Context Of Brain Computer Interface Research Articles

Transfer learning and SpecAugment applied to SSVEP based BCI classification

ObjectiveWe used deep convolutional neural networks (DCNNs) to classify electroencephalography (EEG) signals in a steady-state visually evoked potentials (SSVEP) based single-channel brain–computer interface (BCI), which does not require calibration on the user. MethodsEEG signals were converted to spectrograms and served as input to train DCNNs using the transfer learning technique. We also modified and applied a data augmentation method, SpecAugment, generally employed for speech recognition. Furthermore, for comparison purposes, we classified the SSVEP dataset using support-vector machines (SVMs) and filter bank canonical correlation analysis (FBCCA). ResultsExcluding the evaluated user's data from the fine-tuning process, we reached 82.2% mean test accuracy and 0.825 mean F1-Score on 35 subjects from an open dataset, using a small data length (0.5 s), only one electrode (Oz) and the DCNN with transfer learning, window slicing (WS) and SpecAugment's time masks. ConclusionThe DCNN results surpassed SVM and FBCCA performances, using a single electrode and a small data length. Transfer learning provided minimal accuracy change, but made training faster. SpecAugment created a small performance improvement and was successfully combined with WS, yielding higher accuracies. SignificanceWe present a new methodology to solve the problem of SSVEP classification using DCNNs. We also modified a speech recognition data augmentation technique and applied it to the context of BCIs. The presented methodology surpassed performances obtained with FBCCA and SVMs (more traditional SSVEP classification methods) in BCIs with small data lengths and one electrode. This type of BCI can be used to develop small and fast systems.

Prefrontal Asymmetry BCI Neurofeedback Datasets.

Prefrontal cortex (PFC) asymmetry is an important marker in affective neuroscience and has attracted significant interest, having been associated with studies of motivation, eating behavior, empathy, risk propensity, and clinical depression. The data presented in this paper are the result of three different experiments using PFC asymmetry neurofeedback (NF) as a Brain-Computer Interface (BCI) paradigm, rather than a therapeutic mechanism aiming at long-term effects, using functional near-infrared spectroscopy (fNIRS) which is known to be particularly well-suited to the study of PFC asymmetry and is less sensitive to artifacts. From an experimental perspective the BCI context brings more emphasis on individual subjects' baselines, successful and sustained activation during epochs, and minimal training. The subject pool is also drawn from the general population, with less bias toward specific behavioral patterns, and no inclusion of any patient data. We accompany our datasets with a detailed description of data formats, experiment and protocol designs, as well as analysis of the individualized metrics for definitions of success scores based on baseline thresholds as well as reference tasks. The work presented in this paper is the result of several experiments in the domain of BCI where participants are interacting with continuous visual feedback following a real-time NF paradigm, arising from our long-standing research in the field of affective computing. We offer the community access to our fNIRS datasets from these experiments. We specifically provide data drawn from our empirical studies in the field of affective interactions with computer-generated narratives as well as interfacing with algorithms, such as heuristic search, which all provide a mechanism to improve the ability of the participants to engage in active BCI due to their realistic visual feedback. Beyond providing details of the methodologies used where participants received real-time NF of left-asymmetric increase in activation in their dorsolateral prefrontal cortex (DLPFC), we re-establish the need for carefully designing protocols to ensure the benefits of NF paradigm in BCI are enhanced by the ability of the real-time visual feedback to adapt to the individual responses of the participants. Individualized feedback is paramount to the success of NF in BCIs.

Active inference as a unifying, generic and adaptive framework for a P300-based BCI

Objective. Going adaptive is a major challenge for the field of brain–computer interface (BCI). This entails a machine that optimally articulates inference about the user’s intentions and its own actions. Adaptation can operate over several dimensions which calls for a generic and flexible framework. Approach. We appeal to one of the most comprehensive computational approach to brain (adaptive) functions: the active inference (AI) framework. It entails an explicit (probabilistic) model of the user that the machine interacts with, here involved in a P300-spelling task. This takes the form of a discrete input–output state-space model establishing the link between the machine’s (i) observations—a P300 or error potential for instance, (ii) representations—of the user intentions to spell or pause, and (iii) actions—to flash, spell or switch-off the application. Main results. Using simulations with real EEG data from 18 subjects, results demonstrate the ability of AI to yield a significant increase in bit rate (17%) over state-of-the-art approaches, such as dynamic stopping. Significance. Thanks to its flexibility, this one model enables to implement optimal (dynamic) stopping but also optimal flashing (i.e. active sampling), automated error correction, and switching off when the user does not look at the screen anymore. Importantly, this approach enables the machine to flexibly arbitrate between all these possible actions. We demonstrate AI as a unifying and generic framework to implement a flexible interaction behaviour in a given BCI context.

Neural mechanisms of training an auditory event-related potential task in a brain-computer interface context.

Effective use of brain-computer interfaces (BCIs) typically requires training. Improved understanding of the neural mechanisms underlying BCI training will facilitate optimisation of BCIs. The current study examined the neural mechanisms related to training for electroencephalography (EEG)-based communication with an auditory event-related potential (ERP) BCI. Neural mechanisms of training in 10 healthy volunteers were assessed with functional magnetic resonance imaging (fMRI) during an auditory ERP-based BCI task before (t1) and after (t5) three ERP-BCI training sessions outside the fMRI scanner (t2, t3, and t4). Attended stimuli were contrasted with ignored stimuli in the first-level fMRI data analysis (t1 and t5); the training effect was verified using the EEG data (t2-t4); and brain activation was contrasted before and after training in the second-level fMRI data analysis (t1 vs. t5). Training increased the communication speed from 2.9 bits/min (t2) to 4 bits/min (t4). Strong activation was found in the putamen, supplementary motor area (SMA), and superior temporal gyrus (STG) associated with attention to the stimuli. Training led to decreased activation in the superior frontal gyrus and stronger haemodynamic rebound in the STG and supramarginal gyrus. The neural mechanisms of ERP-BCI training indicate improved stimulus perception and reduced mental workload. The ERP task used in the current study showed overlapping activations with a motor imagery based BCI task from a previous study on the neural mechanisms of BCI training in the SMA and putamen. This suggests commonalities between the neural mechanisms of training for both BCI paradigms.

Empirical Movement Models for Brain Computer Interfaces.

For brain-computer interfaces (BCIs) which provide the user continuous position control, there is little standardization of performance metrics or evaluative tasks. One candidate metric is Fitts's law, which has been used to describe aimed movements across a range of computer interfaces, and has recently been applied to BCI tasks. Reviewing selected studies, we identify two basic problems with Fitts's law: its predictive performance is fragile, and the estimation of 'information transfer rate' from the model is unsupported. Our main contribution is the adaptation and validation of an alternative model to Fitts's law in the BCI context. We show that the Shannon-Welford model outperforms Fitts's law, showing robust predictive power when target distance and width have disproportionate effects on difficulty. Building on a prior study of the Shannon-Welford model, we show that identified model parameters offer a novel approach to quantitatively assess the role of control-display gain in speed/accuracy performance tradeoffs during brain control.

Extracellular voltage threshold settings can be tuned for optimal encoding of movement and stimulus parameters

Objective. A traditional goal of neural recording with extracellular electrodes is to isolate action potential waveforms of an individual neuron. Recently, in brain–computer interfaces (BCIs), it has been recognized that threshold crossing events of the voltage waveform also convey rich information. To date, the threshold for detecting threshold crossings has been selected to preserve single-neuron isolation. However, the optimal threshold for single-neuron identification is not necessarily the optimal threshold for information extraction. Here we introduce a procedure to determine the best threshold for extracting information from extracellular recordings. We apply this procedure in two distinct contexts: the encoding of kinematic parameters from neural activity in primary motor cortex (M1), and visual stimulus parameters from neural activity in primary visual cortex (V1). Approach. We record extracellularly from multi-electrode arrays implanted in M1 or V1 in monkeys. Then, we systematically sweep the voltage detection threshold and quantify the information conveyed by the corresponding threshold crossings. Main Results. The optimal threshold depends on the desired information. In M1, velocity is optimally encoded at higher thresholds than speed; in both cases the optimal thresholds are lower than are typically used in BCI applications. In V1, information about the orientation of a visual stimulus is optimally encoded at higher thresholds than is visual contrast. A conceptual model explains these results as a consequence of cortical topography. Significance. How neural signals are processed impacts the information that can be extracted from them. Both the type and quality of information contained in threshold crossings depend on the threshold setting. There is more information available in these signals than is typically extracted. Adjusting the detection threshold to the parameter of interest in a BCI context should improve our ability to decode motor intent, and thus enhance BCI control. Further, by sweeping the detection threshold, one can gain insights into the topographic organization of the nearby neural tissue.

Brain oscillatory signatures of motor tasks.

Noninvasive brain-computer-interfaces (BCI) coupled with prosthetic devices were recently introduced in the rehabilitation of chronic stroke and other disorders of the motor system. These BCI systems and motor rehabilitation in general involve several motor tasks for training. This study investigates the neurophysiological bases of an EEG-oscillation-driven BCI combined with a neuroprosthetic device to define the specific oscillatory signature of the BCI task. Controlling movements of a hand robotic orthosis with motor imagery of the same movement generates sensorimotor rhythm oscillation changes and involves three elements of tasks also used in stroke motor rehabilitation: passive and active movement, motor imagery, and motor intention. We recorded EEG while nine healthy participants performed five different motor tasks consisting of closing and opening of the hand as follows: 1) motor imagery without any external feedback and without overt hand movement, 2) motor imagery that moves the orthosis proportional to the produced brain oscillation change with online proprioceptive and visual feedback of the hand moving through a neuroprosthetic device (BCI condition), 3) passive and 4) active movement of the hand with feedback (seeing and feeling the hand moving), and 5) rest. During the BCI condition, participants received contingent online feedback of the decrease of power of the sensorimotor rhythm, which induced orthosis movement and therefore proprioceptive and visual information from the moving hand. We analyzed brain activity during the five conditions using time-frequency domain bootstrap-based statistical comparisons and Morlet transforms. Activity during rest was used as a reference. Significant contralateral and ipsilateral event-related desynchronization of sensorimotor rhythm was present during all motor tasks, largest in contralateral-postcentral, medio-central, and ipsilateral-precentral areas identifying the ipsilateral precentral cortex as an integral part of motor regulation. Changes in task-specific frequency power compared with rest were similar between motor tasks, and only significant differences in the time course and some narrow specific frequency bands were observed between motor tasks. We identified EEG features representing active and passive proprioception (with and without muscle contraction) and active intention and passive involvement (with and without voluntary effort) differentiating brain oscillations during motor tasks that could substantially support the design of novel motor BCI-based rehabilitation therapies. The BCI task induced significantly different brain activity compared with the other motor tasks, indicating neural processes unique to the use of body actuators control in a BCI context.

Virtual Agents in Brain-Computer Interfaces

The recent development of Brain-Computer Interfaces (BCI) for Virtual Worlds has resulted in a growing interest in realistic visual feedback. In this paper, we investigate the potential role of Virtual Agents in neurofeedback (NF) systems, which constitute an important paradigm for BCI. We discuss the potential of virtual agents to contribute to the success of NF in the specific context of affective BCI. Throughout the paper, we illustrate our presentation with two fully implemented NF prototypes featuring virtual agents. The first is an interactive narrative in which the user empathises with the feature character; the second, an emotion regulation system in which virtual crowd behaviour becomes a metaphor for arousal, as the user attempts to down-regulate their affective state.

Improved Feature Extraction of Hand Movement EEG Signals based on Independent Component Analysis and Spatial Filter

In brain computer interface (BCI) system, the most important part is classification of human thoughts in order to translate into commands. The more accuracy result in classification the system gets, the more effective BCI system is. To increase the quality of BCI system, we proposed to reduce noise and artifact from the recording data to analyzing data. We used auditory stimuli instead of visual ones to eliminate the eye movement, unwanted visual activation, gaze control. We applied independent component analysis (ICA) algorithm to purify the sources which constructed the raw signals. One of the most famous spatial filter in BCI context is common spatial patterns (CSP), which maximize one class while minimize the other by using covariance matrix. ICA and CSP also do the filter job, as a raw filter and refinement, which increase the classification result of linear discriminant analysis (LDA).

Tactile, Visual, and Bimodal P300s: Could Bimodal P300s Boost BCI Performance?

The P300 is a positive peak in EEG occurring after presentation of a target stimulus. For brain-computer interfaces (BCIs), eliciting P300s by tactile stimuli would have specific advantages; the display can be hidden under clothes and keeps the user's gaze free. In addition, robust classification is especially important for BCIs. This motivated us to investigate P300s in response to tactile and visual stimuli unimodally and bimodally. Tactile stimuli were delivered by tactors around the participant's waist. Visual stimuli were flashed circles on a monitor, schematically representing the tactors. Participants attended to the vibrations and/or flashes of a ‘‘target’’ presented in a stream of standards. The P300 amplitude for the different modalities was comparable in size and depended on electrode location. Classification accuracy was highest in the bimodal condition. We conclude that bimodal stimuli could enhance classification results within a BCI context compared to unimodal presentations.

P14.2 Autoregressive spectral analysis in non-invasive brain computer interface context

P14.2 Autoregressive spectral analysis in non-invasive brain computer interface context