Single-trial EEG Research Articles

Predicting numerical data entry errors by classifying EEG signals with linear discriminant analysis

Daily numerical data entry is subject to human errors, and errors in numerical data can cause serious losses in health care, safety and finance. Difficulty in detecting errors by human operators in numerical data entry necessitates an early error detection/prediction mechanism to proactively prevent severe accidents. To explore the possibility of using multi-channel electroencephalography (EEG) collected before movements/reactions to detect/predict human errors, linear discriminant analysis (LDA) classifier was utilised to predict numerical typing errors before their occurrence in numerical typing. Single trial EEG data were collected from seven participants during numerical hear-and-type tasks and three temporal features were extracted from six EEG sites in a 150-ms time window. The sensitivity of LDA classifier was revealed by adjusting the critical ratio of two Mahalanobis distances as a classification criterion. On average, the LDA classifier was able to detect 74.34% of numerical typing errors in advance with only 34.46% false alarms, resulting in a sensitivity of 1.05. A cost analysis also showed that using the LDA classifier would be beneficial as long as the penalty is at least 15 times the cost of inspection when the error rate is 5%. LDA demonstrated its realistic potential in detecting/predicting relatively few errors in numerical data without heavy pre-processing. This is one step towards predicting and preventing human errors in perceptual-motor tasks before their occurrence.

ERP signal estimation from single trial EEG.

Non-invasive EEG recordings are subject to effects such as surface conduction, resulting in very low signal to noise ratio (SNR). The conventional approach of using signal averaging to improve the SNR cannot be used for single trial EEG estimation. As such, this paper proposes a beamforming based technique that can be used to improve the signal quality from a signal trial EEG measurement. Results on experimental data show that the proposed technique can successfully isolate the signal of interest from background processes.

Decoding of attentional selection in a cocktail party environment from single-trial EEG is robust to task.

Recently it has been shown to be possible to ascertain the target of a subject's attention in a cocktail party environment from single-trial (~60 s) electroencephalography (EEG) data. Specifically, this was shown in the context of a dichotic listening paradigm where subjects were cued to attend to a story in one ear while ignoring a different story in the other and were required to answer questions on both stories. This paradigm resulted in a high decoding accuracy that correlated with task performance across subjects. Here, we extend this finding by showing that the ability to accurately decode attentional selection in a dichotic speech paradigm is robust to the particular attention task at hand. Subjects attended to one of two dichotically presented stories under four task conditions. These conditions required subjects to 1) answer questions on the content of both stories, 2) detect irregular frequency fluctuations in the voice of the attended speaker 3) answer questions on both stories and detect frequency fluctuations in the attended story, and 4) detect target words in the attended story. All four tasks led to high decoding accuracy (~89%). These results offer new possibilities for creating user-friendly brain computer interfaces (BCIs).

Emotion recognition from single-trial EEG based on kernel Fisher's emotion pattern and imbalanced quasiconformal kernel support vector machine.

Electroencephalogram-based emotion recognition (EEG-ER) has received increasing attention in the fields of health care, affective computing, and brain-computer interface (BCI). However, satisfactory ER performance within a bi-dimensional and non-discrete emotional space using single-trial EEG data remains a challenging task. To address this issue, we propose a three-layer scheme for single-trial EEG-ER. In the first layer, a set of spectral powers of different EEG frequency bands are extracted from multi-channel single-trial EEG signals. In the second layer, the kernel Fisher's discriminant analysis method is applied to further extract features with better discrimination ability from the EEG spectral powers. The feature vector produced by layer 2 is called a kernel Fisher's emotion pattern (KFEP), and is sent into layer 3 for further classification where the proposed imbalanced quasiconformal kernel support vector machine (IQK-SVM) serves as the emotion classifier. The outputs of the three layer EEG-ER system include labels of emotional valence and arousal. Furthermore, to collect effective training and testing datasets for the current EEG-ER system, we also use an emotion-induction paradigm in which a set of pictures selected from the International Affective Picture System (IAPS) are employed as emotion induction stimuli. The performance of the proposed three-layer solution is compared with that of other EEG spectral power-based features and emotion classifiers. Results on 10 healthy participants indicate that the proposed KFEP feature performs better than other spectral power features, and IQK-SVM outperforms traditional SVM in terms of the EEG-ER accuracy. Our findings also show that the proposed EEG-ER scheme achieves the highest classification accuracies of valence (82.68%) and arousal (84.79%) among all testing methods.

Envelope responses in single-trial EEG indicate attended speaker in a ‘cocktail party’

Objective. Recent studies have shown that auditory cortex better encodes the envelope of attended speech than that of unattended speech during multi-speaker (‘cocktail party’) situations. We investigated whether these differences were sufficiently robust within single-trial electroencephalographic (EEG) data to accurately determine where subjects attended. Additionally, we compared this measure to other established EEG markers of attention. Approach. High-resolution EEG was recorded while subjects engaged in a two-speaker ‘cocktail party’ task. Cortical responses to speech envelopes were extracted by cross-correlating the envelopes with each EEG channel. We also measured steady-state responses (elicited via high-frequency amplitude modulation of the speech) and alpha-band power, both of which have been sensitive to attention in previous studies. Using linear classifiers, we then examined how well each of these features could be used to predict the subjects’ side of attention at various epoch lengths. Main results. We found that the attended speaker could be determined reliably from the envelope responses calculated from short periods of EEG, with accuracy improving as a function of sample length. Furthermore, envelope responses were far better indicators of attention than changes in either alpha power or steady-state responses. Significance. These results suggest that envelope-related signals recorded in EEG data can be used to form robust auditory BCI’s that do not require artificial manipulation (e.g., amplitude modulation) of stimuli to function.

Phase space reconstruction for improving the classification of single trial EEG

Electroencephalogram (EEG) signals are nonlinear time series, which are generally very noisy, nonstationary, and contaminated with artifacts that can deteriorate classification methods. This contribution presents an efficient scheme to extract features in phase space by exploiting the theoretical results derived in nonlinear dynamics for motor imagery tasks recognition. To remodel the single nonlinear sequence is to reveal variety of information hidden in the origin series by its phase space reconstruction (PSR), and maintaining the original information continuity. The phase space features (PSF) were extracted by the amplitude–frequency analysis (AFA) method in the state space of EEG signals (AFAPS). The linear discriminant analysis (LDA) classifiers based on the AFAPS features are used to classify two Graz datasets used in BCI Competition 2003 and 2005. The results have shown that the LDA classifiers based on PSF outperformed most of other similar studies on the same Graz dataset in terms of the competition criterions. The features extracted by the proposed scheme contain the nonlinear information which helps to improve the classification results in the BCI.

Decoding auditory attention to instruments in polyphonic music using single-trial EEG classification

Objective. Polyphonic music (music consisting of several instruments playing in parallel) is an intuitive way of embedding multiple information streams. The different instruments in a musical piece form concurrent information streams that seamlessly integrate into a coherent and hedonistically appealing entity. Here, we explore polyphonic music as a novel stimulation approach for use in a brain–computer interface. Approach. In a multi-streamed oddball experiment, we had participants shift selective attention to one out of three different instruments in music audio clips. Each instrument formed an oddball stream with its own specific standard stimuli (a repetitive musical pattern) and oddballs (deviating musical pattern). Main results. Contrasting attended versus unattended instruments, ERP analysis shows subject- and instrument-specific responses including P300 and early auditory components. The attended instrument can be classified offline with a mean accuracy of 91% across 11 participants. Significance. This is a proof of concept that attention paid to a particular instrument in polyphonic music can be inferred from ongoing EEG, a finding that is potentially relevant for both brain–computer interface and music research.

Sliding HDCA: Single-Trial EEG Classification to Overcome and Quantify Temporal Variability

Patterns of neural data obtained from electroencephalography (EEG) can be classified by machine learning techniques to increase human-system performance. In controlled laboratory settings this classification approach works well; however, transitioning these approaches into more dynamic, unconstrained environments will present several significant challenges. One such challenge is an increase in temporal variability in measured behavioral and neural responses, which often results in suboptimal classification performance. Previously, we reported a novel classification method designed to account for temporal variability in the neural response in order to improve classification performance by using sliding windows in hierarchical discriminant component analysis (HDCA), and demonstrated a decrease in classification error by over 50% when compared to the standard HDCA method (Marathe et al., 2013). Here, we expand upon this approach and show that embedded within this new method is a novel signal transformation that, when applied to EEG signals, significantly improves the signal-to-noise ratio and thereby enables more accurate single-trial analysis. The results presented here have significant implications for both brain-computer interaction technologies and basic science research into neural processes.

Towards real-time decoding of attentional selection in a multi-speaker environment, using single-trial EEG

Towards real-time decoding of attentional selection in a multi-speaker environment, using single-trial EEG

Robust Spatial Filters on Three-Class Motor Imagery EEG Data Using Independent Component Analysis

Independent Component Analysis (ICA) was often used to separate movement related independent components (MRICs) from Electroencephalogram (EEG) data. However, to obtain robust spatial filters, complex characteristic features, which were manually selected in most cases, have been commonly used. This study proposed a new simple algorithm to extract MRICs automatically, which just utilized the spatial distribution pattern of ICs. The main goal of this study was to show the relationship between spatial filters performance and designing samples. The EEG data which contain mixed brain states (preparing, motor imagery and rest) were used to design spatial filters. Meanwhile, the single class data was also used to calculate spatial filters to assess whether the MRICs extracted on different class motor imagery spatial filters are similar. Furthermore, the spatial filters constructed on one subject’s EEG data were applied to extract the others’ MRICs. Finally, the different spatial filters were then applied to single-trial EEG to extract MRICs, and Support Vector Machine (SVM) classifiers were used to discriminate left hand、right-hand and foot imagery movements of BCI Competition IV Dataset 2a, which recorded four motor imagery data of nine subjects. The results suggested that any segment of finite motor imagery EEG samples could be used to design ICA spatial filters, and the extracted MRICs are consistent if the position of electrodes are the same, which confirmed the robustness and practicality of ICA used in the motor imagery Brain Computer Interfaces (MI-BCI) systems.

On the applicability of brain reading for predictive human-machine interfaces in robotics.

The ability of today's robots to autonomously support humans in their daily activities is still limited. To improve this, predictive human-machine interfaces (HMIs) can be applied to better support future interaction between human and machine. To infer upcoming context-based behavior relevant brain states of the human have to be detected. This is achieved by brain reading (BR), a passive approach for single trial EEG analysis that makes use of supervised machine learning (ML) methods. In this work we propose that BR is able to detect concrete states of the interacting human. To support this, we show that BR detects patterns in the electroencephalogram (EEG) that can be related to event-related activity in the EEG like the P300, which are indicators of concrete states or brain processes like target recognition processes. Further, we improve the robustness and applicability of BR in application-oriented scenarios by identifying and combining most relevant training data for single trial classification and by applying classifier transfer. We show that training and testing, i.e., application of the classifier, can be carried out on different classes, if the samples of both classes miss a relevant pattern. Classifier transfer is important for the usage of BR in application scenarios, where only small amounts of training examples are available. Finally, we demonstrate a dual BR application in an experimental setup that requires similar behavior as performed during the teleoperation of a robotic arm. Here, target recognition processes and movement preparation processes are detected simultaneously. In summary, our findings contribute to the development of robust and stable predictive HMIs that enable the simultaneous support of different interaction behaviors.

Simultaneous EEG-fMRI Reveals Temporal Evolution of Coupling between Supramodal Cortical Attention Networks and the Brainstem

Cortical and subcortical networks have been identified that are commonly associated with attention and task engagement, along with theories regarding their functional interaction. However, a link between these systems has not yet been demonstrated in healthy humans, primarily because of data acquisition and analysis limitations. We recorded simultaneous EEG-fMRI while subjects performed auditory and visual oddball tasks and used these data to investigate the BOLD correlates of single-trial EEG variability at latencies spanning the trial. We focused on variability along task-relevant dimensions in the EEG for identical stimuli and then combined auditory and visual data at the subject level to spatially and temporally localize brain regions involved in endogenous attentional modulations. Specifically, we found that anterior cingulate cortex (ACC) correlates strongly with both early and late EEG components, whereas brainstem, right middle frontal gyrus (rMFG), and right orbitofrontal cortex (rOFC) correlate significantly only with late components. By orthogonalizing with respect to event-related activity, we found that variability in insula and temporoparietal junction is reflected in reaction time variability, rOFC and brainstem correlate with residual EEG variability, and ACC and rMFG are significantly correlated with both. To investigate interactions between these correlates of temporally specific EEG variability, we performed dynamic causal modeling (DCM) on the fMRI data. We found strong evidence for reciprocal effective connections between the brainstem and cortical regions. Our results support the adaptive gain theory of locus ceruleus-norepinephrine (LC-NE) function and the proposed functional relationship between the LC-NE system, right-hemisphere ventral attention network, and P300 EEG response.

Inter-trial coherence as a marker of cortical phase synchrony in children with sensorineural hearing loss and auditory neuropathy spectrum disorder fitted with hearing aids and cochlear implants

ObjectiveAlthough brainstem dys-synchrony is a hallmark of children with auditory neuropathy spectrum disorder (ANSD), little is known about how the lack of neural synchrony manifests at more central levels. We used time–frequency single-trial EEG analyses (i.e., inter-trial coherence; ITC), to examine cortical phase synchrony in children with normal hearing (NH), sensorineural hearing loss (SNHL) and ANSD. MethodsSingle trial time–frequency analyses were performed on cortical auditory evoked responses from 41 NH children, 91 children with ANSD and 50 children with SNHL. The latter two groups included children who received intervention via hearing aids and cochlear implants. ITC measures were compared between groups as a function of hearing loss, intervention type, and cortical maturational status. ResultsIn children with SNHL, ITC decreased as severity of hearing loss increased. Children with ANSD revealed lower levels of ITC relative to children with NH or SNHL, regardless of intervention. Children with ANSD who received cochlear implants showed significant improvements in ITC with increasing experience with their implants. ConclusionsCortical phase coherence is significantly reduced as a result of both severe-to-profound SNHL and ANSD. SignificanceITC provides a window into the brain oscillations underlying the averaged cortical auditory evoked response. Our results provide a first description of deficits in cortical phase synchrony in children with SNHL and ANSD.

The superior temporal sulcus and the N170 during face processing: Single trial analysis of concurrent EEG–fMRI

Face-selective neural signals have been reliably identified using both EEG and fMRI studies. These consist of the N170 component, a neural response peaking approximately 170ms after a face is presented, and face-selective activations in the fusiform face area (FFA), the occipital face area (OFA), and the superior temporal sulcus (STS). As most neuroimaging studies examine these face-selective processes separately, the relationship between the N170 neural response and activation in the fusiform gyrus is still debated. In this study, we concurrently measured EEG and fMRI responses to upright faces, inverted faces, and objects to examine this association. We introduce a method for single-trial estimation of N170 amplitudes and correlation of the trial-by-trial variation in N170 neural responses with fMRI BOLD responses. For upright faces, BOLD responses in the right STS were negatively correlated with N170 amplitudes, showing greater activation on trials in which N170 amplitudes were larger (more negative). For inverted faces, a medial region of the fusiform gyrus (mFG) was positively correlated with N170 amplitudes, showing greater activation on trials in which N170 amplitudes were smaller (less negative). This result points to the STS as a crucial region for generating the N170 associated with face perception, and suggests that the mFG is additionally recruited for processing inverted faces, particularly on trials in which N170 is small. Despite the different time resolution of fMRI and EEG signals, our single-trial estimation and EEG–fMRI correlation method can reveal associations between activation in face-selective brain regions and neural processes at 170ms associated with face perception.

The Synergy between Complex Channel-Specific FIR Filter and Spatial Filter for Single-Trial EEG Classification

The common spatial pattern analysis (CSP), a frequently utilized feature extraction method in brain-computer-interface applications, is believed to be time-invariant and sensitive to noises, mainly due to an inherent shortcoming of purely relying on spatial filtering. Therefore, temporal/spectral filtering which can be very effective to counteract the unfavorable influence of noises is usually used as a supplement. This work integrates the CSP spatial filters with complex channel-specific finite impulse response (FIR) filters in a natural and intuitive manner. Each hybrid spatial-FIR filter is of high-order, data-driven and is unique to its corresponding channel. They are derived by introducing multiple time delays and regularization into conventional CSP. The general framework of the method follows that of CSP but performs better, as proven in single-trial classification tasks like event-related potential detection and motor imagery.

Using single-trial EEG to predict and analyze subsequent memory

We show that it is possible to successfully predict subsequent memory performance based on single-trial EEG activity before and during item presentation in the study phase. Two-class classification was conducted to predict subsequently remembered vs. forgotten trials based on subjects' responses in the recognition phase. The overall accuracy across 18 subjects was 59.6% by combining pre- and during-stimulus information. The single-trial classification analysis provides a dimensionality reduction method to project the high-dimensional EEG data onto a discriminative space. These projections revealed novel findings in the pre- and during-stimulus periods related to levels of encoding. It was observed that the pre-stimulus information (specifically oscillatory activity between 25 and 35Hz) −300 to 0ms before stimulus presentation and during-stimulus alpha (7–12Hz) information between 1000 and 1400ms after stimulus onset distinguished between recollection and familiarity while the during-stimulus alpha information and temporal information between 400 and 800ms after stimulus onset mapped these two states to similar values.

Decoding sensation and perception over time using EEG pattern classification

A multivariate pattern classifier can decode both veridical and illusory visual position from single-trial EEG data with millisecond temporal resolution. Neural representations of illusory position rapidly advance from occipital to more central areas. When sensation and perception are dissociated, neural activity codes for the percept as early as 80 ms post-stimulus. Conclusions: The classifier is able to decode perceived position, even when bottom-up position information is identical. This performance is not attributable to decoding reversal direction (control condition). 2. Decoding Perception

P300 Oddball Task and Classification Based on Support Vector Machine for BCI System

The P300 oddball task is the most popular paradigm in the existing BCI systems. Recently using auditory stimuli in P300 oddball task arises since it gives much freedom to the BCI user. In this paper, we present a novel BCI paradigm using P300 and P100 responses. Since P300 and P100 responses occur in the frontal lobe and the temporal lobe respectively, so that we can use these responses stimulated by an audio in a single task. The main advantage of our designed paradigm is that we can obtain two different kinds of responses in a single trial EEG task. In the EEG data analysis, we first employ the multivariate empirical mode decomposition (MEMD) algorithm to extract P300 and P100 components. And then, we employ a support vector machine (SVM) technique for the feature classification.

Panic Disorder and Serotonin Reuptake Inhibitors Predict Coupling of Cortical and Cardiac Activity

Panic attacks, the cardinal symptom of panic disorder (PD), are characterized by intense physiological reactions including accelerated heart activity. Although cortical processes are thought to trigger and potentiate panic attacks, it is unknown whether individuals with PD have a general tendency to show elevated cortico-cardiac interactions, which could predispose them for brain-driven modulations of heart activity during panic. Consistent with this hypothesis, serotonin, a highly relevant neurotransmitter for panic and PD presumably affects the cortical control of the heart. The current study thus aimed to test whether PD and serotonin reuptake inhibitor (SRI) intake are related to cortico-cardiac interactions in the absence of acute panic. Human participants with PD (N=22), major depression (MD, clinical control group, N=21) or no psychiatric diagnosis (healthy control group, N=23) performed a gambling task. To measure cortico-cardiac coupling, the within-subject covariation of single-trial EEG after feedback presentation and subsequent changes in heart period was determined. As in prior studies, there was a significant time-lagged covariation of EEG and heart activity indicating that trial-by-trial fluctuations of feedback-evoked EEG amplitude determined how much heart activity accelerated seconds later. Importantly, this covariation pattern was significantly potentiated in PD vs control participants. Moreover, concurrent SRI intake further augmented brain-heart covariation in individuals with PD and MD. The present findings demonstrate that PD and serotonin are associated with altered brain-heart interactions in a non-panic situation. Future work should clarify whether brain-heart coupling has a causal role in PD, for example by facilitating panic attacks.

An Iterative Framework for EEG-based Image Search: Robust Retrieval with Weak Classifiers

We revisit the framework for brain-coupled image search, where the Electroencephalography (EEG) channel under rapid serial visual presentation protocol is used to detect user preferences. Extending previous works on the synergy between content-based image labeling and EEG-based brain-computer interface (BCI), we propose a different perspective on iterative coupling. Previously, the iterations were used to improve the set of EEG-based image labels before propagating them to the unseen images for the final retrieval. In our approach we accumulate the evidence of the true labels for each image in the database through iterations. This is done by propagating the EEG-based labels of the presented images at each iteration to the rest of images in the database. Our results demonstrate a continuous improvement of the labeling performance across iterations despite the moderate EEG-based labeling (AUC <75%). The overall analysis is done in terms of the single-trial EEG decoding performance and the image database reorganization quality. Furthermore, we discuss the EEG-based labeling performance with respect to a search task given the same image database.