The LDA beamformer: Optimal estimation of ERP source time series using linear discriminant analysis.

We introduce a novel beamforming approach for estimating event-related potential (ERP) source time series based on regularized linear discriminant analysis (LDA). The optimization problems in LDA and linearly-constrained minimum-variance (LCMV) beamformers are formally equivalent. The approaches differ in that, in LCMV beamformers, the spatial patterns are derived from a source model, whereas in an LDA beamformer the spatial patterns are derived directly from the data (i.e., the ERP peak). Using a formal proof and MEG simulations, we show that the LDA beamformer is robust to correlated sources and offers a higher signal-to-noise ratio than the LCMV beamformer and PCA. As an application, we use EEG data from an oddball experiment to show how the LDA beamformer can be harnessed to detect single-trial ERP latencies and estimate connectivity between ERP sources. Concluding, the LDA beamformer optimally reconstructs ERP sources by maximizing the ERP signal-to-noise ratio. Hence, it is a highly suited tool for analyzing ERP source time series, particularly in EEG/MEG studies wherein a source model is not available.

Identifying Granger causal relationships between neural power dynamics and variables of interest.

Power modulations of oscillations in electro- and magnetoencephalographic (EEG/MEG) signals have been linked to a wide range of brain functions. To date, most of the evidence is obtained by correlating bandpower fluctuations to specific target variables such as reaction times or task ratings, while the causal links between oscillatory activity and behavior remain less clear. Here, we propose to identify causal relationships by the statistical concept of Granger causality, and we investigate which methods are bests suited to reveal Granger causal links between the power of brain oscillations and experimental variables. As an alternative to testing such causal links on the sensor level, we propose to linearly combine the information contained in each sensor in order to create virtual channels, corresponding to estimates of underlying brain oscillations, the Granger-causal relations of which may be assessed. Such linear combinations of sensor can be given by source separation methods such as, for example, Independent Component Analysis (ICA) or by the recently developed Source Power Correlation (SPoC) method. Here we compare Granger causal analysis on power dynamics obtained from i) sensor directly, ii) spatial filtering methods that do not optimize for Granger causality (ICA and SPoC), and iii) a method that directly optimizes spatial filters to extract sources the power dynamics of which maximally Granger causes a given target variable. We refer to this method as Granger Causal Power Analysis (GrangerCPA). Using both simulated and real EEG recordings, we find that computing Granger causality on channel-wise spectral power suffers from a poor signal-to-noise ratio due to volume conduction, while all three multivariate approaches alleviate this issue. In real EEG recordings from subjects performing self-paced foot movements, all three multivariate methods identify neural oscillations with motor-related patterns at a similar performance level. In an auditory perception task, the application of GrangerCPA reveals significant Granger-causal links between alpha oscillations and reaction times in more subjects compared to conventional methods.

Extracting latent brain states--Towards true labels in cognitive neuroscience experiments.

Neuroscientific data is typically analyzed based on the behavioral response of the participant. However, the errors made may or may not be in line with the neural processing. In particular in experiments with time pressure or studies where the threshold of perception is measured, the error distribution deviates from uniformity due to the structure in the underlying experimental set-up. When we base our analysis on the behavioral labels as usually done, then we ignore this problem of systematic and structured (non-uniform) label noise and are likely to arrive at wrong conclusions in our data analysis. This paper contributes a remedy to this important scenario: we present a novel approach for a) measuring label noise and b) removing structured label noise. We demonstrate its usefulness for EEG data analysis using a standard d2 test for visual attention (N=20 participants).

EEG-based classification of video quality perception using steady state visual evoked potentials (SSVEPs).

OBJECTIVE: Recent studies exploit the neural signal recorded via electroencephalography (EEG) to get a more objective measurement of perceived video quality. Most of these studies capitalize on the event-related potential component P3. We follow an alternative approach to the measurement problem investigating steady state visual evoked potentials (SSVEPs) as EEG correlates of quality changes. Unlike the P3, SSVEPs are directly linked to the sensory processing of the stimuli and do not require long experimental sessions to get a sufficient signal-to-noise ratio. Furthermore, we investigate the correlation of the EEG-based measures with the outcome of the standard behavioral assessment. APPROACH: As stimulus material, we used six gray-level natural images in six levels of degradation that were created by coding the images with the HM10.0 test model of the high efficiency video coding (H.265/MPEG-HEVC) using six different compression rates. The degraded images were presented in rapid alternation with the original images. In this setting, the presence of SSVEPs is a neural marker that objectively indicates the neural processing of the quality changes that are induced by the video coding. We tested two different machine learning methods to classify such potentials based on the modulation of the brain rhythm and on time-locked components, respectively. MAIN RESULTS: Results show high accuracies in classification of the neural signal over the threshold of the perception of the quality changes. Accuracies significantly correlate with the mean opinion scores given by the participants in the standardized degradation category rating quality assessment of the same group of images. SIGNIFICANCE: The results show that neural assessment of video quality based on SSVEPs is a viable complement of the behavioral one and a significantly fast alternative to methods based on the P3 component.

Single-trial analysis of the neural correlates of speech quality perception.

OBJECTIVE: Assessing speech quality perception is a challenge typically addressed in behavioral and opinion-seeking experiments. Only recently, neuroimaging methods were introduced, which were used to study the neural processing of quality at group level. However, our electroencephalography (EEG) studies show that the neural correlates of quality perception are highly individual. Therefore, it became necessary to establish dedicated machine learning methods for decoding subject-specific effects. APPROACH: The effectiveness of our methods is shown by the data of an EEG study that investigates how the quality of spoken vowels is processed neurally. Participants were asked to indicate whether they had perceived a degradation of quality (signal-correlated noise) in vowels, presented in an oddball paradigm. MAIN RESULTS: We find that the P3 amplitude is attenuated with increasing noise. Single-trial analysis allows one to show that this is partly due to an increasing jitter of the P3 component. A novel classification approach helps to detect trials with presumably non-conscious processing at the threshold of perception. We show that this approach uncovers a non-trivial confounder between neural hits and neural misses. SIGNIFICANCE: The combined use of EEG signals and machine learning methods results in a significant 'neural' gain in sensitivity (in processing quality loss) when compared to standard behavioral evaluation; averaged over 11 subjects, this amounts to a relative improvement in sensitivity of 35%.

Revealing the neural response to imperceptible peripheral flicker with machine learning.

Lighting in modern-day devices is often discrete. The sharp onsets and offsets of light are known to induce a steady-state visually evoked potential (SSVEP) in the electroencephalogram (EEG) at low frequencies. However, it is not well-known how the brain processes visual flicker at the threshold of conscious perception and beyond. To shed more light on this, we ran an EEG study in which we asked participants (N=6) to discriminate on a behavioral level between visual stimuli in which they perceived flicker and those that they perceived as constant wave light. We found that high frequency flicker which is not perceived consciously anymore still elicits a neural response in the corresponding frequency band of EEG, con-tralateral to the stimulated hemifield. The main contribution of this paper is to show the benefit of machine learning techniques for investigating this effect of subconscious processing: Common Spatial Pattern (CSP) filtering in combination with classification based on Linear Discriminant Analysis (LDA) could be used to reveal the effect for additional participants and stimuli, with high statistical significance. We conclude that machine learning techniques are a valuable extension of conventional neurophysiological analysis that can substantially boost the sensitivity to subconscious effects, such as the processing of imperceptible flicker.

Using ERPs for assessing the (sub) conscious perception of noise.

In this paper, we investigate the use of event-related potentials (ERPs) as a quantitative measure for quality assessment of disturbed audio signals. For this purpose, we ran an EEG study (N=11) using an oddball paradigm, during which subjects were presented with the phoneme /a/, superimposed with varying degrees of signal-correlated noise. Based on this data set, we address the question to which degree the degradation of the auditory stimuli is reflected on a neural level, even if the disturbance is below the threshold of conscious perception. For those stimuli that are consciously recognized as being disturbed, we suggest the use of the amplitude and latency of the P300 component for assessing the level of disturbance. For disturbed stimuli for which the noise is not perceived consciously, we show for two subjects that a classifier based on shrinkage LDA can be applied successfully to single out stimuli, for which the noise was presumably processed subconsciously.