Application of rapid invisible frequency tagging for brain computer interfaces

BACKGROUND

Brain-computer interfaces (BCI) based on steady-state visual evoked potentials (SSVEPs/SSVEFs) are among the most commonly used BCI systems. They require participants to covertly attend to visual objects flickering at specified frequencies. The attended location is decoded online by analysing the power of neuronal responses at the flicker frequency.

NEW METHOD

We implemented a novel rapid invisible frequency-tagging technique, utilizing a state-of-the-art projector with refresh rates of up to 1440 Hz. We flickered the luminance of visual objects at 56 and 60 Hz, which was invisible to participants but produced strong neuronal responses measurable with magnetoencephalography (MEG). The direction of covert attention, decoded from frequency-tagging responses, was used to control an online BCI PONG game.

RESULTS

Our results show that seven out of eight participants were able to play the pong game controlled by the frequency-tagging signal, with average accuracies exceeding 60 %. Importantly, participants were able to modulate the power of the frequency-tagging response within a 1-second interval, while only seven occipital sensors were required to reliably decode the neuronal response.

COMPARISON WITH EXISTING METHODS

In contrast to existing SSVEP-based BCI systems, rapid frequency-tagging does not produce a visible flicker. This extends the time-period participants can use it without fatigue, by avoiding distracting visual input. Furthermore, higher frequencies increase the temporal resolution of decoding, resulting in higher communication rates.

CONCLUSION

Using rapid invisible frequency-tagging opens new avenues for fundamental research and practical applications. In combination with novel optically pumped magnetometers (OPMs), it could facilitate the development of high-speed and mobile next-generation BCI systems.

Therapists' perspectives on using brain-computer interface-triggered functional electrical stimulation therapy for individuals living with upper extremity paralysis: a qualitative case series study

BACKGROUND

Brain computer interface-triggered functional electrical stimulation therapy (BCI-FEST) has shown promise as a therapy to improve upper extremity function for individuals who have had a stroke or spinal cord injury. The next step is to determine whether BCI-FEST could be used clinically as part of broader therapy practice. To do this, we need to understand therapists' opinions on using the BCI-FEST and what limitations potentially exist. Therefore, we conducted a qualitative exploratory study to understand the perspectives of therapists on their experiences delivering BCI-FEST and the feasibility of large-scale clinical implementation.

METHODS

Semi-structured interviews were conducted with physical therapists (PTs) and occupational therapists (OTs) who have delivered BCI-FEST. Interview questions were developed using the COM-B (Capability, Opportunity, Motivation-Behaviour) model of behaviour change. COM-B components were used to inform deductive content analysis while other subthemes were detected using an inductive approach.

RESULTS

We interviewed PTs (n = 3) and OTs (n = 3), with 360 combined hours of experience delivering BCI-FEST. Components and subcomponents of the COM-B determined deductively included: (1) Capability (physical, psychological), (2) Opportunity (physical, social), and (3) Motivation (automatic, reflective). Under each deductive subcomponent, one to two inductive subthemes were identified (n = 8). Capability and Motivation were perceived as strengths, and therefore supported therapists' decisions to use BCI-FEST. Under Opportunity, for both subcomponents (physical, social), therapists recognized the need for more support to clinically implement BCI-FEST.

CONCLUSIONS

We identified facilitating and limiting factors to BCI-FEST delivery in a clinical setting according to clinicians. These factors implied that education, training, a support network or mentors, and restructuring the physical environment (e.g., scheduling) should be targeted as interventions. The results of this study may help to inform future development of new technologies and interventions.

[Research advances in non-invasive brain-computer interface control strategies]

Brain-computer interface (BCI) can establish a direct communications pathway between the human brain and the external devices, which is independent of peripheral nerves and muscles. Compared with invasive BCI, non-invasive BCI has the advantages of low cost, low risk, and ease of operation. In recent years, using non-invasive BCI technology to control devices has gradually evolved into a new type of human-computer interaction manner. Moreover, the control strategy for BCI is an essential component of this manner. First, this study introduced how the brain control techniques were developed and classified. Second, the basic characteristics of direct and shared control strategies were thoroughly explained. And then the benefits and drawbacks of these two strategies were compared and further analyzed. Finally, the development direction and application prospects for non-invasive brain control strategies were suggested.

[Neurofeedback technology based on functional near infrared spectroscopy imaging and its applications]

Neurofeedback (NF) technology based on electroencephalogram (EEG) data or functional magnetic resonance imaging (fMRI) has been widely studied and applied. In contrast, functional near infrared spectroscopy (fNIRS) has become a new technique in NF research in recent years. fNIRS is a neuroimaging technology based on hemodynamics, which has the advantages of low cost, good portability and high spatial resolution, and is more suitable for use in natural environments. At present, there is a lack of comprehensive review on fNIRS-NF technology (fNIRS-NF) in China. In order to provide a reference for the research of fNIRS-NF technology, this paper first describes the principle, key technologies and applications of fNIRS-NF, and focuses on the application of fNIRS-NF. Finally, the future development trend of fNIRS-NF is prospected and summarized. In conclusion, this paper summarizes fNIRS-NF technology and its application, and concludes that fNIRS-NF technology has potential practicability in neurological diseases and related fields. fNIRS can be used as a good method for NF training. This paper is expected to provide reference information for the development of fNIRS-NF technology.

A novel online BCI system using speech imagery and ear-EEG for home appliances control

BACKGROUND AND OBJECTIVE

This paper investigates a novel way to interact with home appliances via a brain-computer interface (BCI), using electroencephalograph (EEG) signals acquired from around the user's ears with a custom-made wearable BCI headphone.

METHODS

The users engage in speech imagery (SI), a type of mental task where they imagine speaking out a specific word without producing any sound, to control an interactive simulated home appliance. In this work, multiple models are employed to improve the performance of the system. Temporally-stacked multi-band covariance matrix (TSMBC) method is used to represent the neural activities during SI tasks with spatial, temporal, and spectral information included. To further increase the usability of our proposed system in daily life, a calibration session, where the pre-trained models are fine-tuned, is added to maintain performance over time with minimal training. Eleven participants were recruited to evaluate our method over three different sessions: a training session, a calibration session, and an online session where users were given the freedom to achieve a given goal on their own.

RESULTS

In the offline experiment, all participants were able to achieve a classification accuracy significantly higher than the chance level. In the online experiments, a few participants were able to use the proposed system to freely control the home appliance with high accuracy and relatively fast command delivery speed. The best participant achieved an average true positive rate and command delivery time of 0.85 and 3.79 s/command, respectively.

CONCLUSION

Based on the positive experimental results and user surveys, the novel ear-EEG-SI-based BCI paradigm is a promising approach for the wearable BCI system for daily life.

Decoding locomotion speed and slope from local field potentials of rat motor cortex

BACKGROUND AND OBJECTIVE

Local Field Potentials (LFPs) recorded from the primary motor cortex (M1) have been shown to be very informative for decoding movement parameters, and these signals can be used to decode forelimb kinematic and kinetic parameters accurately. Although locomotion is one of the most basic and important motor abilities of humans and animals, the potential of LFPs in decoding abstract hindlimb locomotor parameters has not been investigated. This study investigates the feasibility of decoding speed and slope of locomotion, as two important abstract parameters of walking, using the LFP signals.

METHODS

Rats were trained to walk smoothly on a treadmill with different speeds and slopes. The brain signals were recorded using the microwire arrays chronically implanted in the hindlimb area of M1 while rats walked on the treadmill. LFP channels were spatially filtered using optimal common spatial patterns to increase the discriminability of speeds and slopes of locomotion. Logarithmic wavelet band powers were extracted as basic features, and the best features were selected using the statistical dependency criterion before classification.

RESULTS

Using 5 s LFP trials, the average classification accuracies of four different speeds and seven different slopes reached 90.8% and 86.82%, respectively. The high-frequency LFP band (250-500 Hz) was the most informative band about these parameters and contributed more than other frequency bands in the final decoder model.

CONCLUSIONS

Our results show that the LFP signals in M1 accurately decode locomotion speed and slope, which can be considered as abstract walking parameters needed for designing long-term brain-computer interfaces for hindlimb locomotion control.

FB-EEGNet: A fusion neural network across multi-stimulus for SSVEP target detection

BACKGROUND

Steady-state visual evoked potential (SSVEP) is a prevalent paradigm of brain-computer interface (BCI). Recently, deep neural networks (DNNs) have been employed for SSVEP target recognition. However, current DNN models can not fully extract information from SSVEP harmonic components, and ignore the influence of non-target stimuli.

NEW METHOD

To employ information of multiple sub-bands and non-target stimulus data, we propose a DNN model for SSVEP target detection, i.e., FB-EEGNet, which fuses features of multiple neural networks. Additionally, we design a multi-label for each sample and optimize the parameters of FB-EEGNet across multi-stimulus to incorporate the information from non-target stimuli.

RESULTS

Under the subject-specific condition, FB-EEGNet achieves the average classification accuracies (information transfer rate (ITR)) of 76.75 % (50.70 bits/min) and 89.14 % (70.45 bits/min) in a time widow of 0.7 s under the public 12-target dataset and our experimental 9-target dataset, respectively. Under the cross-subject condition, FB-EEGNet achieved mean accuracies (ITRs) of 81.72 % (67.99 bits/min) and 92.15 % (76.12 bits/min) on the public and experimental datasets in a time window of 1 s, respectively.

COMPARISON WITH EXISTING METHODS

FB-EEGNet shows superior performance than CCNN, EEGNet, CCA and FBCCA both for subject-dependent and subject-independent SSVEP target recognition.

CONCLUSION

FB-EEGNet can effectively extract information from multiple sub-bands and cross-stimulus targets, providing a promising way for extracting deep features in SSVEP using neural networks.

[Motor imagery electroencephalogram classification based on sparse spatiotemporal decomposition and channel attention]

Motor imagery electroencephalogram (EEG) signals are non-stationary time series with a low signal-to-noise ratio. Therefore, the single-channel EEG analysis method is difficult to effectively describe the interaction characteristics between multi-channel signals. This paper proposed a deep learning network model based on the multi-channel attention mechanism. First, we performed time-frequency sparse decomposition on the pre-processed data, which enhanced the difference of time-frequency characteristics of EEG signals. Then we used the attention module to map the data in time and space so that the model could make full use of the data characteristics of different channels of EEG signals. Finally, the improved time-convolution network (TCN) was used for feature fusion and classification. The BCI competition IV-2a data set was used to verify the proposed algorithm. The experimental results showed that the proposed algorithm could effectively improve the classification accuracy of motor imagination EEG signals, which achieved an average accuracy of 83.03% for 9 subjects. Compared with the existing methods, the classification accuracy of EEG signals was improved. With the enhanced difference features between different motor imagery EEG data, the proposed method is important for the study of improving classifier performance.

Toward P300-brain-computer interface access to contextual scene displays for AAC: An initial exploration of context and asymmetry processing in healthy adults

Brain-computer interfaces for augmentative and alternative communication (BCI-AAC) may help overcome physical barriers to AAC access. Traditionally, visually based P300-BCI-AAC displays utilize a symmetrical grid layout. Contextual scene displays are composed of context-rich images (e.g., photographs) and may support AAC success. However, contextual scene displays contrast starkly with the standard P300-grid approach. Understanding the neurological processes from which BCI-AAC devices function is crucial to human-centered computing for BCI-AAC. Therefore, the aim of this multidisciplinary investigation is to provide an initial exploration of contextual scene use for BCI-AAC.

METHODS

Participants completed three experimental conditions to evaluate the effects of item arrangement asymmetry and context on P300-based BCI-AAC signals and offline BCI-AAC accuracy, including 1) the full contextual scene condition, 2) asymmetrical item arraignment without context condition and 3) the grid condition. Following each condition, participants completed task-evaluation ratings (e.g., engagement). Offline BCI-AAC accuracy for each condition was evaluated using cross-validation.

RESULTS

Display asymmetry significantly decreased P300 latency in the centro-parietal cluster. P300 amplitudes in the frontal cluster were decreased, though nonsignificantly. Display context significantly increased N170 amplitudes in the occipital cluster, and N400 amplitudes in the centro-parietal and occipital clusters. Scenes were rated as more visually appealing and engaging, and offline BCI-AAC performance for the scene condition was not statistically different from the grid standard.

CONCLUSION

Findings support the feasibility of incorporating scene-based displays for P300-BCI-AAC development to help provide communication for individuals with minimal or emerging language and literacy skills.

Intracranial brain-computer interface spelling using localized visual motion response

Intracranial brain-computer interfaces (BCIs) can assist severely disabled persons in text communication and environmental control with high precision and speed. Nevertheless, sustainable BCI implants require minimal invasiveness. One of the implantation strategies is to adopt localized and robust cortical activities to drive BCI communication and to make a precise presurgical planning. The visual motion response is a good candidate for inclusion in this strategy because of its focal activity over the middle temporal visual area (MT). Here, we developed an intracranial BCI for spelling, utilizing only three electrodes over the MT area. The best recording electrodes were decided by preoperative functional magnetic resonance imaging (MRI) localization of the MT, and local neural activities were further enhanced by differential rereferencing of these electrodes. The BCI spelling system was validated both offline and online by five epilepsy patients, achieving the fastest speed of 62 bits/min, i.e., 12 characters/min. Moreover, the response patterns of dual-directional visual motion stimuli provided an additional dimension of BCI target encoding and paved the way for a higher information transfer rate of intracranial BCI spelling.

Machine learning based brain signal decoding for intelligent adaptive deep brain stimulation

Sensing enabled implantable devices and next-generation neurotechnology allow real-time adjustments of invasive neuromodulation. The identification of symptom and disease-specific biomarkers in invasive brain signal recordings has inspired the idea of demand dependent adaptive deep brain stimulation (aDBS). Expanding the clinical utility of aDBS with machine learning may hold the potential for the next breakthrough in the therapeutic success of clinical brain computer interfaces. To this end, sophisticated machine learning algorithms optimized for decoding of brain states from neural time-series must be developed. To support this venture, this review summarizes the current state of machine learning studies for invasive neurophysiology. After a brief introduction to the machine learning terminology, the transformation of brain recordings into meaningful features for decoding of symptoms and behavior is described. Commonly used machine learning models are explained and analyzed from the perspective of utility for aDBS. This is followed by a critical review on good practices for training and testing to ensure conceptual and practical generalizability for real-time adaptation in clinical settings. Finally, first studies combining machine learning with aDBS are highlighted. This review takes a glimpse into the promising future of intelligent adaptive DBS (iDBS) and concludes by identifying four key ingredients on the road for successful clinical adoption: i) multidisciplinary research teams, ii) publicly available datasets, iii) open-source algorithmic solutions and iv) strong world-wide research collaborations.

[A review of researches on decoding algorithms of steady-state visual evoked potentials]

Brain-computer interface (BCI) systems based on steady-state visual evoked potential (SSVEP) have become one of the major paradigms in BCI research due to their high signal-to-noise ratio and short training time required by users. Fast and accurate decoding of SSVEP features is a crucial step in SSVEP-BCI research. However, the current researches lack a systematic overview of SSVEP decoding algorithms and analyses of the connections and differences between them, so it is difficult for researchers to choose the optimum algorithm under different situations. To address this problem, this paper focuses on the progress of SSVEP decoding algorithms in recent years and divides them into two categories-trained and non-trained-based on whether training data are needed. This paper also explains the fundamental theories and application scopes of decoding algorithms such as canonical correlation analysis (CCA), task-related component analysis (TRCA) and the extended algorithms, concludes the commonly used strategies for processing decoding algorithms, and discusses the challenges and opportunities in this field in the end.

Exploiting pretrained CNN models for the development of an EEG-based robust BCI framework

Identifying motor and mental imagery electroencephalography (EEG) signals is imperative to realizing automated, robust brain-computer interface (BCI) systems. In the present study, we proposed a pretrained convolutional neural network (CNN)-based new automated framework feasible for robust BCI systems with small and ample samples of motor and mental imagery EEG training data. The framework is explored by investigating the implications of different limiting factors, such as learning rates and optimizers, processed versus unprocessed scalograms, and features derived from untuned pretrained models in small, medium, and large pretrained CNN models. The experiments were performed on three public datasets obtained from BCI Competition III. The datasets were denoised with multiscale principal component analysis, and time-frequency scalograms were obtained by employing a continuous wavelet transform. The scalograms were fed into several variants of ten pretrained models for feature extraction and identification of different EEG tasks. The experimental results showed that ShuffleNet yielded the maximum average classification accuracy of 99.52% using an RMSProp optimizer with a learning rate of 0.000 1. It was observed that low learning rates converge to more optimal performances compared to high learning rates. Moreover, noisy scalograms and features extracted from untuned networks resulted in slightly lower performance than denoised scalograms and tuned networks, respectively. The overall results suggest that pretrained models are robust when identifying EEG signals because of their ability to preserve the time-frequency structure of EEG signals and promising classification outcomes.

An adaptive closed-loop ECoG decoder for long-term and stable bimanual control of an exoskeleton by a tetraplegic

OBJECTIVE

The article aims at addressing 2 challenges to step motor BCI out of laboratories: asynchronous control of complex bimanual effectors with large numbers of degrees of freedom, using chronic and safe recorders, and the decoding performance stability over time without frequent decoder recalibration.

APPROACH

Closed-loop adaptive/incremental decoder training is one strategy to create a model stable over time. Adaptive decoders update their parameters with new incoming data, optimizing the model parameters in real time. It allows cross-session training with multiple recording conditions during closed loop BCI experiments. In the article, an adaptive tensor-based Recursive Exponentially Weighted Markov-Switching multi-Linear Model (REW-MSLM) decoder is proposed. REW-MSLM uses a Mixture of Expert (ME) architecture, mixing or switching independent decoders (experts) according to the probability estimated by a "gating" model. A Hidden Markov model approach is employed as gating model to improve the decoding robustness and to provide strong idle state support. The ME architecture fits the multi-limb paradigm associating an expert to a particular limb or action.

MAIN RESULTS

Asynchronous control of an exoskeleton by a tetraplegic patient using a chronically implanted epidural electrocorticography (EpiCoG) recorder is reported. The stable over a period of 6 months (without decoder recalibration) 8-dimensional alternative bimanual control of the exoskeleton and its virtual avatar is demonstrated.

SIGNIFICANCE

Based on the long-term (>36 months) chronic bilateral epidural ECoG recordings in a tetraplegic (ClinicalTrials.gov, NCT02550522), we addressed the poorly explored field of asynchronous bimanual BCI. The new decoder was designed to meet to several challenges: the high-dimensional control of a complex effector in experiments closer to real-world behaviour (point-to-point pursuit versus conventional center-out tasks), with the ability of the BCI system to act as a stand-alone device switching between idle and control states, and a stable performance over a long period of time without decoder recalibration.

[Key technologies for intelligent brain-computer interaction based on magnetoencephalography]

Brain-computer interaction (BCI) is a transformative human-computer interaction, which aims to bypass the peripheral nerve and muscle system and directly convert the perception, imagery or thinking activities of cranial nerves into actions for further improving the quality of human life. Magnetoencephalogram (MEG) measures the magnetic field generated by the electrical activity of neurons. It has the unique advantages of non-contact measurement, high temporal and spatial resolution, and convenient preparation. It is a new BCI driving signal. MEG-BCI research has important brain science significance and potential application value. So far, few documents have elaborated the key technical issues involved in MEG-BCI. Therefore, this paper focuses on the key technologies of MEG-BCI, and details the signal acquisition technology involved in the practical MEG-BCI system, the design of the MEG-BCI experimental paradigm, the MEG signal analysis and decoding key technology, MEG-BCI neurofeedback technology and its intelligent method. Finally, this paper also discusses the existing problems and future development trends of MEG-BCI. It is hoped that this paper will provide more useful ideas for MEG-BCI innovation research.

[A spatial-temporal hybrid feature extraction method for rapid serial visual presentation of electroencephalogram signals]

Rapid serial visual presentation-brain computer interface (RSVP-BCI) is the most popular technology in the early discover task based on human brain. This algorithm can obtain the rapid perception of the environment by human brain. Decoding brain state based on single-trial of multichannel electroencephalogram (EEG) recording remains a challenge due to the low signal-to-noise ratio (SNR) and nonstationary. To solve the problem of low classification accuracy of single-trial in RSVP-BCI, this paper presents a new feature extraction algorithm which uses principal component analysis (PCA) and common spatial pattern (CSP) algorithm separately in spatial domain and time domain, creating a spatial-temporal hybrid CSP-PCA (STHCP) algorithm. By maximizing the discrimination distance between target and non-target, the feature dimensionality was reduced effectively. The area under the curve (AUC) of STHCP algorithm is higher than that of the three benchmark algorithms (SWFP, CSP and PCA) by 17.9%, 22.2% and 29.2%, respectively. STHCP algorithm provides a new method for target detection.

Evaluation of classification approaches for distinguishing brain states predictive of episodic memory performance from electroencephalography: Abbreviated Title: Evaluating methods of classifying memory states from EEG

Previous studies have attempted to separate single trial neural responses for events a person is likely to remember from those they are likely to forget using machine learning classification methods. Successful single trial classification holds potential for translation into the clinical realm for real-time detection of memory and other cognitive states to provide real-time interventions (i.e., brain-computer interfaces). However, most of these studies-and classification analyses in general- do not make clear if the chosen methodology is optimally suited for the classification of memory-related brain states. To address this problem, we systematically compared different methods for every step of classification (i.e., feature extraction, feature selection, classifier selection) to investigate which methods work best for decoding episodic memory brain states-the first analysis of its kind. Using an adult lifespan sample EEG dataset collected during performance of an episodic context encoding and retrieval task, we found that no specific feature type (including Common Spatial Pattern (CSP)-based features, mean, variance, correlation, features based on AR model, entropy, phase, and phase synchronization) outperformed others consistently in distinguishing different memory classes. However, extracting all of these feature types consistently outperformed extracting only one type of feature. Additionally, the combination of filtering and sequential forward selection was the optimal method to select the effective features compared to filtering alone or performing no feature selection at all. Moreover, although all classifiers performed at a fairly similar level, LASSO was consistently the highest performing classifier compared to other commonly used options (i.e., naïve Bayes, SVM, and logistic regression) while naïve Bayes was the fastest classifier. Lastly, for multiclass classification (i.e., levels of context memory confidence and context feature perception), generalizing the binary classification using the binary decision tree performed better than the voting or one versus rest method. These methods were shown to outperform alternative approaches for three orthogonal datasets (i.e., EEG working memory, EEG motor imagery, and MEG working memory), supporting their generalizability. Our results provide an optimized methodological process for classifying single-trial neural data and provide important insight and recommendations for a cognitive neuroscientist's ability to make informed choices at all stages of the classification process for predicting memory and other cognitive states.

SAM 40: Dataset of 40 subject EEG recordings to monitor the induced-stress while performing Stroop color-word test, arithmetic task, and mirror image recognition task

This paper presents a collection of electroencephalogram (EEG) data recorded from 40 subjects (female: 14, male: 26, mean age: 21.5 years). The dataset was recorded from the subjects while performing various tasks such as Stroop color-word test, solving arithmetic questions, identification of symmetric mirror images, and a state of relaxation. The experiment was primarily conducted to monitor the short-term stress elicited in an individual while performing the aforementioned cognitive tasks. The individual tasks were carried out for 25 s and were repeated to record three trials. The EEG was recorded using a 32-channel Emotiv Epoc Flex gel kit. The EEG data were then segmented into non-overlapping epochs of 25 s depending on the various tasks performed by the subjects. The EEG data were further processed to remove the baseline drifts by subtracting the average trend obtained using the Savitzky-Golay filter. Furthermore, the artifacts were also removed from the EEG data by applying wavelet thresholding. The dataset proposed in this paper can aid and support the research activities in the field of brain-computer interface and can also be used in the identification of patterns in the EEG data elicited due to stress.

A comparison and classification of oscillatory characteristics in speech perception and covert speech

Covert speech, the mental imagery of speaking, has been studied increasingly to understand and decode thoughts in the context of brain-computer interfaces. In studies of speech comprehension, neural oscillations are thought to play a key role in the temporal encoding of speech. However, little is known about the role of oscillations in covert speech. In this study, we investigated the oscillatory involvements in covert speech and speech perception. Data were collected from 10 participants with 64 channel EEG. Participants heard the words, 'blue' and 'orange', and subsequently mentally rehearsed them. First, continuous wavelet transform was performed on epoched signals and subsequently two-tailed t-tests between two classes were conducted to determine statistical differences in frequency and time (t-CWT). Features were also extracted using t-CWT and subsequently classified using a support vector machine. θ and γ phase amplitude coupling (PAC) was also assessed within and between tasks. All binary classifications produced accuracies significantly greater (80-90%) than chance level, supporting the use of t-CWT in determining relative oscillatory involvements. While the perception task dynamically invoked all frequencies with more prominent θ and α activity, the covert task favoured higher frequencies with significantly higher γ activity than perception. Moreover, the perception condition produced significant θ-γ PAC, corroborating a reported linkage between syllabic and phonemic sampling. Although this coupling was found to be suppressed in the covert condition, we found significant cross-task coupling between perception θ and covert speech γ. Covert speech processing appears to be largely associated with higher frequencies of EEG. Importantly, the significant cross-task coupling between speech perception and covert speech, in the absence of within-task covert speech PAC, supports the notion that the γ- and θ-bands subserve, respectively, shared and unique encoding processes across tasks.

Brain-Computer Interface: Applications to Speech Decoding and Synthesis to Augment Communication

Damage or degeneration of motor pathways necessary for speech and other movements, as in brainstem strokes or amyotrophic lateral sclerosis (ALS), can interfere with efficient communication without affecting brain structures responsible for language or cognition. In the worst-case scenario, this can result in the locked in syndrome (LIS), a condition in which individuals cannot initiate communication and can only express themselves by answering yes/no questions with eye blinks or other rudimentary movements. Existing augmentative and alternative communication (AAC) devices that rely on eye tracking can improve the quality of life for people with this condition, but brain-computer interfaces (BCIs) are also increasingly being investigated as AAC devices, particularly when eye tracking is too slow or unreliable. Moreover, with recent and ongoing advances in machine learning and neural recording technologies, BCIs may offer the only means to go beyond cursor control and text generation on a computer, to allow real-time synthesis of speech, which would arguably offer the most efficient and expressive channel for communication. The potential for BCI speech synthesis has only recently been realized because of seminal studies of the neuroanatomical and neurophysiological underpinnings of speech production using intracranial electrocorticographic (ECoG) recordings in patients undergoing epilepsy surgery. These studies have shown that cortical areas responsible for vocalization and articulation are distributed over a large area of ventral sensorimotor cortex, and that it is possible to decode speech and reconstruct its acoustics from ECoG if these areas are recorded with sufficiently dense and comprehensive electrode arrays. In this article, we review these advances, including the latest neural decoding strategies that range from deep learning models to the direct concatenation of speech units. We also discuss state-of-the-art vocoders that are integral in constructing natural-sounding audio waveforms for speech BCIs. Finally, this review outlines some of the challenges ahead in directly synthesizing speech for patients with LIS.

Spatial localization in target detection based on decoding N2pc component

BACKGROUND

The Gaze-independent BCI system is used to restore communication in patients with eye movement disorders. One available control mechanism is the utilization of spatial attention. However, spatial information is mostly used to simply answer the "True/False" target recognition question and is seldom used to improve the efficiency of target detection. Therefore, it is necessary to utilize the potential advantages of spatial attention to improving the target detection efficiency.

NEW METHOD

We found that N2pc could be used to assess spatial attention shift and determine target position. It was a negative wave in the posterior brain on the contralateral target stimulus. From this, we designed a novel spatial coding paradigm to achieve two main purposes at each stimulus presentation: target recognition and spatial localization.

COMPARISON WITH EXISTING METHODS

We used a two-step classification framework to decode the P300 and N2pc components.

RESULTS

The average decoding accuracy of fourteen subjects was 84.43% (σ = 1.14%), and the classification accuracy of six subjects was more than 85%. The information transfer rate of the spatial coding paradigm could reach 60.52 bits/min. Compared with the single stimulus paradigm, the target detection efficiency was successfully improved by approximately 10%.

CONCLUSIONS

The spatial coding paradigm proposed in this paper answered both "True/False" and "Left/Right" questions by decoding spatial attention information. This method could significantly improve image detection efficiencies, such as visual search tasks, Internet image screening, or military target determination.

A 1D CNN for high accuracy classification and transfer learning in motor imagery EEG-based brain-computer interface

OBJECTIVE

Brain-computer interface (BCI) aims to establish communication paths between the brain processes and external devices. Different methods have been used to extract human intentions from electroencephalography (EEG) recordings. Those based on motor imagery (MI) seem to have a great potential for future applications. These approaches rely on the extraction of EEG distinctive patterns during imagined movements. Techniques able to extract patterns from raw signals represent an important target for BCI as they do not need labor-intensive data pre-processing.

APPROACH

We propose a new approach based on a 10-layer one-dimensional convolution neural network (1D-CNN) to classify five brain states (four MI classes plus a 'baseline' class) using a data augmentation algorithm and a limited number of EEG channels. In addition, we present a transfer learning method used to extract critical features from the EEG group dataset and then to customize the model to the single individual by training its outer layers with only 12-minute individual-related data.

MAIN RESULTS

The model tested with the 'EEG Motor Movement/Imagery Dataset' outperforms the current state-of-the-art models by achieving a 99.38% accuracy at the group level. In addition, the transfer learning approach we present achieves an average accuracy of 99.46%.

SIGNIFICANCE

The proposed methods could foster future BCI applications relying on few-channel portable recording devices and individual-based training.

Psychological assessments of a senile patient with tetraplegia who received brain-computer interface implantation: a case report

OBJECTIVE

Research on individuals with brain-computer interface (BCI) presents not only technological challenges but ethical challenges (e.g., psychological aspects) as well. We assessed the mental health of a senile patient with tetraplegia after an invasive implantation of BCI and a long-term daily training, in order to provide new experience about the ethical impact of BCI on users and inform future clinical applications of such devices.

METHODS

This case was a 71-year-old man with tetraplegia for 2 years. Prior to the implant surgery of BCI, and 1 month, 2 months, 3 months, and 9 months after training, a series of tests for cognition, emotion, social support, sleep, and quality of life were performed to evaluate the patient's mental health.

RESULTS

Compared with baseline before surgery, the patients' cognition, emotion, social support, sleep, and quality of life improved after the surgery and the long-term daily training. At 3 months post-training, the patient's cognitive score measured by Mini-mental State Examination reached the cutoff point for cognitive impairment in the elderly. Subjective well-being and quality of life showed a slight decline at 9 months post-training compared with that 3 months post-training but remained above the baseline.

CONCLUSION

This study shows the psychological benefits in a senile patient after an invasive BCI implantation and a long-term daily training. BCI ethics is still in its early stages, and further research is needed to understand emerging psychological states of this specific population.

Sense of agency for mental actions: Insights from a belief-based action-effect paradigm

A substantial body of research has converged on the idea that the sense of agency arises from the integration of multiple sources of information. In this study, we investigated whether a measurable sense of agency can be detected for mental actions, without the contribution of motor components. We used a fake action-effect paradigm, where participants were led to think that a motor action or a particular thought could trigger a sound. Results showed that the sense of agency, when measured through explicit reports, was of comparable strength for motor and mental actions. The intentional binding effect, a phenomenon typically associated with the experience of agency, was also observed for both motor and mental actions. Taken together, our results provide novel insights into the specific role of intentional cues in instantiating a sense of agency, even in the absence of motor signals.

A novel method to reduce the motor imagery BCI illiteracy

To reduce the motor imagery brain-computer interface (MI-BCI) illiteracy phenomenon and improve the classification accuracy, this paper proposed a novel method combining paradigm selection and Riemann distance classification. Firstly, a novel sensitivity-based paradigm selection (SPS) algorithm is designed for the optimization of classification to find the best classification pattern through a sensitive indicator. Then, a generalized Riemann minimum distance mean (GRMDM) classifier is proposed by introducing a weight factor to fuse the Log-Euclidean Metric classifier and the Riemannian Stein divergence classifier. The experimental results show that the proposed method achieves a better performance for multi-class motor imagery tasks. The average classification accuracy on the BCI competition IV dataset2a is 80.98%, which is 11.04% higher than Stein divergence classifier on the original two-class paradigm. Furthermore, the proposed method demonstrates its capacity on reducing MI-BCI illiteracy. Graphical abstract Here we investigate whether the BCI illiteracy phenomenon can be reduced through sensitivity-based paradigm selection (SPS) method and generalized Riemann minimum distance mean (GRMDM) classifier when performing motor imagery tasks.