Journal of neural engineering最新文献

Objective: This study investigated the potential of estimating various mental workload levels during two different tasks using a commercial in-ear electroencephalography (EEG) system, the IDUN "Guardian". Approach: Participants performed versions of two classical workload tasks: an n-back task and a mental arithmetic task. Both in-ear and conventional EEG data were simultaneously collected during these tasks. In an effort to facilitate a more comprehensive comparison, the complexity of the tasks was intentionally increased beyond typical levels. Special emphasis was also placed on understanding the significance of gamma band activity in workload estimations. Therefore, each signal was analyzed across low frequency (1-35 Hz) and high frequency (1-100 Hz) ranges. Additionally, surrogate in-ear EEG measures, derived from the conventional EEG recordings, were extracted and examined. Main results: Workload estimation using in-ear EEG yielded statistically significant performance levels, surpassing chance levels with 44.1% for four classes and 68.4% for two classes in the n-back task and was better than a naive predictor for the mental arithmetic task. Conventional EEG exhibited significantly higher performance compared to in-ear EEG, achieving 80.3% and 92.9% accuracy for the respective tasks, along with lower error rates than the naive predictor. The developed surrogate measures achieved improved results, reaching accuracies of 57.5% and 85.5%, thus providing insights for enhancing future in-ear systems. Notably, most high frequency range signals outperformed their low frequency counterparts in terms of accuracy validating that high frequency gamma band features can improve workload estimation. Significance: The application of EEG-based Brain-Computer Interfaces (BCIs) beyond laboratory settings is often hindered by practical limitations. In-ear EEG systems offer a promising solution to this problem, potentially enabling everyday use. This study evaluates the performance of a commercial in-ear headset and provides guidelines for increased effectiveness.

Objective One out of three stroke-patients develop language processing impairment known as aphasia. The need for ecological validity of the existing diagnostic tools motivates research on biomarkers, such as stimulus-evoked brain responses. With the aim of enhancing the physiological interpretation of the latter, we used EEG to investigate how functional brain network patterns associated with the neural response to natural speech are affected in persons with post-stroke chronic aphasia. Approach EEG was recorded from 24 healthy controls and 40 persons with aphasia while they listened to a story. Stimulus-evoked brain responses at all scalp regions were measured as neural envelope tracking in the delta (0.5-4 Hz), theta (4-8 Hz) and low-gamma bands (30-49 Hz) using mutual information. Functional connectivity between neural-tracking signals was measured, and the Network-Based Statistics toolbox was used to: 1) assess the added value of the neural tracking vs EEG time series, 2) test between-group differences and 3) investigate any association with language performance in aphasia. Graph theory was also used to investigate topological alterations in aphasia. Main results Functional connectivity was higher when assessed from neural tracking compared to EEG time series. Persons with aphasia showed weaker low-gamma-band left-hemispheric connectivity, and graph theory-based results showed a greater network segregation and higher region-specific node strength. Aphasia also exhibited a correlation between delta-band connectivity within the left pre-frontal region and language performance. Significance We demonstrated the added value of combining brain connectomics with neural-tracking measurement when investigating natural speech processing in post-stroke aphasia. The higher sensitivity to language-related brain circuits of this approach favours its use as informative biomarker for the assessment of aphasia. .

Objective.Methods that can detect brain activities accurately are crucial owing to the increasing prevalence of neurological disorders. In this context, a combination of electroencephalography (EEG) and functional near-infrared spectroscopy (fNIRS) offers a powerful approach to understanding normal and pathological brain functions, thereby overcoming the limitations of each modality, such as susceptibility to artefacts of EEG and limited temporal resolution of fNIRS. However, challenges such as class imbalance and inter-class variability within multisubject data hinder their full potential.Approach.To address this issue, we propose a novel temporal attention fusion network (TAFN) with a custom loss function. The TAFN model incorporates attention mechanisms to its long short-term memory and temporal convolutional layers to accurately capture spatial and temporal dependencies in the EEG--fNIRS data. The custom loss function combines class weights and asymmetric loss terms to ensure the precise classification of cognitive and motor intentions, along with addressing class imbalance issues.Main resultsRigorous testing demonstrated the exceptional cross-subject accuracy of the TAFN, exceeding 99% for cognitive tasks and 97% for motor imagery (MI) tasks. Additionally, the ability of the model to detect subtle differences in epilepsy was analyzed using scalp topography in MI tasks.Significance.This study presents a technique that outperforms traditional methods for detecting high-precision brain activity with subtle differences in the associated patterns. This makes it a promising tool for applications such as epilepsy and seizure detection, in which discerning subtle pattern differences is of paramount importance.

Transcranial magnetic stimulation (TMS) modulates neuronal activity, but the efficacy of an open-loop approach is limited due to the brain state's dynamic nature. Real-time integration with electroencephalography (EEG) increases experimental reliability and offers personalized neuromodulation therapy by using immediate brain states as biomarkers. Here, we review brain state-controlled TMS-EEG studies since the first publication several years ago. A summary of experiments on the sensorimotor mu rhythm (8-13 Hz) shows increased cortical excitability due to TMS pulse at the trough and decreased excitability at the peak of the oscillation. Pre-TMS pulse mu power also affects excitability. Further, there is emerging evidence that the oscillation phase in theta and beta frequency bands modulates neural excitability. Here, we provide a guide for real-time TMS-EEG application and discuss experimental and technical considerations. We consider the effects of hardware choice, signal quality, spatial and temporal filtering, and neural characteristics of the targeted brain oscillation. Finally, we speculate on how closed-loop TMS-EEG potentially could improve the treatment of neurological and mental disorders such as depression, Alzheimer's, Parkinson's, schizophrenia, and stroke.

In the field of brain-computer interfaces (BCIs), the potential for leveraging deep learning techniques for representing electroencephalogram (EEG) signals has gained substantial interest.Objective: This review synthesizes empirical findings from a collection of articles using deep representation learning techniques for BCI decoding, to provide a comprehensive analysis of the current state-of-the-art.Approach: Each article was scrutinized based on three criteria: (1) the deep representation learning technique employed, (2) the underlying motivation for its utilization, and (3) the approaches adopted for characterizing the learned representations.Main results: Among the 81 articles finally reviewed in depth, our analysis reveals a predominance of 31 articles using autoencoders. We identified 13 studies employing self-supervised learning (SSL) techniques, among which ten were published in 2022 or later, attesting to the relative youth of the field. However, at the time being, none of these have led to standard foundation models that are picked up by the BCI community. Likewise, only a few studies have introspected their learned representations. We observed that the motivation in most studies for using representation learning techniques is for solving transfer learning tasks, but we also found more specific motivations such as to learn robustness or invariances, as an algorithmic bridge, or finally to uncover the structure of the data.Significance: Given the potential of foundation models to effectively tackle these challenges, we advocate for a continued dedication to the advancement of foundation models specifically designed for EEG signal decoding by using SSL techniques. We also underline the imperative of establishing specialized benchmarks and datasets to facilitate the development and continuous improvement of such foundation models.

Objective.Current intracortical brain-computer interfaces (iBCIs) rely predominantly on threshold crossings ('spikes') for decoding neural activity into a control signal for an external device. Spiking data can yield high accuracy online control during complex behaviors; however, its dependence on high-sampling-rate data collection can pose challenges. An alternative signal for iBCI decoding is the local field potential (LFP), a continuous-valued signal that can be acquired simultaneously with spiking activity. However, LFPs are seldom used alone for online iBCI control as their decoding performance has yet to achieve parity with spikes.Approach.Here, we present a strategy to improve the performance of LFP-based decoders by first training a neural dynamics model to use LFPs to reconstruct the firing rates underlying spiking data, and then decoding from the estimated rates. We test these models on previously-collected macaque data during center-out and random-target reaching tasks as well as data collected from a human iBCI participant during attempted speech.Main results.In all cases, training models from LFPs enables firing rate reconstruction with accuracy comparable to spiking-based dynamics models. In addition, LFP-based dynamics models enable decoding performance exceeding that of LFPs alone and approaching that of spiking-based models. In all applications except speech, LFP-based dynamics models also facilitate decoding accuracy exceeding that of direct decoding from spikes.Significance.Because LFP-based dynamics models operate on lower bandwidth and with lower sampling rate than spiking models, our findings indicate that iBCI devices can be designed to operate with lower power requirements than devices dependent on recorded spiking activity, without sacrificing high-accuracy decoding.

Objective. machine learning has achieved significant success in electroencephalogram (EEG) based brain-computer interfaces (BCIs), with most existing research focusing on improving the decoding accuracy. However, recent studies have shown that EEG-based BCIs are vulnerable to adversarial attacks, where small perturbations added to the input can cause misclassification. Detecting adversarial examples is crucial for both understanding this phenomenon and developing effective defense strategies.Approach. this paper, for the first time, explores adversarial detection in EEG-based BCIs. We extend several popular adversarial detection approaches from computer vision to BCIs. Two new Mahalanobis distance based adversarial detection approaches, and three cosine distance based adversarial detection approaches, are also proposed, which showed promising performance in detecting three kinds of white-box attacks.Main results. we evaluated the performance of eight adversarial detection approaches on three EEG datasets, three neural networks, and four types of adversarial attacks. Our approach achieved an area under the curve score of up to 99.99% in detecting white-box attacks. Additionally, we assessed the transferability of different adversarial detectors to unknown attacks.Significance. through extensive experiments, we found that white-box attacks may be easily detected, and differences exist in the distributions of different types of adversarial examples. Our work should facilitate understanding the vulnerability of existing BCI models and developing more secure BCIs in the future.

Neurological disorders affecting speech production adversely impact quality of life for over 7 million individuals in the US. Traditional speech interfaces like eyetracking devices and P300 spellers are slow and unnatural for these patients. An alternative solution, speech Brain-Computer Interfaces (BCIs), directly decodes speech characteristics, offering a more natural communication mechanism. This research explores the feasibility of decoding speech features using non-invasive EEG. Nine neurologically intact participants were equipped with a 63-channel EEG system with additional sensors to eliminate eye artifacts. Participants read aloud sentences displayed on a screen selected for phonetic similarity to the English language. Deep learning models, including Convolutional Neural Networks and Recurrent Neural Networks with and without attention modules, were optimized with a focus on minimizing trainable parameters and utilizing small input window sizes for real-time application. These models were employed for discrete and continuous speech decoding tasks, achieving statistically significant participant-independent decoding performance for discrete classes and continuous characteristics of the produced audio signal. A frequency sub-band analysis highlighted the significance of certain frequency bands (delta, theta, and gamma) for decoding performance, and a perturbation analysis was used to identify crucial channels. Assessed channel selection methods did not significantly improve performance, suggesting a distributed representation of speech information encoded in the EEG signals. Leave-One-Out training demonstrated the feasibility of utilizing common speech neural correlates, reducing data collection requirements from individual participants.

Objetive. Decoding speech from brain activity can enable communication for individuals with speech disorders. Deep neural networks (DNNs) have shown great potential for speech decoding applications. However, the limited availability of large datasets containing neural recordings from speech-impaired subjects poses a challenge. Leveraging data from healthy participants can mitigate this limitation and expedite the development of speech neuroprostheses while minimizing the need for patient-specific training data.Approach. In this study, we collected a substantial dataset consisting of recordings from 56 healthy participants using 64 EEG channels. Multiple neural networks were trained to classify perceived sentences in the Spanish language using subject-independent, mixed-subjects, and fine-tuning approaches. The dataset has been made publicly available to foster further research in this area.Main results. Our results demonstrate a remarkable level of accuracy in distinguishing sentence identity across 30 classes, showcasing the feasibility of training DNNs to decode sentence identity from perceived speech using EEG. Notably, the subject-independent approach rendered accuracy comparable to the mixed-subjects approach, although with higher variability among subjects. Additionally, our fine-tuning approach yielded even higher accuracy, indicating an improved capability to adapt to individual subject characteristics, which enhances performance. This suggests that DNNs have effectively learned to decode universal features of brain activity across individuals while also being adaptable to specific participant data. Furthermore, our analyses indicate that EEGNet and DeepConvNet exhibit comparable performance, outperforming ShallowConvNet for sentence identity decoding. Finally, our Grad-CAM visualization analysis identifies key areas influencing the network's predictions, offering valuable insights into the neural processes underlying language perception and comprehension.Significance. These findings advance our understanding of EEG-based speech perception decoding and hold promise for the development of speech neuroprostheses, particularly in scenarios where subjects cannot provide their own training data.

Objective.To create highly immersive experiences in virtual reality (VR) it is important to not only include the visual sense but also to involve multimodal sensory input. To achieve optimal results, the temporal and spatial synchronization of these multimodal inputs is critical. It is therefore necessary to find methods to objectively evaluate the synchronization of VR experiences with a continuous tracking of the user.Approach.In this study a passive touch experience was incorporated in a visual-tactile VR setup using VR glasses and tactile sensations in mid-air. Inconsistencies of multimodal perception were intentionally integrated into a discrimination task. The participants' electroencephalogram (EEG) was recorded to obtain neural correlates of visual-tactile mismatch situations.Main results.The results showed significant differences in the event-related potentials (ERP) between match and mismatch situations. A biphasic ERP configuration consisting of a positivity at 120 ms and a later negativity at 370 ms was observed following a visual-tactile mismatch.Significance.This late negativity could be related to the N400 that is associated with semantic incongruency. These results provide a promising approach towards the objective evaluation of visual-tactile synchronization in virtual experiences.