Thesis

Error correcting codes for the P300 visual speller

Authors:
To read the full-text of this research, you can request a copy directly from the author.

No full-text available

Request Full-text Paper PDF

To read the full-text of this research,
you can request a copy directly from the author.

... Various review and comparison articles have been published to cover different aspects of P300 spellers and compare the performance of different classifier strategies on P300based BCI (Akcakaya et al., 2014;Fazel-Rezai et al., 2012;Hwang, Kim, Choi, & Im, 2013;Krusienski et al., 2006;Lotte et al., 2007;Mirghasemi, Fazel-Rezai, & Shamsollahi, 2006;Syan & Harnarinesingh, 2010). Different types of signal processing methods (Cecotti, 2015;Jung et al., 2001;Xu et al., 2004), dimension reduction methods (Andrews, Palaniappan, Teoh, & Chu Kiong, 2008;Li, Sankar, Arbel, & Donchin, 2009;Ming et al., 2010;Piccione et al., 2006;Syan & Harnarinesingh, 2010), and error correction codes (Bießmann, 2007;Hill, Farquhar, Martens, Bießmann, & Schölkopf, 2009) have also been developed to increase the ITR. ...
Article
P300 speller based Brain-Computer Interface (BCI) is a direct communication from human brain to computer machine that is based on decoding of brain responses generated by stimulation of a subject using P300 speller paradigm. This communication does not require any muscular movements. A novel Devanagari Script (DS) input based P300 speller system is proposed in this paper. A novel 8 × 8 matrix consisting of Devanagari characters, digits and special symbols has also been proposed as DS paradigm. The character set associated with DS paradigm is comparatively larger than the standard 6 × 6 English Row/Column (RC) paradigm. The problems related to crowding effect, fatigue and task difficulty increases while using DS paradigm for P300 speller. This leads to either exhaustive or false detection of characters. In order to overcome these problems, a novel Weighted Ensemble of Support Vector Machines (WESVM) based method has been proposed for classification. Further improvement in the system performance in terms of accuracy and reduced computational cost has been achieved by employing a binary Differential Evolution (DE) method for optimal channel selection. The proposed method has been tested on the EEG data collected from 9 subjects using DS paradigm. An average accuracy of 94.2% was achieved when WESVM method was applied with binary DE based channel selection method.
Article
Full-text available
We summarize results from a series of related studies that aim to develop a motor-imagery-based brain-computer interface using a single recording session of EEG or ECoG signals for each subject. We apply the same experimental and analytical methods to 11 non-paralysed subjects (8 EEG, 3 ECoG), and to 5 paralysed subjects (4 EEG, 1 ECoG) who had been unable to communicate for some time. While it was relatively easy to obtain classifiable signals quickly from most of the non-paralysed subjects, it proved impossible to classify the signals obtained from the paralysed patients by the same methods. This highlights the fact that though certain BCI paradigms may work well with healthy subjects, this does not necessarily indicate success with the target user group. We outline possible reasons for this failure to transfer.
Article
Full-text available
A P300 spelling system is one of the most popular EEG-based spelling systems. This system is normally presented as a matrix and allows its users to select one of many options by focused attention. It is possible to use large matrices as a large menu (computer keyboard, etc.), but then more time is required for each selection, because all rows and columns of the matrix must flash once per trial to locate the target character in the row/column (RC) speller method. In this paper, a new flash pattern design based on mathematical combinations is suggested. This new method decreases the number of flashes required in each trial. A typical example of a 6x6 matrix is considered. Only 9 flashes per trial for the 6x6 matrix are required in this new method, which is 3 flashes less than the RC speller method (12 flashes per trial). In this paper, practical bit rate was used. Results from offline analysis have shown that the 9-flash pattern yielded significantly higher practical bit rate than the 12-flash pattern (RC pattern).
Article
Full-text available
A brain-computer interface (BCI) is a new communication channel between humans and computers that translates brain activity into recognizable command and control signals. Attended events can evoke P300 potentials in the electroencephalogram. Hence, the P300 has been used in BCI systems to spell, control cursors or robotic devices, and other tasks. This paper introduces a novel P300 BCI to communicate Chinese characters. To improve classification accuracy, an optimization algorithm (particle swarm optimization, PSO) is used for channel selection (i.e., identifying the best electrode configuration). The effects of different electrode configurations on classification accuracy were tested by Bayesian linear discriminant analysis offline. The offline results from 11 subjects show that this new P300 BCI can effectively communicate Chinese characters and that the features extracted from the electrodes obtained by PSO yield good performance.
Article
Full-text available
We propose an approach to analyze data from the P300 speller paradigm using the machine-learning technique support vector machines. In a conservative classification scheme, we found the correct solution after five repetitions. While the classification within the competition is designed for offline analysis, our approach is also well-suited for a real-world online solution: It is fast, requires only 10 electrode positions and demands only a small amount of preprocessing.
Article
Full-text available
Over the past decade, many laboratories have begun to explore brain-computer interface (BCI) technology as a radically new communication option for those with neuromuscular impairments that prevent them from using conventional augmentative communication methods. BCI's provide these users with communication channels that do not depend on peripheral nerves and muscles. This article summarizes the first international meeting devoted to BCI research and development. Current BCI's use electroencephalographic (EEG) activity recorded at the scalp or single-unit activity recorded from within cortex to control cursor movement, select letters or icons, or operate a neuroprosthesis. The central element in each BCI is a translation algorithm that converts electrophysiological input from the user into output that controls external devices. BCI operation depends on effective interaction between two adaptive controllers, the user who encodes his or her commands in the electrophysiological input provided to the BCI, and the BCI which recognizes the commands contained in the input and expresses them in device control. Current BCI's have maximum information transfer rates of 5-25 b/min. Achievement of greater speed and accuracy depends on improvements in signal processing, translation algorithms, and user training. These improvements depend on increased interdisciplinary cooperation between neuroscientists, engineers, computer programmers, psychologists, and rehabilitation specialists, and on adoption and widespread application of objective methods for evaluating alternative methods. The practical use of BCI technology depends on the development of appropriate applications, identification of appropriate user groups, and careful attention to the needs and desires of individual users. BCI research and development will also benefit from greater emphasis on peer-reviewed publications, and from adoption of standard venues for presentations and discussion.
Article
Full-text available
A considerable rate of misdiagnosis has recently been reported in movement disorders. One of the most difficult clinical problems is the differentiation of Parkinson's disease and essential tremor. In this study, we have examined whether event-related potentials (ERPs) could aid in the solution of this differential diagnostic problem. Visual ERPs were obtained by using an "oddball" paradigm in 20 patients with idiopathic Parkinson's disease (IPD), 20 patients with essential tremor (ET), and 20 age-matched control subjects. We found that the P300 amplitudes were selectively reduced in the IPD group at the midline (Fz, Cz, Pz) electrode sites, whereas the ET group exhibited selectively elevated P300 amplitudes at the left parietal and frontal (F3, P3) recording sites. The patients with IPD, but not ET, showed a significant prolongation of the P300 latency at each electrode site. Similarly, only the IPD patients were significantly slower in responding to the target stimulus. The primary visual evoked potential (P100) did not distinguish among the IPD, ET, and control subjects. These results suggest that visual ERPs might provide a useful diagnostic method for differentiating IPD from ET.
Article
Full-text available
Clinical trials have suggested that neurofeedback may be efficient in treating attention-deficit/hyperactivity disorder (ADHD). We compared the effects of a 3-month electroencephalographic feedback program providing reinforcement contingent on the production of cortical sensorimotor rhythm (12-15 Hz) and betal activity (15-18 Hz) with stimulant medication. Participants were N = 34 children aged 8-12 years, 22 of which were assigned to the neurofeedback group and 12 to the methylphenidate group according to their parents' preference. Both neurofeedback and methylphenidate were associated with improvements on all subscales of the Test of Variables of Attention, and on the speed and accuracy measures of the d2 Attention Endurance Test. Furthermore, behaviors related to the disorder were rated as significantly reduced in both groups by both teachers and parents on the IOWA-Conners Behavior Rating Scale. These findings suggest that neurofeedback was efficient in improving some of the behavioral concomitants of ADHD in children whose parents favored a nonpharmacological treatment.
Article
Full-text available
The mismatch negativity (MMN) component is an event-related potential (ERP) that can be elicited by any change in the acoustic environment, and it is related to memory-based, automatic processing mechanisms, and attentional capture processes. This component is well defined in the auditory modality. However, there is still a great controversy about its existence in the visual modality. This paper reviews the studies that are relevant with regard to memory-based, automatic deviance detection ERPs in the visual system. The paper discusses the main strengths and limitations of those studies and suggests what directions should be taken for future research.
Article
Full-text available
The abrupt onset of a novel event captures attention away from, and disrupts, ongoing task performance. Less obvious is that intentional task switching compares with novelty-induced behavioral distraction. Here we explore the hypothesis that intentional task switching and attentional capture by a novel distracter both activate a common neural network involved in processing contextual novelty [Barcelo, F., Periáñez, J. A., & Knight, R. T. Think differently: A brain orienting response to task novelty. NeuroReport, 13, 1887-1892, 2002.]. Event-related potentials were recorded in two task-cueing paradigms while 16 subjects sorted cards following either two (color or shape; two-task condition) or three (color, shape, or number; three-task condition) rules of action. Each card was preceded by a familiar tone cueing the subject either to switch or to repeat the previous rule. Novel sound distracters were interspersed in one of two blocks of trials in each condition. Both novel sounds and task-switch cues impaired responses to the following visual target. Novel sounds elicited novelty P3 potentials with their usual peak latency and frontal-central scalp distribution. Familiar tonal switch cues in the three- and two-task conditions elicited brain potentials with a similar latency and morphology as the novelty P3, but with relatively smaller amplitudes over frontal scalp regions. Covariance and principal component analyses revealed a sustained frontal negative potential that was distorting concurrent novelty P3 activity to the tonal switch cues. When this frontal negativity was statistically removed, P3 potentials to novel sounds and task-switch cues showed similar scalp topographies. The degree of activation in the novelty P3 network seemed to be a function of the information (entropy) conveyed by the eliciting stimulus for response selection, over and above its relative novelty, probability of occurrence, task relevance, or feedback value. We conclude that novelty P3 reflects transient activation in a neural network involved in updating task set information for goal-directed action selection and might thus constitute one key element in a central bottleneck for attentional control.
Article
Full-text available
There has been an increase in research interest for brain-computer interface (BCI) technology as an alternate mode of communication and environmental control for the disabled, such as patients suffering from amyotrophic lateral sclerosis (ALS), brainstem stroke and spinal cord injury. Disabled patients with appropriate physical care and cognitive ability to communicate with their social environment continue to live with a reasonable quality of life over extended periods of time. Near-infrared spectroscopy is a non-invasive technique which utilizes light in the near-infrared range (700 to 1000 nm) to determine cerebral oxygenation, blood flow and metabolic status of localized regions of the brain. In this paper, we describe a study conducted to test the feasibility of using multichannel NIRS in the development of a BCI. We used a continuous wave 20-channel NIRS system over the motor cortex of 5 healthy volunteers to measure oxygenated and deoxygenated hemoglobin changes during left-hand and right-hand motor imagery. We present results of signal analysis indicating that there exist distinct patterns of hemodynamic responses which could be utilized in a pattern classifier towards developing a BCI. We applied two different pattern recognition algorithms separately, Support Vector Machines (SVM) and Hidden Markov Model (HMM), to classify the data offline. SVM classified left-hand imagery from right-hand imagery with an average accuracy of 73% for all volunteers, while HMM performed better with an average accuracy of 89%. Our results indicate potential application of NIRS in the development of BCIs. We also discuss here future extension of our system to develop a word speller application based on a cursor control paradigm incorporating online pattern classification of single-trial NIRS data.
Conference Paper
Full-text available
P300 speller is a communication tool with which one can input texts or commands to a computer by thought. The amplitude of the P300 evoked potential is inversely proportional to the probability of infrequent or task-related stimulus. In existing P300 spellers, rows and columns of a matrix are intensified successively and randomly, resulting in a stimulus frequency of 1/N (N is the number of rows or columns of the matrix). We propose a new paradigm to display each single character randomly and individually (therefore reducing the stimulus frequency to 1/(N*N)). On-line experiments showed that this new speller significantly improved the performance. Specifically, the new speller can reduce character classification error rate by up to 80% or double the information transfer rate compared to the existing P300 spellers.
Conference Paper
Biometric input devices can provide assistive technology access to people who have little or no motor control. We explore a biometric control interface based on the Galvanic Skin Response, to determine its effectiveness as a non-muscular channel of input. This paper presents data from several online studies of a locked-in subject using a Galvanic Skin Response system for communication and control. We present issues with GSR control, and approaches that may improve accuracy and information transfer rate.
Visual evoked potentials (VEPs) were recorded from normal adult subjects performing in a visual discrimination task. Subjects counted the number of presentations of the numeral 4 which was interposed rarely and randomly within a sequence of tachistoscopically flashed background stimuli (numeral 2s). Intrusive, task-irrelevant (not counted) stimuli were also interspersed rarely and randomly in the sequence of 2s; these stimuli were of two types: simples, which were easily recognizable (e.g., geometric figures), and novels, which were completely unrecognizable (i.e., complex, colorful patterns). It was found that the simples and the counted 4s evoked posteriorly distributed P3 waves (latency 380-430 msec) while the irrelevant novels evoked large, frontally distributed P3 waves (latency 360-380 msec). These large, frontal P3 waves to novels were also found to be preceded by large N2 waves (latency 278 msec). These findings indicate that "the P3" wave is not a unitary phenomenon but should be considered in terms of a family of waves, differing in their brain generators and in their psychological correlates. These late positive components are discussed in terms of task-relevance, recognition and Pavlov's "what is it" response.
Article
In recent years, many new cortical areas have been identified in the macaque monkey. The number of identified connections between areas has increased even more dramatically. We report here on (1) a summary of the layout of cortical areas associated with vision and with other modalities, (2) a computerized database for storing and representing large amounts of information on connectivity patterns, and (3) the application of these data to the analysis of hierarchical organization of the cerebral cortex. Our analysis concentrates on the visual system, which includes 25 neocortical areas that are predominantly or exclusively visual in function, plus an additional 7 areas that we regard as visual-association areas on the basis of their extensive visual inputs. A total of 305 connections among these 32 visual and visual-association areas have been reported. This represents 31% of the possible number of pathways if each area were connected with all others. The actual degree of connectivity is likely to be closer to 40%. The great majority of pathways involve reciprocal connections between areas. There are also extensive connections with cortical areas outside the visual system proper, including the somatosensory cortex, as well as neocortical, transitional, and archicortical regions in the temporal and frontal lobes. In the somatosensory/motor system, there are 62 identified pathways linking 13 cortical areas, suggesting an overall connectivity of about 40%. Based on the laminar patterns of connections between areas, we propose a hierarchy of visual areas and of somatosensory/motor areas that is more comprehensive than those suggested in other recent studies. The current version of the visual hierarchy includes 10 levels of cortical processing. Altogether, it contains 14 levels if one includes the retina and lateral geniculate nucleus at the bottom as well as the entorhinal cortex and hippocampus at the top. Within this hierarchy, there are multiple, intertwined processing streams, which, at a low level, are related to the compartmental organization of areas V1 and V2 and, at a high level, are related to the distinction between processing centers in the temporal and parietal lobes. However, there are some pathways and relationships (about 10% of the total) whose descriptions do not fit cleanly into this hierarchical scheme for one reason or another. In most instances, though, it is unclear whether these represent genuine exceptions to a strict hierarchy rather than inaccuracies or uncertainities in the reported assignment.
Article
In a visual event-related potential experiment, both N100 augmenting/reducing data and oddball paradigm P300 data were collected from the same subjects. A significant correlation was obtained between augmenting/reducing and the degree to which stimulus probability affected P300 amplitude. Subjects who augment/reduce in response to increased stimulus brightness in the sensory domain also appear to augment/reduce in response to low probability in the cognitive domain.
Article
The present study investigated the role of attentional resources in the performance of controlled and automatic detection tasks. The amplitude of the P300 component of the event-related potential has been shown to be a sensitive index of the attentional resources allocated to the perceptual processing of sensory stimuli. We found that P300s elicited in both automatic and controlled detection were large and of comparable amplitude, suggesting the involvement of a limited-capacity mechanism in both tasks. This result is in agreement with previous behavioral studies showing equivalent dual-task trade-offs with both search tasks (Hoffman & Nelson, Note 1). In contrast, P300 latency was considerably reduced in the automatic task, suggesting that the main effect of practice in the detection task is to improve the discriminability of targets and distractors.
Article
In a study of the neural processes that mediate visual attention in humans, 32-channel recordings of event-related potentials were obtained from 14 normal subjects while they performed a spatial attention task. The generator locations of the early C1, P1, and N1 components of the visual evoked response were estimated by means of topographic maps of voltage and current source density in conjunction with dipole modelling. The topography of the C1 component (ca. 85 ms post-stimulus) was consistent with a generator in striate cortex, and this component was unaffected by attention. In contrast, the P1 and N1 components (ca. 95 and 170 ms) exhibited current density foci at scalp sites overlying lateral extrastriate cortex and were larger for attended stimuli than for unattended stimuli. The voltage topographies in the 75-175 ms latency range were modeled with a 5-dipole configuration consisting of a single striate dipole and left-right pairs of dipoles located in lateral extrastriate and inferior occipito-temporal areas. This model was found to account for the voltage topographies produced by both attended and unattended stimuli with low residual variance. These results support the proposal that visual-spatial attention modulates neural activity in extrastriate visual cortex but does not affect the initial evoked response in striate cortex.
Article
P300 differences for target (.10), nontarget (.10), and standard tones (.80) were assessed using a three-stimulus oddball paradigm in which participants responded only to the target (n = 12). Target/standard (easy or difficult) and nontarget/standard (large or small) pitch differences were manipulated orthogonally. In all conditions, target tones elicited a parietal P300, which was affected only by the target/standard discrimination ease. Nontarget in the easy/large and difficult/small conditions elicited a parietal but smaller P300 than the target but in the easy/small condition elicited similar ERPs to the standard. However, nontarget stimuli in the difficult/large condition elicited an anterior maximum and earlier P300 (P3a) component. The findings suggest that target P300s are not influenced by the nontarget stimulus configuration, whereas the nontarget P300 outcomes are determined directly by the stimulus context. The theoretical implications are discussed.
Article
People with nerve or limb injuries may one day be able to command wheelchairs, prosthetics, and even paralyzed arms and legs by “thinking them through” the motions.
Article
Colored grating patterns were presented to 8 participants in a passive oddball condition (standard, 87.5% and deviant, 12.5%, differing in their color). In the corresponding multicolor condition, grating patterns of eight different colors were presented, their probabilities set equal both to each other and to that of the deviant in the oddball task. Compared with the ERP response elicited by the standard stimulus, the deviant response was negatively displaced over posterior areas, the difference wave peaking at 136 ms. A similar negative wave was obtained when the ERP response to the deviant was compared with the ERP elicited by the same stimulus in the multicolor condition. This result rules out stimulus- (color-) specific refractoriness as a major factor in the generation of the deviance-related posterior negativity. The observed posterior negativity can therefore be regarded as a visual analog of the mismatch negativity (vMMN).
Article
In one type of brain-computer interface (BCI), users self-modulate brain activity as detected by electroencephalography (EEG). To infer user intent, EEG signals are classified by algorithms which typically use only one of the several types of information available in these signals. One such BCI uses slow cortical potential (SCP) measures to classify single trials. We complemented these measures with estimates of high-frequency (gamma-band) activity, which has been associated with attentional and intentional states. Using a simple linear classifier, we obtained significantly greater classification accuracy using both types of information from the same recording epochs compared to using SCPs alone.
Article
A threshold detector for single-trial P300 detection has been evaluated. The detector operates on the 0-4 Hz band, isolated from the raw electroencephalogram using low-pass filtering, wavelet transforms, or the piecewise prony method (PPM). A detection rate around 70% was found, irregardless of stimulus type, interstimulus interval (ISI), probability of occurrence (Pr) of the target stimuli, intrasession and intersession effects, or filtering method. This suggests that P300-based brain-machine interfaces can use an ISI as short as 1 s and a Pr of 45%, to increase throughput.
Article
Can the rapid stream of conscious experience be predicted from brain activity alone? Recently, spatial patterns of activity in visual cortex have been successfully used to predict feature-specific stimulus representations for both visible [1 • Kamitani Y. • Tong F. Decoding the subjective contents of the human brain.Nat. Neurosci. 2005; 8: 679-685 • Crossref • PubMed • Scopus (1174) • Google Scholar , 2 • Haynes J.D.H. • Rees G. Predicting the orientation of invisible stimuli from activity in primary visual cortex.Nat. Neurosci. 2005; 6: 686-696 • Crossref • Scopus (592) • Google Scholar ] and invisible [2 • Haynes J.D.H. • Rees G. Predicting the orientation of invisible stimuli from activity in primary visual cortex.Nat. Neurosci. 2005; 6: 686-696 • Crossref • Scopus (592) • Google Scholar ] stimuli. However, because these studies examined only the prediction of static and unchanging perceptual states during extended periods of stimulation, it remains unclear whether activity in early visual cortex can also predict the rapidly and spontaneously changing stream of consciousness [3 • James W. The Principles of Psychology. Henry Holt, New York1890 • Crossref • Google Scholar ]. Here, we used binocular rivalry [4 • Blake R. • Logothetis N.K. Visual competition.Nat. Rev. Neurosci. 2002; 3: 13-21 • Crossref • PubMed • Scopus (925) • Google Scholar ] to induce frequent spontaneous and stochastic changes in conscious experience without any corresponding changes in sensory stimulation, while measuring brain activity with fMRI. Using information that was present in the multivariate pattern of responses to stimulus features, we could accurately predict, and therefore track, participants’ conscious experience from the fMRI signal alone while it underwent many spontaneous changes. Prediction in primary visual cortex primarily reflected eye-based signals, whereas prediction in higher areas reflected the color of the percept. Furthermore, accurate prediction during binocular rivalry could be established with signals recorded during stable monocular viewing, showing that prediction generalized across viewing conditions and did not require or rely on motor responses. It is therefore possible to predict the dynamically changing time course of subjective experience with only brain activity.
Article
Deception is a clinically important behavior with poorly understood neurobiological correlates. Published functional MRI (fMRI) data on the brain activity during deception indicates that, on a multisubject group level, lie is distinguished from truth by increased prefrontal and parietal activity. These findings are theoretically important; however, their applied value will be determined by the accuracy of the discrimination between single deceptive and truthful responses in individual subjects. This study presents the first quantitative estimate of the accuracy of fMRI in conjunction with a formal forced-choice paradigm in detecting deception in individual subjects. We used a paradigm balancing the salience of the target cues to elicit deceptive and truthful responses and determined the accuracy of this model in the classification of single lie and truth events. The relative salience of the task cues affected the net activation associated with lie in the superior medial and inferolateral prefrontal cortices. Lie was discriminated from truth on a single-event level with an accuracy of 78%, while the predictive ability expressed as the area under the curve (AUC) of the receiver operator characteristic curve (ROC) was 85%. Our findings confirm that fMRI, in conjunction with a carefully controlled query procedure, could be used to detect deception in individual subjects. Salience of the task cues is a potential confounding factor in the fMRI pattern attributed to deception in forced choice deception paradigms.
Article
Early stage Alzheimer disease patients and matched elderly unaffected controls (n = 16/group) were evaluated with the P300 event-related brain potential (ERP). All subjects performed four oddball tasks that varied systematically in task difficulty and were each presented in the auditory and visual modalities. P300 amplitude was smaller and peak latency longer for the Alzheimer patients compared to elderly control subjects across tasks and modalities. P300 differences between Alzheimer patients and controls were largest for the relatively easy tasks, with little influence of stimulus modality observed. The results suggest that the P300 brain potential is sensitive to Alzheimer's disease processes during its early stages, and that easily performed stimulus discrimination tasks are the clinically most useful. Theoretical and practical implications are reviewed.
Article
The current study evaluates the effectiveness of a brain-computer interface (BCI) system that operates by detecting a P300 elicited by one of four randomly presented stimuli (i.e. YES, NO, PASS, END). Two groups of participants were tested. The first group included three amyotrophic lateral sclerosis (ALS) patients that varied in degree of disability, but all retained the ability to communicate; the second group included three non-ALS controls. Each participant participated in ten experimental sessions during a period of approximately 6 weeks. During each run the participant's task was to attend to one stimulus and disregard the other three. Stimuli were presented auditorily, visually, or in both modes. Two of the 3 ALS patient's classification rates were equal to those achieved by the non-ALS participants. Waveform morphology varied as a function of the presentation mode, but not in a similar pattern for each participant. The event-related potentials elicited by the target stimuli could be discriminated from the non-target stimuli for the non-ALS and the ALS groups. Future studies will begin to examine online classification. The results of offline classification suggest that a P300-based BCI can serve as a non-muscular communication device in both ALS, and non-ALS control groups.