The Berlin Brain-Computer Interface: Accurate performance from first-session in BCI-naive subjects

A Brain-Controlled and User-Centered Intelligent Wheelchair: A Feasibility Study

Recently, due to physical aging, diseases, accidents, and other factors, the population with lower limb disabilities has been increasing, and there is consequently a growing demand for wheelchair products. Modern product design tends to be more intelligent and multi-functional than in the past, with the popularization of intelligent concepts. This supports the design of a new, fully functional, intelligent wheelchair that can assist people with lower limb disabilities in their day-to-day life. Based on the UCD (user-centered design) concept, this study focused on the needs of people with lower limb disabilities. Accordingly, the demand for different functions of intelligent wheelchair products was studied through a questionnaire survey, interview survey, literature review, expert consultation, etc., and the function and appearance of the intelligent wheelchair were then defined. A brain-machine interface system was developed for controlling the motion of the intelligent wheelchair, catering to the needs of disabled individuals. Furthermore, ergonomics theory was used as a guide to determine the size of the intelligent wheelchair seat, and eventually, a new intelligent wheelchair with the features of climbing stairs, posture adjustment, seat elevation, easy interaction, etc., was developed. This paper provides a reference for the design upgrade of the subsequently developed intelligent wheelchair products.

A Brain-Controlled Quadruped Robot: A Proof-of-Concept Demonstration

Coupling brain-computer interfaces (BCIs) and robotic systems in the future can enable seamless personal assistant systems in everyday life, with the requests that can be performed in a discrete manner, using one's brain activity only. These types of systems might be of a particular interest for people with locked-in syndrome (LIS) or amyotrophic lateral sclerosis (ALS) because they can benefit from communicating with robotic assistants using brain sensing interfaces. In this proof-of-concept work, we explored how a wireless and wearable BCI device can control a quadruped robot-Boston Dynamics' Spot. The device measures the user's electroencephalography (EEG) and electrooculography (EOG) activity of the user from the electrodes embedded in the glasses' frame. The user responds to a series of questions with YES/NO answers by performing a brain-teaser activity of mental calculus. Each question-answer pair has a pre-configured set of actions for Spot. For instance, Spot was prompted to walk across a room, pick up an object, and retrieve it for the user (i.e., bring a bottle of water) when a sequence resolved to a YES response. Our system achieved at a success rate of 83.4%. To the best of our knowledge, this is the first integration of wireless, non-visual-based BCI systems with Spot in the context of personal assistant use cases. While this BCI quadruped robot system is an early prototype, future iterations may embody friendly and intuitive cues similar to regular service dogs. As such, this project aims to pave a path towards future developments in modern day personal assistant robots powered by wireless and wearable BCI systems in everyday living conditions.

Multi-domain feature joint optimization based on multi-view learning for improving the EEG decoding

Background

Brain-computer interface (BCI) systems based on motor imagery (MI) have been widely used in neurorehabilitation. Feature extraction applied by the common spatial pattern (CSP) is very popular in MI classification. The effectiveness of CSP is highly affected by the frequency band and time window of electroencephalogram (EEG) segments and channels selected.

Objective

In this study, the multi-domain feature joint optimization (MDFJO) based on the multi-view learning method is proposed, which aims to select the discriminative features enhancing the classification performance.

Method

The channel patterns are divided using the Fisher discriminant criterion (FDC). Furthermore, the raw EEG is intercepted for multiple sub-bands and time interval signals. The high-dimensional features are constructed by extracting features from CSP on each EEG segment. Specifically, the multi-view learning method is used to select the optimal features, and the proposed feature sparsification strategy on the time level is proposed to further refine the optimal features.

Results

Two public EEG datasets are employed to validate the proposed MDFJO method. The average classification accuracy of the MDFJO in Data 1 and Data 2 is 88.29 and 87.21%, respectively. The classification result of MDFJO was significantly better than MSO (p < 0.05), FBCSP32 (p < 0.01), and other competing methods (p < 0.001).

Conclusion

Compared with the CSP, sparse filter band common spatial pattern (SFBCSP), and filter bank common spatial pattern (FBCSP) methods with channel numbers 16, 32 and all channels as well as MSO, the MDFJO significantly improves the test accuracy. The feature sparsification strategy proposed in this article can effectively enhance classification accuracy. The proposed method could improve the practicability and effectiveness of the BCI system.

Enhanced Motor Imagery Decoding by Calibration Model-Assisted With Tactile ERD

OBJECTIVE

In this study, we propose a tactile-assisted calibration method for a motor imagery (MI) based Brain-Computer Interface (BCI) system.

METHOD

In the proposed calibration, tactile stimulation was applied to the hand wrist to assist the subjects in the MI task, which is named SA-MI task. Then, classifier training in the SA-MI Calibration was performed using the SA-MI data, while the Conventional Calibration employed the MI data. After the classifiers were trained, the performance was evaluated on a common MI dataset.

RESULTS

Our study demonstrated that the SA-MI Calibration significantly improved the performance as compared with the Conventional Calibration, with a decoding accuracy of (78.3% vs. 71.3%). Moreover, the average calibration time could be reduced by 40%. This benefit of the SA-MI Calibration effect was further validated by an independent control group, which showed no improvement when tactile stimulation was not applied during the calibration phase. Further analysis showed that when compared with MI, greater motor-related cortical activation and higher R 2 value in the alpha-beta frequency band were induced in SA-MI.

CONCLUSION

Indeed, the SA-MI Calibration could significantly improve the performance and reduce the calibration time as compared with the Conventional Calibration.

SIGNIFICANCE

The proposed tactile stimulation-assisted MI Calibration method holds great potential for a faster and more accurate system setup at the beginning of BCI usage.

Talking with hands and feet: Selective somatosensory attention and fMRI enable robust and convenient brain-based communication

In brain-based communication, voluntarily modulated brain signals (instead of motor output) are utilized to interact with the outside world. The possibility to circumvent the motor system constitutes an important alternative option for severely paralyzed. Most communication brain-computer interface (BCI) paradigms require intact visual capabilities and impose a high cognitive load, but for some patients, these requirements are not given. In these situations, a better-suited, less cognitively demanding information-encoding approach may exploit auditorily-cued selective somatosensory attention to vibrotactile stimulation. Here, we propose, validate and optimize a novel communication-BCI paradigm using differential fMRI activation patterns evoked by selective somatosensory attention to tactile stimulation of the right hand or left foot. Using cytoarchitectonic probability maps and multi-voxel pattern analysis (MVPA), we show that the locus of selective somatosensory attention can be decoded from fMRI-signal patterns in (especially primary) somatosensory cortex with high accuracy and reliability, with the highest classification accuracy (85.93%) achieved when using Brodmann area 2 (SI-BA2) at a probability level of 0.2. Based on this outcome, we developed and validated a novel somatosensory attention-based yes/no communication procedure and demonstrated its high effectiveness even when using only a limited amount of (MVPA) training data. For the BCI user, the paradigm is straightforward, eye-independent, and requires only limited cognitive functioning. In addition, it is BCI-operator friendly given its objective and expertise-independent procedure. For these reasons, our novel communication paradigm has high potential for clinical applications.

Lexical and sublexical cortical tuning for print revealed by Steady-State Visual Evoked Potentials (SSVEPs) in early readers

There are multiple levels of processing relevant to reading that vary in their visual, sublexical, and lexical orthographic processing demands. Segregating distinct cortical sources for each of these levels has been challenging in EEG studies of early readers. To address this challenge, we applied recent advances in analyzing high-density EEG using Steady-State Visual Evoked Potentials (SSVEPs) via data-driven Reliable Components Analysis (RCA) in a group of early readers spanning from kindergarten to second grade. Three controlled stimulus contrasts-familiar words versus unfamiliar pseudofonts, familiar words versus pseudowords, and pseudowords versus nonwords-were used to isolate coarse print tuning, lexical processing, and sublexical orthography-related processing, respectively. First, three overlapping yet distinct neural sources-left vOT, dorsal parietal, and primary visual cortex were revealed underlying coarse print tuning. Second, we segregated distinct cortical sources for the other two levels of processing: lexical fine tuning over occipito-temporal/parietal regions; sublexical orthographic fine tuning over left occipital regions. Finally, exploratory group analyses based on children's reading fluency suggested that coarse print tuning emerges early even in children with limited reading knowledge, while sublexical and higher-level lexical processing emerge only in children with sufficient reading knowledge. RESEARCH HIGHLIGHTS: Cognitive processes underlying coarse print tuning, sublexical, and lexical fine tuning were examined in beginning readers. Three overlapping yet distinct neural sources-left ventral occipito-temporal (vOT), left temporo-parietal, and primary visual cortex-were revealed underlying coarse print tuning. Responses to sublexical orthographic fine tuning were found over left occipital regions, while responses to higher-level linguistic fine tuning were found over occipito-temporal/parietal regions. Exploratory group analyses suggested that coarse print tuning emerges in children with limited reading knowledge, while sublexical and higher-level linguistic fine tuning effects emerge in children with sufficient reading knowledge.

EEG motor imagery classification using deep learning approaches in naïve BCI users

Motor Imagery (MI)-Brain Computer-Interfaces (BCI) illiteracy defines that not all subjects can achieve a good performance in MI-BCI systems due to different factors related to the fatigue, substance consumption, concentration, and experience in the use. To reduce the effects of lack of experience in the use of BCI systems (naïve users), this paper presents the implementation of three Deep Learning (DL) methods with the hypothesis that the performance of BCI systems could be improved compared with baseline methods in the evaluation of naïve BCI users. The methods proposed here are based on Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM)/Bidirectional Long Short-Term Memory (BiLSTM), and a combination of CNN and LSTM used for upper limb MI signal discrimination on a dataset of 25 naïve BCI users. The results were compared with three widely used baseline methods based on the Common Spatial Pattern (CSP), Filter Bank Common Spatial Pattern (FBCSP), and Filter Bank Common Spatial-Spectral Pattern (FBCSSP), in different temporal window configurations. As results, the LSTM-BiLSTM-based approach presented the best performance, according to the evaluation metrics of Accuracy, F-score, Recall, Specificity, Precision, and ITR, with a mean performance of 80% (maximum 95%) and ITR of 10 bits/min using a temporal window of 1.5 s. The DL Methods represent a significant increase of 32% compared with the baseline methods (p< 0.05). Thus, with the outcomes of this study, it is expected to increase the controllability, usability, and reliability of the use of robotic devices in naïve BCI users.

Evidence of Chaos in Electroencephalogram Signatures of Human Performance: A Systematic Review

(1) Background: Chaos, a feature of nonlinear dynamical systems, is well suited for exploring biological time series, such as heart rates, respiratory records, and particularly electroencephalograms. The primary purpose of this article is to review recent studies using chaos theory and nonlinear dynamical methods to analyze human performance in different brain processes. (2) Methods: Several studies have examined chaos theory and related analytical tools for describing brain dynamics. The present study provides an in-depth analysis of the computational methods that have been proposed to uncover brain dynamics. (3) Results: The evidence from 55 articles suggests that cognitive function is more frequently assessed than other brain functions in studies using chaos theory. The most frequently used techniques for analyzing chaos include the correlation dimension and fractal analysis. Approximate, Kolmogorov and sample entropy account for the largest proportion of entropy algorithms in the reviewed studies. (4) Conclusions: This review provides insights into the notion of the brain as a chaotic system and the successful use of nonlinear methods in neuroscience studies. Additional studies of brain dynamics would aid in improving our understanding of human cognitive performance.

Improvement of brain-computer interface in motor imagery training through the designing of a dynamic experiment and FBCSP

Motor imagery (MI) can produce a specific brain pattern when the subject imagines performing a particular action without any actual body movements. According to related previous research, the improvement of the training of MI brainwaves can be adopted by feedback methods in which the analysis of brainwave characteristics is very important. The aim of this study was to improve the subject's MI and the accuracy of classification. In order to ameliorate the accuracy of the MI of the left and right hand, the present study designed static and dynamic visual stimuli in experiments so as to evaluate which one can improve subjects' imagination training. Additionally, the filter bank common spatial pattern (FBCSP) method was used to divide the frequency band range of the brainwaves into multiple segments, following which linear discriminant analysis (LDA) was adopted for classification. The results revealed that the averaged false positive rate (FPR) under FBCSP-LDA in the dynamic MI experiment was the lowest FPR (23.76%). As such, this study suggested that a combination of the dynamic MI experiment and the FBCSP-LDA method improved the overall prediction error rate and ameliorated the performance of the MI brain-computer interface.

[Current approaches to the use of robotic devices in rehabilitation complex of children with cerebral palsy]

Cerebral palsy is a neurological disease that is associated with multiple motor impairments and dysfunctions in children. The effective recovery of motor activity in both the upper and lower limbs is an important condition for the patient's social independence throughout his life. Robotic systems are new devices which are becoming increasingly popular as a part of the treatment of cerebral palsy. They have become a good addition to comprehensive rehabilitation therapy, including conducted at the sanatorium-resort stage. Further research is needed to clarify and prove the extent to which these devices help in treatment of children with cerebral palsy.

An Adaptive EEG Classification Algorithm Based on CSSD and ELM_Kernel for Small Training Samples

Rehabilitation technologies based on brain-computer interface (BCI) have become a promising approach for patients with dyskinesia to regain movement. In BCI experiment, there is often a necessary stage of calibration measurement before the feedback applications. To reduce the time required for initial training, it is of great importance to have a method which can learn to classify electroencephalogram (EEG) signals with a little amount of training data. In this paper, the novel combination of feature extraction and classification algorithm is proposed for classification of EEG signals with a small number of training samples. For feature extraction, the motor imagery EEG signals are pre-processed, and a relative distance criterion is defined to select the optimal combination of channels. Subsequently, common spatial subspace decomposition (CSSD) algorithm and extreme learning machine with kernel (ELM_Kernel) algorithm are used to perform the types of tasks classification of motor imagery EEG signals. Simulation results demonstrate that the proposed method produces a high average classification accuracy of 99.1% on BCI Competition III dataset IVa and 76.92% on BCI Competition IV dataset IIa outperforming state-of-the-art algorithms and obtains a good classification accuracy.

Future Solutions for Voice Rehabilitation in Laryngectomees: A Review of Technologies Based on Electrophysiological Signals

Loss of voice is a serious concern for a laryngectomee which should be addressed prior to planning the procedure. Voice rehabilitation options must be educated before the surgery. Even though many devices have been in use, each device has got its limitations. We are searching for probable future technologies for voice rehabilitation in laryngectomees and to familiarise with the ENT fraternity. We performed a bibliographic search using title/abstract searches and Medical Subject Headings (MeSHs) where appropriate, of the Medline, CINAHL, EMBASE, Web of Science and Google scholars for publications from January 1985 to January 2020. The obtained results with scope for the development of a device for speech rehabilitation were included in the review. A total of 1036 articles were identified and screened. After careful scrutining 40 articles have been included in this study. Silent speech interface is one of the topics which is extensively being studied. It is based on various electrophysiological biosignals like non-audible murmur, electromyography, ultrasound characteristics of vocal folds and optical imaging of lips and tongue, electro articulography and electroencephalography. Electromyographic signals have been studied in laryngectomised patients. Silent speech interface may be the answer for the future of voice rehabilitation in laryngectomees. However, all these technologies are in their primitive stages and are potential in conforming into a speech device.

EEG Channel Selection Techniques in Motor Imagery Applications: A Review and New Perspectives

Communication, neuro-prosthetics, and environmental control are just a few applications for disabled persons who use robots and manipulators that use brain-computer interface (BCI) systems. The brain's motor imagery (MI) signal is an essential input for a brain-related task in BCI applications. Due to their noninvasive, portability, and cost-effectiveness, electroencephalography (EEG) signals are the most widely used input in BCI systems. The EEG data are often collected from more than 100 different locations in the brain; channel selection techniques are critical for selecting the optimum channels for a given application. However, when analyzing EEG data, the principal purpose of channel selection is to reduce computational complexity, improve classification accuracy by avoiding overfitting, and reduce setup time. Several channel selection assessment algorithms, both with and without classification-based methods, extracted appropriate channel subsets using defined criteria. Therefore, based on the exhaustive analysis of the EEG channel selection, this manuscript analyses several existing studies to reduce the number of noisy channels and improve system performance. We review several existing works to find the most promising MI-based EEG channel selection algorithms and associated classification methodologies on various datasets. Moreover, we focus on channel selection methods that choose fewer channels with great precision. Finally, our main finding is that a smaller channel set, typically 10-30% of total channels, provided excellent performance compared to other existing studies.

Virtual Intelligence: A Systematic Review of the Development of Neural Networks in Brain Simulation Units

The functioning of the brain has been a complex and enigmatic phenomenon. From the first approaches made by Descartes about this organism as the vehicle of the mind to contemporary studies that consider the brain as an organism with emergent activities of primary and higher order, this organism has been the object of continuous exploration. It has been possible to develop a more profound study of brain functions through imaging techniques, the implementation of digital platforms or simulators through different programming languages and the use of multiple processors to emulate the speed at which synaptic processes are executed in the brain. The use of various computational architectures raises innumerable questions about the possible scope of disciplines such as computational neurosciences in the study of the brain and the possibility of deep knowledge into different devices with the support that information technology (IT) brings. One of the main interests of cognitive science is the opportunity to develop human intelligence in a system or mechanism. This paper takes the principal articles of three databases oriented to computational sciences (EbscoHost Web, IEEE Xplore and Compendex Engineering Village) to understand the current objectives of neural networks in studying the brain. The possible use of this kind of technology is to develop artificial intelligence (AI) systems that can replicate more complex human brain tasks (such as those involving consciousness). The results show the principal findings in research and topics in developing studies about neural networks in computational neurosciences. One of the principal developments is the use of neural networks as the basis of much computational architecture using multiple techniques such as computational neuromorphic chips, MRI images and brain–computer interfaces (BCI) to enhance the capacity to simulate brain activities. This article aims to review and analyze those studies carried out on the development of different computational architectures that focus on affecting various brain activities through neural networks. The aim is to determine the orientation and the main lines of research on this topic and work in routes that allow interdisciplinary collaboration.

Determining optimal mobile neurofeedback methods for motor neurorehabilitation in children and adults with non-progressive neurological disorders: a scoping review

Background

Brain–computer interfaces (BCI), initially designed to bypass the peripheral motor system to externally control movement using brain signals, are additionally being utilized for motor rehabilitation in stroke and other neurological disorders. Also called neurofeedback training, multiple approaches have been developed to link motor-related cortical signals to assistive robotic or electrical stimulation devices during active motor training with variable, but mostly positive, functional outcomes reported. Our specific research question for this scoping review was: for persons with non-progressive neurological injuries who have the potential to improve voluntary motor control, which mobile BCI-based neurofeedback methods demonstrate or are associated with improved motor outcomes for Neurorehabilitation applications?

Methods

We searched PubMed, Web of Science, and Scopus databases with all steps from study selection to data extraction performed independently by at least 2 individuals. Search terms included: brain machine or computer interfaces, neurofeedback and motor; however, only studies requiring a motor attempt, versus motor imagery, were retained. Data extraction included participant characteristics, study design details and motor outcomes.

Results

From 5109 papers, 139 full texts were reviewed with 23 unique studies identified. All utilized EEG and, except for one, were on the stroke population. The most commonly reported functional outcomes were the Fugl-Meyer Assessment (FMA; n = 13) and the Action Research Arm Test (ARAT; n = 6) which were then utilized to assess effectiveness, evaluate design features, and correlate with training doses. Statistically and functionally significant pre-to post training changes were seen in FMA, but not ARAT. Results did not differ between robotic and electrical stimulation feedback paradigms. Notably, FMA outcomes were positively correlated with training dose.

Conclusion

This review on BCI-based neurofeedback training confirms previous findings of effectiveness in improving motor outcomes with some evidence of enhanced neuroplasticity in adults with stroke. Associative learning paradigms have emerged more recently which may be particularly feasible and effective methods for Neurorehabilitation. More clinical trials in pediatric and adult neurorehabilitation to refine methods and doses and to compare to other evidence-based training strategies are warranted.

An EEG-based asynchronous MI-BCI system to reduce false positives with a small number of channels for neurorehabilitation: A pilot study

Many studies have used motor imagery-based brain–computer interface (MI-BCI) systems for stroke rehabilitation to induce brain plasticity. However, they mainly focused on detecting motor imagery but did not consider the effect of false positive (FP) detection. The FP could be a threat to patients with stroke as it can induce wrong-directed brain plasticity that would result in adverse effects. In this study, we proposed a rehabilitative MI-BCI system that focuses on rejecting the FP. To this end, we first identified numerous electroencephalogram (EEG) signals as the causes of the FP, and based on the characteristics of the signals, we designed a novel two-phase classifier using a small number of EEG channels, including the source of the FP. Through experiments with eight healthy participants and nine patients with stroke, our proposed MI-BCI system showed 71.76% selectivity and 13.70% FP rate by using only four EEG channels in the patient group with stroke. Moreover, our system can compensate for day-to-day variations for prolonged session intervals by recalibration. The results suggest that our proposed system, a practical approach for the clinical setting, could improve the therapeutic effect of MI-BCI by reducing the adverse effect of the FP.

Decoding EEG rhythms offline and online during motor imagery for standing and sitting based on a brain-computer interface

Motor imagery (MI)-based brain-computer interface (BCI) systems have shown promising advances for lower limb motor rehabilitation. The purpose of this study was to develop an MI-based BCI for the actions of standing and sitting. Thirty-two healthy subjects participated in the study using 17 active EEG electrodes. We used a combination of the filter bank common spatial pattern (FBCSP) method and the regularized linear discriminant analysis (RLDA) technique for decoding EEG rhythms offline and online during motor imagery for standing and sitting. The offline analysis indicated the classification of motor imagery and idle state provided a mean accuracy of 88.51 ± 1.43% and 85.29 ± 1.83% for the sit-to-stand and stand-to-sit transitions, respectively. The mean accuracies of the sit-to-stand and stand-to-sit online experiments were 94.69 ± 1.29% and 96.56 ± 0.83%, respectively. From these results, we believe that the MI-based BCI may be useful to future brain-controlled standing systems.

Class-distinctiveness-based frequency band selection on the Riemannian manifold for oscillatory activity-based BCIs: preliminary results

Considering user-specific settings is known to enhance Brain-Computer Interface (BCI) performances. In particular, the optimal frequency band for oscillatory activity classification is highly user-dependent and many frequency band selection methods have been developed in the past two decades. However, it is not well studied whether those conventional methods can be efficiently applied to the Riemannian BCIs, a recent family of BCI systems that utilize the non-Euclidean nature of the data unlike conventional BCI pipelines. In this paper, we proposed a novel frequency band selection method working on the Riemannian manifold. The frequency band is selected considering the class distinctiveness as quantified based on the inter-class distance and the intra-class variance on the manifold. An advantage of this method is that the frequency bandwidth can be adjusted for each individual without intensive optimization steps. In a comparative experiment using a public dataset of motor imagery-based BCI, our method showed a substantial improvement in average accuracy over both a fixed broad frequency band and a popular conventional frequency band selection method. In particular, our method substantially improved performances for subjects with initially low accuracies. This preliminary result suggests the importance of developing new user-specific setting algorithms considering the manifold properties, rather than directly applying methods developed prior to the rise of the Riemannian BCIs.

Algorithm Contest of Calibration-free Motor Imagery BCI in the BCI Controlled Robot Contest in World Robot Contest 2021: A survey

Objective:

From September 10 to 13, 2021, the finals of the BCI Controlled Robot Contest in World Robot Contest 2021 were held in Beijing, China. Eleven teams participated in the Algorithm Contest of Calibration-free Motor Imagery BCI. The participants employed both traditional electroencephalograph (EEG) analysis methods and deep learning-based methods in the contest. In this paper, we reviewed the algorithms utilized by the participants, extracted the trends and highlighted interesting approaches from these methods to inform future contests and research recommendations.

Method:

First, we analyzed the algorithms in separate steps, including EEG channel and signal segment setup, prepossessing technology, and classification model. Then, we emphasized the highlights of each algorithm. Finally, we compared the competition algorithm with the SOTA algorithm.

Results:

The algorithm employed in the finals performed better than that of the SOTA algorithm. During the final stage of the contest, four of the top five teams used convolutional neural network models, suggesting that with the rapid development of deep learning, convolutional neural network-based models have been the most popular methods in the field of motor imagery BCI.

Riemannian channel selection for BCI with between-session non-stationarity reduction capabilities

OBJECTIVE

Between-session non-stationarity is a major challenge of current Brain-Computer Interfaces (BCIs) that affects system performance. In this paper, we investigate the use of channel selection for reducing between-session non-stationarity with Riemannian BCI classifiers. We use the Riemannian geometry framework of covariance matrices due to its robustness and promising performances. Current Riemannian channel selection methods do not consider between-session non-stationarity and are usually tested on a single session. Here, we propose a new channel selection approach that specifically considers non-stationarity effects and is assessed on multi-session BCI data sets.

METHODS

We remove the least significant channels using a sequential floating backward selection search strategy. Our contributions include: 1) quantifying the non-stationarity effects on brain activity in multi-class problems by different criteria in a Riemannian framework and 2) a method to predict whether BCI performance can improve using channel selection.

RESULTS

We evaluate the proposed approaches on three multi-session and multi-class mental tasks (MT)-based BCI datasets. They could lead to significant improvements in performance as compared to using all channels for datasets affected by between-session non-stationarity and to significant superiority to the state-of-the-art Riemannian channel selection methods over all datasets, notably when selecting small channel set sizes.

CONCLUSION

Reducing non-stationarity by channel selection could significantly improve Riemannian BCI classification accuracy.

SIGNIFICANCE

Our proposed channel selection approach contributes to make Riemannian BCI classifiers more robust to between-session non-stationarities.

F-Value Time-Frequency Analysis: Between-Within Variance Analysis

Studies on brain mechanisms enable us to treat various brain diseases and develop diverse technologies for daily life. Therefore, an analysis method of neural signals is critical, as it provides the basis for many brain studies. In many cases, researchers want to understand how neural signals change according to different conditions. However, it is challenging to find distinguishing characteristics, and doing so requires complex statistical analysis. In this study, we propose a novel analysis method, FTF (F-value time-frequency) analysis, that applies the F-value of ANOVA to time-frequency analysis. The proposed method shows the statistical differences among conditions in time and frequency. To evaluate the proposed method, electroencephalography (EEG) signals were analyzed using the proposed FTF method. The EEG signals were measured during imagined movement of the left hand, right hand, foot, and tongue. The analysis revealed the important characteristics which were different among different conditions and similar within the same condition. The FTF analysis method will be useful in various fields, as it allows researchers to analyze how frequency characteristics vary according to different conditions.

Functional Connectivity Analysis in Motor-Imagery Brain Computer Interfaces

Motor Imagery BCI systems have a high rate of users that are not capable of modulating their brain activity accurately enough to communicate with the system. Several studies have identified psychological, cognitive, and neurophysiological measures that might explain this MI-BCI inefficiency. Traditional research had focused on mu suppression in the sensorimotor area in order to classify imagery, but this does not reflect the true dynamics that underlie motor imagery. Functional connectivity reflects the interaction between brain regions during the MI task and resting-state network and is a promising tool in improving MI-BCI classification. In this study, 54 novice MI-BCI users were split into two groups based on their accuracy and their functional connectivity was compared in three network scales (Global, Large and Local scale) during the resting-state, left vs. right-hand motor imagery task, and the transition between the two phases. Our comparison of High and Low BCI performers showed that in the alpha band, functional connectivity in the right hemisphere was increased in High compared to Low aptitude MI-BCI users during motor imagery. These findings contribute to the existing literature that indeed connectivity might be a valuable feature in MI-BCI classification and in solving the MI-BCI inefficiency problem.

Distinct neural sources underlying visual word form processing as revealed by steady state visual evoked potentials (SSVEP)

EEG has been central to investigations of the time course of various neural functions underpinning visual word recognition. Recently the steady-state visual evoked potential (SSVEP) paradigm has been increasingly adopted for word recognition studies due to its high signal-to-noise ratio. Such studies, however, have been typically framed around a single source in the left ventral occipitotemporal cortex (vOT). Here, we combine SSVEP recorded from 16 adult native English speakers with a data-driven spatial filtering approach—Reliable Components Analysis (RCA)—to elucidate distinct functional sources with overlapping yet separable time courses and topographies that emerge when contrasting words with pseudofont visual controls. The first component topography was maximal over left vOT regions with a shorter latency (approximately 180 ms). A second component was maximal over more dorsal parietal regions with a longer latency (approximately 260 ms). Both components consistently emerged across a range of parameter manipulations including changes in the spatial overlap between successive stimuli, and changes in both base and deviation frequency. We then contrasted word-in-nonword and word-in-pseudoword to test the hierarchical processing mechanisms underlying visual word recognition. Results suggest that these hierarchical contrasts fail to evoke a unitary component that might be reasonably associated with lexical access.

Weak Feature Extraction and Strong Noise Suppression for SSVEP-EEG Based on Chaotic Detection Technology

Brain computer interface (BCI) is a novel communication method that does not rely on the normal neural pathway between the brain and muscle of human. It can transform mental activities into relevant commands to control external equipment and establish direct communication pathway. Among different paradigms, steady-state visual evoked potential (SSVEP) is widely used due to its certain periodicity and stability of control. However, electroencephalogram (EEG) of SSVEP is extremely weak and companied with multi-scale and strong noise. Existing algorithms for classification are based on the principle of template matching and spatial filtering, which cannot obtain satisfied performance of feature extraction under the multi-scale noise. Especially for the subjects produce weak response for external stimuli in EEG representation, i.e., BCI-Illiteracy subject, traditional algorithms are difficult to recognize the internal patterns of brain. To address this issue, a novel method based on Chaos theory is proposed to extract feature of SSVEP. The rule of this method is applying the peculiarity of nonlinear dynamics system to detect feature of SSVEP by judging the state changes of chaotic systems after adding weak EEG. To evaluate the validity of proposed method, this research recruit 32 subjects to participate the experiment. All subjects are divided into two groups according to the preliminary classification accuracy (mean acc >70% or < 70%) by canonical correlation analysis and we define the accuracy above 70% as group A (normal subjects), below 70% as group B (BCI-Illiteracy). Then, the classification accuracy and information transmission rate of two groups are verified using Chaotic theory. Experimental results show that all classification methods using in our study achieve good performance for normal subjects while chaos obtain excellent performance and significant improvements than traditional methods for BCI-Illiteracy.

The performance of a low-cost bio-amplifier on 3D human arm movement reconstruction

Objectives In this study, the performance of OpenBCI, a low-cost bio-amplifier, is assessed when used for 3D motion reconstruction. Methods Eleven scalp electrode locations from three subjects were used, with sampling rate of 125 Hz, subsequently band-pass filtered from 0.5 to 40 Hz. After segmentation into epochs, information-rich frequency ranges were determined using filter bank common spatial filter. Simultaneously, the actual hand motions of subjects were captured using a Microsoft Kinect sensor. Multimodal data streams were synchronized using the lab streaming layer (LSL) application. A modified version of an existing multiple linear regression models was employed to learn the relationship between the electroencephalography (EEG) feature input and the recorded kinematic data. To assess system performance with limited data, 10-fold cross validation was used. Results The most information-rich frequency bands for subjects were found to be in the ranges of 5 - 9 Hz and 33 - 37 Hz. Hand lateralization accuracy for the three subjects were 97.4, 78.7 and 96.9% respectively. 3D position reconstructed with an average correlation coefficient of 0.21, 0.47 and 0.38 respectively along three pre-defined axes, with the corresponding average correlation coefficients for velocity being 0.21, 0.36 and 0.25 respectively. The results compare favourably with a cross-section of existing results, while cost-per-electrode costs were 76% lower than the average per-electrode cost for similar systems and 44% lower than the cheapest previously-reported system. Conclusions This study has shown that low-cost bio-amplifiers such as the OpenBCI can be used for 3D motion reconstruction tasks.

A neurophysiological approach to spatial filter selection for adaptive brain–computer interfaces

Objective. The common spatial patterns (CSP) algorithm is an effective method to extract discriminatory features from electroencephalography (EEG) to be used by a brain–computer interface (BCI). However, informed selection of CSP filters typically requires oversight from a BCI expert to accept or reject filters based on the neurophysiological plausibility of their activation patterns. Our goal was to identify, analyze and automatically classify prototypical CSP patterns to enhance the prediction of motor imagery states in a BCI. Approach. A data-driven approach that used four publicly available EEG datasets was adopted. Cluster analysis revealed recurring, visually similar CSP patterns and a convolutional neural network was developed to distinguish between established CSP pattern classes. Furthermore, adaptive spatial filtering schemes that utilize the categorization of CSP patterns were proposed and evaluated. Main results. Classes of common neurophysiologically probable and improbable CSP patterns were established. Analysis of the relationship between these categories of CSP patterns and classification performance revealed discarding neurophysiologically improbable filters can decrease decoder performance. Further analysis revealed that the spatial orientation of EEG modulations can evolve over time, and that the features extracted from the original CSP filters can become inseparable. Importantly, it was shown through a novel adaptive CSP technique that adaptation in response to these emerging patterns can restore feature separability. Significance. These findings highlight the importance of considering and reporting on spatial filter activation patterns in both online and offline studies. They also emphasize to researchers in the field the importance of spatial filter adaptation in BCI decoder design, particularly for online studies with a focus on training users to develop stable and suitable brain patterns.

Brain Oscillations and Their Implications for Neurorehabilitation

Neural oscillation is rhythmic or repetitive neural activities, which can be observed at all levels of the central nervous system (CNS). The large-scale oscillations measured by electroencephalography have long been used in clinical practice and may have a potential for the usage in neurorehabilitation for people with various CNS disorders. The recent advancement of computational neuroscience has opened up new opportunities to explore clinical application of the results of neural oscillatory activity analysis to evaluation and diagnosis; monitoring the rehab progress; prognostication; and personalized rehabilitation planning in neurorehabilitation. In addition, neural oscillation is catching more attention to its role as a target of noninvasive neuromodulation in neurological disorders.

Brain-computer interface-triggered functional electrical stimulation therapy for rehabilitation of reaching and grasping after spinal cord injury: a feasibility study

STUDY DESIGN

Feasibility and preliminary clinical efficacy analysis in a single-arm interventional study.

OBJECTIVES

We developed a brain-computer interface-triggered functional electrical stimulation therapy (BCI-FEST) system for clinical application and conducted an interventional study to (1) assess its feasibility and (2) understand its potential clinical efficacy for the rehabilitation of reaching and grasping in individuals with sub-acute spinal cord injury (SCI).

SETTING

Spinal cord injury rehabilitation hospital-Toronto Rehabilitation Institute-Lyndhurst Centre.

METHODS

Five participants with sub-acute SCI completed between 12 and 40 1-hour sessions using BCI-FEST, with up to 5 sessions a week. We assessed feasibility by measuring participants' compliance with treatment, the occurrence of adverse events, BCI sensitivity, and BCI setup duration. Clinical efficacy was assessed using Functional Independence Measure (FIM) and Spinal Cord Independence Measure (SCIM), as primary outcomes. In addition, we used two upper-limb function tests as secondary outcomes.

RESULTS

On average, participants completed 29.8 sessions with no adverse events. Only one of the 149 sessions was affected by technical challenges. The BCI sensitivity ranged between 69.5 and 80.2%, and the mean BCI setup duration was ~11 min. In the primary outcomes, three out of five participants showed changes greater than the minimal clinically important differences (MCIDs). Additionally, the mean change in secondary outcome measures met the threshold for detecting MCID as well; four out of five participants achieved MCID.

CONCLUSIONS

The new BCI-FEST intervention is safe, feasible, and promising for the rehabilitation of reaching and grasping after SCI.

A Multifrequency Brain Network-Based Deep Learning Framework for Motor Imagery Decoding

Motor imagery (MI) is an important part of brain-computer interface (BCI) research, which could decode the subject's intention and help remodel the neural system of stroke patients. Therefore, accurate decoding of electroencephalography- (EEG-) based motion imagination has received a lot of attention, especially in the research of rehabilitation training. We propose a novel multifrequency brain network-based deep learning framework for motor imagery decoding. Firstly, a multifrequency brain network is constructed from the multichannel MI-related EEG signals, and each layer corresponds to a specific brain frequency band. The structure of the multifrequency brain network matches the activity profile of the brain properly, which combines the information of channel and multifrequency. The filter bank common spatial pattern (FBCSP) algorithm filters the MI-based EEG signals in the spatial domain to extract features. Further, a multilayer convolutional network model is designed to distinguish different MI tasks accurately, which allows extracting and exploiting the topology in the multifrequency brain network. We use the public BCI competition IV dataset 2a and the public BCI competition III dataset IIIa to evaluate our framework and get state-of-the-art results in the first dataset, i.e., the average accuracy is 83.83% and the value of kappa is 0.784 for the BCI competition IV dataset 2a, and the accuracy is 89.45% and the value of kappa is 0.859 for the BCI competition III dataset IIIa. All these results demonstrate that our framework can classify different MI tasks from multichannel EEG signals effectively and show great potential in the study of remodelling the neural system of stroke patients.

Multiclass Classification Based on Combined Motor Imageries

Motor imagery (MI) allows the design of self-paced brain–computer interfaces (BCIs), which can potentially afford an intuitive and continuous interaction. However, the implementation of non-invasive MI-based BCIs with more than three commands is still a difficult task. First, the number of MIs for decoding different actions is limited by the constraint of maintaining an adequate spacing among the corresponding sources, since the electroencephalography (EEG) activity from near regions may add up. Second, EEG generates a rather noisy image of brain activity, which results in a poor classification performance. Here, we propose a solution to address the limitation of identifiable motor activities by using combined MIs (i.e., MIs involving 2 or more body parts at the same time). And we propose two new multilabel uses of the Common Spatial Pattern (CSP) algorithm to optimize the signal-to-noise ratio, namely MC2CMI and MC2SMI approaches. We recorded EEG signals from seven healthy subjects during an 8-class EEG experiment including the rest condition and all possible combinations using the left hand, right hand, and feet. The proposed multilabel approaches convert the original 8-class problem into a set of three binary problems to facilitate the use of the CSP algorithm. In the case of the MC2CMI method, each binary problem groups together in one class all the MIs engaging one of the three selected body parts, while the rest of MIs that do not engage the same body part are grouped together in the second class. In this way, for each binary problem, the CSP algorithm produces features to determine if the specific body part is engaged in the task or not. Finally, three sets of features are merged together to predict the user intention by applying an 8-class linear discriminant analysis. The MC2SMI method is quite similar, the only difference is that any of the combined MIs is considered during the training phase, which drastically accelerates the calibration time. For all subjects, both the MC2CMI and the MC2SMI approaches reached a higher accuracy than the classic pair-wise (PW) and one-vs.-all (OVA) methods. Our results show that, when brain activity is properly modulated, multilabel approaches represent a very interesting solution to increase the number of commands, and thus to provide a better interaction.

Shapelet-transformed Multi-channel EEG Channel Selection

This article proposes an approach to select EEG channels based on EEG shapelet transformation, aiming to reduce the setup time and inconvenience for subjects and to improve the applicable performance of Brain-Computer Interfaces (BCIs). In detail, the method selects top- k EEG channels by solving a logistic loss-embedded minimization problem with respect to EEG shapelet learning, hyperplane learning, and EEG channel weight learning simultaneously. Especially, to learn distinguished EEG shapelets for weighting contributions of each EEG channel to the logistic loss, EEG shapelet similarity is also minimized during the procedure. Furthermore, the gradient descent strategy is adopted in the article to solve the non-convex optimization problem, which finally leads to the algorithm termed StEEGCS. In a result, classification accuracy, with those EEG channels selected by StEEGCS, is improved compared to that with all EEG channels, and classification time consumption is reduced as well. Additionally, the comparisons with several state-of-the-art EEG channel selection methods on several real-world EEG datasets also demonstrate the efficacy and superiority of StEEGCS.

Improvement motor imagery EEG classification based on sparse common spatial pattern and regularized discriminant analysis

BACKGROUND

The classification of psychological tasks such as motor imagery based on electroencephalography (EEG) signals is an essential issue in the brain computer interface (BCI) system. The feature extraction is an important issue for improving classification accuracy of BCI system.

NEW METHOD

For extracting discriminative features, common spatial pattern (CSP) is an effective feature extraction method. However, features extracted by CSP are dense, and even feature patterns are repeatedly selected in the feature space. A sparse CSP algorithm is proposed, which embeds the sparse techniques and iterative search into the CSP. To improve the classification performance, two regularization parameters are added to the traditional linear discriminant analysis (LDA).

RESULTS

The sparse CSP algorithm can select several channels of EEG signals with the most obvious features. The improved regularized discriminant analysis is used to solve the singularity problem and improve the feature classification accuracy. Comparison with Existing Method(s): The proposed algorithm was evaluated by the data set I of the IVth BCI competition and our dataset. The experimental results of the BCI competition dataset show that accuracy of the improved algorithm is 10.75 % higher than that of the traditional algorithm. Comparing with the currently existing methods for the same data, it also shows excellent classification performance. The effectiveness of the improved algorithm is also shown in experiments on our dataset.

CONCLUSIONS

It sufficiently proves that the improved algorithm proposed in this paper improves the classification performance of motor intent recognition.

Reduce brain computer interface inefficiency by combining sensory motor rhythm and movement-related cortical potential features

OBJECTIVE

Brain Computer Interface (BCI) inefficiency indicates that there would be 10% to 50% of users are unable to operate Motor-Imagery-based BCI systems. Importantly, the almost all previous studieds on BCI inefficiency were based on tests of Sensory Motor Rhythm (SMR) feature. In this work, we assessed the occurrence of BCI inefficiency with SMR and Movement-Related Cortical Potential (MRCP) features.

APPROACH

A pool of datasets of resting state and movements related EEG signals was recorded with 93 subjects during 2 sessions in separated days. Two methods, Common Spatial Pattern (CSP) and template matching, were used for SMR and MRCP feature extraction, and a winner-take-all strategy was applied to assess pattern recognition with posterior probabilities from Linear Discriminant Analysis to combine SMR and MRCP features.

MAIN RESULTS

The results showed that the two types of features showed high complementarity, in line with their weak intercorrelation. In the subject group with poor accuracies (< 70%) by SMR feature in the two-class problem (right foot vs. right hand), the combination of SMR and MRCP features improved the averaged accuracy from 62% to 79%. Importantly, accuracies obtained by feature combination exceeded the inefficiency threshold.

SIGNIFICANCE

The feature combination of SMR and MRCP is not new in BCI decoding, but the large scale and repeatable study on BCI inefficiency assessment by using SMR and MRCP features is novel. MRCP feature provides the similar classification accuracies on the two subject groups with poor (< 70%) and good (> 90%) accuracies by SMR feature. These results suggest that the combination of SMR and MRCP features may be a practical approach to reduce BCI inefficiency. While, 'BCI inefficiency' might be more aptly called 'SMR inefficiency' after this study.

Alpha Frequency Intervention by Electrical Stimulation to Improve Performance in Mu-Based BCI

The accuracy of brain-computer interfaces (BCIs) is important for effective communication and control. The mu-based BCI is one of the most widely used systems, of which the related methods to improve users' accuracy are still poorly studied, especially for the BCI illiteracy. Here, we examined a way to enhance mu-based BCI performance by electrically stimulating the ulnar nerve of the contralateral wrist at the alpha frequency (10 Hz) during left- and right-hand motor imagination in two BCI groups (literate and illiterate). We demonstrate that this alpha frequency intervention enhances the classification accuracy between left- and right-hand motor imagery from 66.41% to 81.57% immediately after intervention and to 75.28% two days after intervention in the BCI illiteracy group, while classification accuracy improves from 82.12% to 91.84% immediately after intervention and to 89.03% two days after intervention in the BCI literacy group. However, the classification accuracy did not change before and after the sham intervention (no electrical stimulation). Furthermore, the ERD on the primary sensorimotor cortex during left- or right-hand motor imagery tasks was more visible at the mu-rhythm (8-13 Hz) after alpha frequency intervention. Alpha frequency intervention increases the mu-rhythm power difference between left- and right-hand motor imagery tasks. These results provide evidence that alpha frequency intervention is an effective way to improve BCI performance by regulating the mu-rhythm which might provide a way to reduce BCI illiteracy.

Self-Regulation of SMR Power Led to an Enhancement of Functional Connectivity of Somatomotor Cortices in Fibromyalgia Patients

Neuroimaging studies have demonstrated that altered activity in somatosensory and motor cortices play a key role in pain chronification. Neurofeedback training of sensorimotor rhythm (SMR) is a tool which allow individuals to self-modulate their brain activity and to produce significant changes over somatomotor brain areas. Several studies have further shown that neurofeedback training may reduce pain and other pain-related symptoms in chronic pain patients. The goal of the present study was to analyze changes in SMR power and brain functional connectivity of the somatosensory and motor cortices elicited by neurofeedback task designed to both synchronize and desynchronize the SMR power over motor and somatosensory areas in fibromyalgia patients. Seventeen patients were randomly assigned to the SMR training (n = 9) or to a sham protocol (n = 8). All participants were trained during 6 sessions, and fMRI and EEG power elicited by synchronization and desynchronization trials were analyzed. In the SMR training group, four patients achieved the objective of SMR modulation in more than 70% of the trials from the second training session (good responders), while five patients performed the task at the chance level (bad responders). Good responders to the neurofeedback training significantly reduced pain and increased both SMR power modulation and functional connectivity of motor and somatosensory related areas during the last neurofeedback training session, whereas no changes in brain activity or pain were observed in bad responders or participants in the sham group. In addition, we observed that good responders were characterized by reduced impact of fibromyalgia and pain symptoms, as well as by increased levels of health-related quality of life during the pre-training sessions. In summary, the present study revealed that neurofeedback training of SMR elicited significant brain changes in somatomotor areas leading to a significant reduction of pain in fibromyalgia patients. In this sense, our research provide evidence that neurofeedback training is a promising tool for a better understanding of brain mechanisms involved in pain chronification.

Subject-specific EEG channel selection using non-negative matrix factorization for lower-limb motor imagery recognition

OBJECTIVE

This study aims to propose and validate a subject-specific approach to recognize two different cognitive neural states (relax and pedaling motor imagery (MI)) by selecting the relevant electroencephalogram (EEG) channels. The main aims of the proposed work are: (i) to reduce the computational complexity of the BCI systems during MI detection by selecting the relevant EEG channels, (ii) to reduce the amount of data overfitting that may arise due to unnecessary channels and redundant features, and (iii) to reduce the classification time for real-time BCI applications.

APPROACH

The proposed method selects subject-specific EEG channels and features based on their MI. In this work, we make use of non-negative matrix factorization to extract the weight of the EEG channels based on their contribution to MI detection. Further, the neighborhood component analysis is used for subject-specific feature selection.

MAIN RESULTS

We executed the experiments using EEG signals recorded for MI where ten healthy subjects performed MI movement of the lower limb to generate motor commands. An average accuracy of 96.66%, average true positive rate (TPR) of 97.77%, average false positives rate of 4.44%, and average Kappa of 93.33% were obtained. The proposed subject-specific EEG channel selection based MI recognition system provides 13.20% improvement in detection accuracy, and 27% improvement in Kappa value with less number of EEG channels compared to the results obtained using all EEG channels.

SIGNIFICANCE

The proposed subject-specific BCI system has been found significantly advantageous compared to the typical approach of using a fixed channel configuration. This work shows that fewer EEG channels not only reduce computational complexity and processing time (two times faster) but also improve the MI detection performance. The proposed method selects EEG locations related to the foot movement, which may be relevant for neuro-rehabilitation using lower-limb movements that may provide a real-time and more natural interface between patient and robotic device.

Brain mechanisms in motor control during reaching movements: Transition of functional connectivity according to movement states

Understanding how the brain controls movements is a critical issue in neuroscience. The role of brain changes rapidly according to movement states. To elucidate the motor control mechanism of brain, it is essential to investigate the changes in brain network in motor-related regions according to movement states. Therefore, the objective of this study was to investigate the brain network transitions according to movement states. We measured whole brain magnetoencephalography (MEG) signals and extracted source signals in 24 motor-related areas. Functional connectivity and centralities were calculated according to time flow. Our results showed that brain networks differed between states of motor planning and movement. Connectivities between most motor-related areas were increased in the motor-planning state. In contrast, only connectivities with cerebellum and basal ganglia were increased while those of other motor-related areas were decreased during movement. Our results indicate that most processes involved in motor control are completed before movement. Further, brain developed network related to feedback rather than motor decision during movements. Our findings also suggest that neural signals during motor planning might be more predictive than neural signals during movement. They facilitate accurate prediction of movement for brain-machine interfaces and provide insight into brain mechanisms in motor control.

Automatic Detection of Epileptic Seizures in EEG Using Sparse CSP and Fisher Linear Discrimination Analysis Algorithm

In order to realize the automatic epileptic seizure detection, feature extraction and classification of electroencephalogram (EEG) signals are performed on the interictal, the pre-ictal, and the ictal status of epilepsy patients. There is no effective strategy for selecting the number of channels and spatial filters in feature extraction of multichannel EEG data. Therefore, this paper combined sparse idea and greedy search algorithm to improve the feature extraction of common space pattern. The feature extraction can effectively overcome the repeating selection problem of feature pattern in the eigenvector space by the traditional method. Then we used the Fisher linear discriminant analysis to realize the classification. The results show that the proposed method can get high classification accuracy using fewer data. For 10 subjects, the averaged accuracy of epilepsy detection is more than 99%. So, the detection of an epileptic seizure based on sparse features using Fisher linear discriminant analysis classifiers is more suitable for a reliable, automatic epileptic seizure detection system to enhance the patient's care and the quality of life.

Compressed Sensing of EEG with Gabor Dictionary: Effect of Time and Frequency Resolution

Electroencephalogram (EEG) signals have been widely used to analyze brain activities so as to diagnose certain brain-related diseases. They are usually recorded for a fairly long interval with adequate resolution, consequently requiring a considerable amount of memory space for storage and transmission. Recently compressed sensing (CS) has been proposed in order to effectively compress EEG signals. However, its performance is closely dependent on how a compression dictionary is built. Through our study, we notice that building the best fit over-complete Gabor dictionary plays an important role in this task. In this paper, we evaluate the effect of different time and frequency step sizes in building Gabor atoms on the performance of EEG signal compression using CS with three common EEG databases used by the research community. Taking the Normalized Mean Square Error (NMSE) as a performance metric, we present a quantitative study with an attempt to provide more insight on how to adopt CS in EEG signal compression.

Novel hybrid brain-computer interface system based on motor imagery and P300

Motor imagery (MI) is a mental representation of motor behavior and has been widely used in electroencephalogram based brain-computer interfaces (BCIs). Several studies have demonstrated the efficacy of MI-based BCI-feedback training in post-stroke rehabilitation. However, in the earliest stage of the training, calibration data typically contain insufficient discriminability, resulting in unreliable feedback, which may decrease subjects' motivation and even hinder their training. To improve the performance in the early stages of MI training, a novel hybrid BCI paradigm based on MI and P300 is proposed in this study. In this paradigm, subjects are instructed to imagine writing the Chinese character following the flash order of the desired Chinese character displayed on the screen. The event-related desynchronization/synchronization (ERD/ERS) phenomenon is produced with writing based on one's imagination. Simultaneously, the P300 potential is evoked by the flash of each stroke. Moreover, a fusion method of P300 and MI classification is proposed, in which unreliable P300 classifications are corrected by reliable MI classifications. Twelve healthy naïve MI subjects participated in this study. Results demonstrated that the proposed hybrid BCI paradigm yielded significantly better performance than the single-modality BCI paradigm. The recognition accuracy of the fusion method is significantly higher than that of P300 (p < 0.05) and MI (p < 0.01). Moreover, the training data size can be reduced through fusion of these two modalities.

A novel hybrid deep learning scheme for four-class motor imagery classification

OBJECTIVE

Learning the structures and unknown correlations of a motor imagery electroencephalogram (MI-EEG) signal is important for its classification. It is also a major challenge to obtain good classification accuracy from the increased number of classes and increased variability from different people. In this study, a four-class MI task is investigated.

APPROACH

An end-to-end novel hybrid deep learning scheme is developed to decode the MI task from EEG data. The proposed algorithm consists of two parts: a. A one-versus-rest filter bank common spatial pattern is adopted to preprocess and pre-extract the features of the four-class MI signal. b. A hybrid deep network based on the convolutional neural network and long-term short-term memory network is proposed to extract and learn the spatial and temporal features of the MI signal simultaneously.

MAIN RESULTS

The main contribution of this paper is to propose a hybrid deep network framework to improve the classification accuracy of the four-class MI-EEG signal. The hybrid deep network is a subject-independent shared neural network, which means it can be trained by using the training data from all subjects to form one model.

SIGNIFICANCE

The classification performance obtained by the proposed algorithm on brain-computer interface (BCI) competition IV dataset 2a in terms of accuracy is 83% and Cohen's kappa value is 0.80. Finally, the shared hybrid deep network is evaluated by every subject respectively, and the experimental results illustrate that the shared neural network has satisfactory accuracy. Thus, the proposed algorithm could be of great interest for real-life BCIs.

Unimanual and Bimanual Reach-and-Grasp Actions Can Be Decoded From Human EEG

While most tasks of daily life can be handled through a small number of different grasps, many tasks require the action of both hands. In these bimanual tasks, the second hand has either a supporting role (e.g. for fixating a jar) or a more active role (e.g. grasping a pot on both handles). In this study we attempt to discriminate the neural correlates of unimanual (performed with left and right hand) from bimanual reach-and-grasp actions using the low-frequency time-domain electroencephalogram (EEG). In a self-initiated movement task, 15 healthy participants were asked to perform unimanual (palmar and lateral grasps with left and right hand) and bimanual (double lateral, mixed palmar/lateral) reach-and-grasps on objects of daily life. Using EEG time-domain features in the frequency range of 0.3-3 Hz, we achieved multiclass-classification accuracies of 38.6 ± 6.6% (7 classes, 17.1% chance level) for a combination of 6 movements and 1 rest condition. The grand average confusion matrix shows highest true positive rates (TPR) for the rest (63%) condition while TPR for the movement classes varied between 33 to 41%. The underlying movement-related cortical potentials (MRCPs) show significant differences between unimanual (e.g left hand vs. right hand grasps) as well unimanual vs. bimanual conditions which both can be attributed to lateralization effects. We believe that these findings can be exploited and further used for attempts in providing persons with spinal cord injury a form of natural control for bimanual neuroprostheses.

Human motor decoding from neural signals: a review

Many people suffer from movement disability due to amputation or neurological diseases. Fortunately, with modern neurotechnology now it is possible to intercept motor control signals at various points along the neural transduction pathway and use that to drive external devices for communication or control. Here we will review the latest developments in human motor decoding. We reviewed the various strategies to decode motor intention from human and their respective advantages and challenges. Neural control signals can be intercepted at various points in the neural signal transduction pathway, including the brain (electroencephalography, electrocorticography, intracortical recordings), the nerves (peripheral nerve recordings) and the muscles (electromyography). We systematically discussed the sites of signal acquisition, available neural features, signal processing techniques and decoding algorithms in each of these potential interception points. Examples of applications and the current state-of-the-art performance were also reviewed. Although great strides have been made in human motor decoding, we are still far away from achieving naturalistic and dexterous control like our native limbs. Concerted efforts from material scientists, electrical engineers, and healthcare professionals are needed to further advance the field and make the technology widely available in clinical use.

The Sensitivity of Single-Trial Mu-Suppression Detection for Motor Imagery Performance as Compared to Motor Execution and Motor Observation Performance

Motor imagery (MI) has been widely used to operate brain-computer interface (BCI) systems for rehabilitation and some life assistive devices. However, the current performance of an MI-based BCI cannot fully meet the needs of its in-field applications. Most of the BCIs utilizing a generalized feature for all participants have been found to greatly hamper the efficacy of the BCI system. Hence, some attempts have made on the exploration of subject-dependent parameters, but it remains challenging to enhance BCI performance as expected. To this end, in this study, we used the independent component analysis (ICA), which has been proved capable of isolating the pure motor-related component from non-motor-related brain processes and artifacts and extracting the common motor-related component across MI, motor execution (ME), and motor observation (MO) conditions. Then, a sliding window approach was used to detect significant mu-suppression from the baseline using the electroencephalographic (EEG) alpha power time course and, thus, the success rate of the mu-suppression detection could be assessed on a single-trial basis. By comparing the success rates using different parameters, we further quantified the extent of the improvement in each motor condition to evaluate the effectiveness of both generalized and individualized parameters. The results showed that in ME condition, the success rate under individualized latency and that under generalized latency was 90.0% and 77.75%, respectively; in MI condition, the success rate was 74.14% for individual latency and 58.47% for generalized latency, and in MO condition, the success rate was 67.89% and 61.26% for individual and generalized latency, respectively. As can be seen, the success rate in each motor condition was significantly improved by utilizing an individualized latency compared to that using the generalized latency. Moreover, the comparison of the individualized window latencies for the mu-suppression detection across different runs of the same participant as well as across different participants showed that the window latency was significantly more consistent in the intra-subject than in the inter-subject settings. As a result, we proposed that individualizing the latency for detecting the mu-suppression feature for each participant might be a promising attempt to improve the MI-based BCI performance.

Simple Convolutional Neural Network for Left-Right Hands Motor Imagery EEG Signals Classification

This article proposes a classification method of two-class motor imagery electroencephalogram (EEG) signals based on convolutional neural network (CNN), in which EEG signals from C3, C4 and Cz electrodes of publicly available BCI competition IV dataset 2b were used to test the performance of the CNN. The authors investigate two similar CNNs: a single-input CNN with a form of 2-dimensional input from short time Fourier transform (STFT) combining time, frequency and location information, and a multiple-input CNN with 3-dimensional input which processes the electrodes as an independent dimension. Fisher discriminant analysis-type F-score based on band pass (BP) feature and power spectra density (PSD) feature are employed respectively to select the subject-optimal frequency bands. In the experiments, typical frequency bands related to motor imagery EEG signals, subject-optimal frequency bands and extension frequency bands are employed respectively as the frequency range of the input image of CNN. The better classification performance of extension frequency bands show that CNN can extract optimal feature from frequency information automatically. The classification result also demonstrates that the proposed approach is more competitive in prediction of left/right hand motor imagery task compared with other state-of-art approaches.

Exploring Cognitive Flexibility With a Noninvasive BCI Using Simultaneous Steady-State Visual Evoked Potentials and Sensorimotor Rhythms

EEG-based brain-computer interface (BCI) technology creates non-biological pathways for conveying a user's mental intent solely through noninvasively measured neural signals. While optimizing the performance of a single task has long been the focus of BCI research, in order to translate this technology into everyday life, realistic situations, in which multiple tasks are performed simultaneously, must be investigated. In this paper, we explore the concept of cognitive flexibility, or multitasking, within the BCI framework by utilizing a 2-D cursor control task, using sensorimotor rhythms (SMRs), and a four-target visual attention task, using steady-state visual evoked potentials (SSVEPs), both individually and simultaneously. We found no significant difference between the accuracy of the tasks when executing them alone (SMR-57.9% ± 15.4% and SSVEP-59.0% ± 14.2%) and simultaneously (SMR-54.9% ± 17.2% and SSVEP-57.5% ± 15.4%). These modest decreases in performance were supported by similar, non-significant changes in the electrophysiology of the SSVEP and SMR signals. In this sense, we report that multiple BCI tasks can be performed simultaneously without a significant deterioration in performance; this finding will help drive these systems toward realistic daily use in which a user's cognition will need to be involved in multiple tasks at once.