI signals using machine learning models such as K-nearest neighbor (KNN), logistic regression (LR), support vector machine (SVM), and naïve Bayes (NB). These models were used to identify electrodes responding to sitting, standing and walking activities of four users from a 16 channel BCI device. Six electrode positions based on the 10–20 system for electroencephalography (EEG) were identified as the most sensitive to plantar activities and found to be consistent with clinical investigations of the sensorimotor cortex during foot movement. A prediction of brain EEG corresponding to given FBG data with lowest mean square error (MSE) values (0.065–0.109) was made with the selection of a long-short term memory (LSTM) machine learning model when compared to the recurrent neural network (RNN) and gated recurrent unit (GRU) models.

State of the Art of Non-Invasive Electrode Materials for Brain-Computer Interface.

The brain–computer interface (BCI) has emerged in recent years and has attracted great attention. As an indispensable part of the BCI signal acquisition system, brain electrodes have a great influence on the quality of the signal, which determines the final effect. Due to the special usage scenario of brain electrodes, some specific properties are required for them. In this study, we review the development of three major types of EEG electrodes from the perspective of material selection and structural design, including dry electrodes, wet electrodes, and semi-dry electrodes. Additionally, we provide a reference for the current chaotic performance evaluation of EEG electrodes in some aspects such as electrochemical performance, stability, and so on. Moreover, the challenges and future expectations for EEG electrodes are analyzed.

Motor Imagery EEG Classification Using Random Subspace Ensemble Network with Variable Length Features

Classification of electroencephalography (EEG) signals for brain-computer interface has great impact on people having various kinds of physical disabilities. Motor imagery EEG signals of hand and leg movement classification can help people whose limbs are replaced by prosthetics. In this paper, random subspace ensemble network with variable length feature sampling has been proposed for improving the prediction accuracy of motor imagery EEG signal classification. The method has been tested on eight different subjects and a hybrid dataset of two subjects data combined. Discrete wavelet transform based de-noising scheme has been adopted to remove artifacts from the EEG signal. For sub-band selection, dual-tree complex wavelet Transform has been employed. Mutual information scoring has been used for univariate feature selection from the feature space. A comparative analysis has been carried out where random subspace ensemble network outperformed other classification models. The maximum accuracy obtained by the model was 90.00%. Furthermore, the model showed better performance on the hybrid dataset with an average accuracy of 86.00%. The findings of this study are expected to be useful in artificial limb movements through brain-computer interfacing for rehabilitation of people with such physical disabilities.

Single stimulus location for two inputs: A combined brain-computer interface based on Steady-State Visual Evoked Potential (SSVEP).

Brain-computer interfaces (BCI) help severely paralyzed people communicate with the outside world. One type of BCI depends on eye movements and has high information transfer (ITR) but is tiring for users and not applicable to people with eye dyskinesia. Conversely, independent BCIs enable attention shifts across visual stimuli without eye movement, but at the cost of a lower ITR. Steady-state visual evoked potential (SSVEP) is an oscillatory brain response and typically used as BCI signal sources because of high signal-to-noise ratio (SNR). Considering the effect of attentional modulation on the SSVEP, we proposed the novel concept of one-to-two BCI to optimize existing problems, wherein the target and other stimuli shared the same location. Specifically, two spatially overlapping stimuli were displayed in the center-of-view field, as in the independent BCI, and participants were required to divide their attention between the right and left visual fields, as in the dependent BCI. Using three different design schemes in two experiments, we aimed to provide a new framework for BCI design by exploring the feasibility of a combined BCI that can realize a single stimulus location for two inputs. The results strongly demonstrated that, even when the targets and distractors overlapped spatially, the former evoked stronger SSVEP responses. Notably, the BCI scheme based on the object-based attention could achieve a recognition rate as high as 83.2% and an ITR of 12.5 bits per minute. The feasibility of a one-to-two BCI design, which simplified the keyboard layout, reduced the attention shift, and relieved user fatigue, was established.