Correcting for ERP latency jitter improves gaze-independent BCI decoding.

Objective.Patients suffering from heavy paralysis or Locked-in-Syndrome can regain communication using a Brain-Computer Interface (BCI). Visual event-related potential (ERP) based BCI paradigms exploit visuospatial attention (VSA) to targets laid out on a screen. However, performance drops if the user does not direct their eye gaze at the intended target, harming the utility of this class of BCIs for patients suffering from eye motor deficits. We aim to create an ERP decoder that is less dependent on eye gaze.Approach.ERP component latency jitter plays a role in covert visuospatial attention (VSA) decoding. We introduce a novel decoder which compensates for these latency effects, termed Woody Classifier-based Latency Estimation (WCBLE). We carried out a BCI experiment recording ERP data in overt and covert visuospatial attention (VSA), and introduce a novel special case of covert VSA termed split VSA, simulating the experience of patients with severely impaired eye motor control. We evaluate WCBLE on this dataset and the BNCI2014-009 dataset, within and across VSA conditions to study the dependency on eye gaze and the variation thereof during the experiment.Main results.WCBLE outperforms state-of-the-art methods in the VSA conditions of interest in gaze-independent decoding, without reducing overt VSA performance. Results from across-condition evaluation show that WCBLE is more robust to varying VSA conditions throughout a BCI operation session.Significance. Together, these results point towards a pathway to achieving gaze independence through suited ERP decoding. Our proposed gaze-independent solution enhances decoding performance in those cases where performing overt VSA is not possible.

The role of distinct ECoG frequency features in decoding finger movement.

Objective.To identify the electrocorticography (ECoG) frequency features that encode distinct finger movement states during repeated finger flexions.Approach.We used the publicly available Stanford ECoG dataset of cue-based, repeated single finger flexions. Using linear regression, we identified the spectral features that contributed most to the encoding of movement dynamics and discriminating movement events from rest, and combined them to predict finger movement trajectories. Furthermore, we also looked into the effect of the used frequency range and the spatial distribution of the identified features.Main results.Two frequency features generate superior performance, each one for a different movement aspect: high gamma band activity distinguishes movement events from rest, whereas the local motor potential (LMP) codes for movement dynamics. Combining these two features in a finger movement decoder outperformed comparable prior work where the entire spectrum was used as the average correlation coefficient with the true trajectories increased from 0.45 to 0.5, both applied to the Stanford dataset, and erroneous predictions during rest were demoted. In addition, for the first time, our results show the influence of the upper cut-off frequency used to extract LMP, yielding a higher performance when this range is adjusted to the finger movement rate.Significance.This study shows the benefit of a detailed feature analysis prior to designing the finger movement decoder.

Source space reduction for eLORETA.

Objective.We introduce Sparse exact low resolution electromagnetic tomography (eLORETA), a novel method for estimating a nonparametric solution to the source localization problem. Its goal is to generate a sparser solution compared to other source localization methods including eLORETA while benefitting from the latter's superior source localization accuracy.Approach.Sparse eLORETA starts by reducing the source space of the Lead Field Matrix using structured sparse Bayesian learning from which a Reduced Lead Field Matrix is constructed, which is used as input to eLORETA.Main results.With Sparse eLORETA, source sparsity can be traded against signal fidelity; the proposed optimum is shown to yield a much sparser solution than eLORETA's with only a slight loss in signal fidelity.Significance.When pursuing a data-driven approach, for cases where it is difficult to choose specific regions of interest, or when subsequently a connectivity analysis is performed, source space reduction could prove beneficial.

Single-paradigm and hybrid brain computing interfaces and their use by disabled patients.

Brain computer interfacing (BCI) has enjoyed increasing interest not only from research communities such as engineering and neuroscience but also from visionaries that predict it will change the way we will interact with technology. Since BCIs establish an alternative communication channel between the brain and the outside world, they have been hailed to provide solutions for patients suffering from severe motor- and/or communication disabilities such as fully paralyzed locked-in syndrome patients. However, despite single-case successes, which sometimes reach a broad audience, BCIs are actually not routinely used to support patients in their daily life activities. This review focusses on non-invasive BCIs, introduces the main paradigms and applications, and shows how the technology has improved over recent years. We identify patient groups that potentially can benefit from BCIs by referring to disability levels and etiology. We list the requirements, indicate how BCIs can tap into their spared competences, and discuss performance issues also in view of other assistive communication technologies. We discuss hybrid BCIs, a more recent development that combines paradigms and signals, possibly also of non-brain origin, to increase performance in terms of accuracy and/or communication speed, also as a way to counter the low performance with a given paradigm by involving another, more suitable one (BCI illiteracy). Finally, we list a few hybrid BCI solutions for patients and note that demonstrations with the ones based entirely on brain activity are still scarce.

Discrimination of three basic male voice types by voice range profile-derived parameters.

AIMS: To assess whether individual voice range profile parameters or combinations of these are able to yield a clear cluster separation of male voices. METHODS: The voice range profiles of 256 male conservatory singing students and professional singers were recorded, parameterized into more compact descriptions ('features'), and subjected to a cluster analysis. RESULTS: Based on all parameters the frequency dip of the register transition zone was shown to yield the best cluster separation for three basic male voice types. CONCLUSIONS: This study demonstrates that parameter combinations of the voice range profile exist that generate a clear separation of voice clusters. This was also the case with female voices as shown in a former study. The clusters may be attributed to the three classic basic male voice types, and in this way our results can provide a fresh angle on the issue of male voice classification.

Discrimination of three basic female voice types in female singing students by voice range profile-derived parameters.

AIMS: To assess whether individual parameters or combinations of voice range profile parameters (also called 'features') are able to yield a clear cluster separation with which three basic female voice categories can be discriminated and can provide a basis for settling the issue of voice classification. METHODS: The voice range profiles of 206 female conservatory singing students were recorded, parameterized into more compact descriptions ('features'), and subjected to a cluster analysis. RESULTS: The three-cluster case provided the most consistent solution across all feature combinations. The feature that led to the best cluster separation was the ratio of the perimeter length of the chest voice part of the voice range profile versus the total perimeter length. CONCLUSIONS: Based on a statistical analysis of voice range profile parameters, the ratio of the perimeter length of the chest voice versus the total perimeter length was shown to yield a clear separation into three basic female voice types, which in turn may give us a basis for settling the issue of voice classification.

Function of center-surround antagonism for motion in visual area MT/V5: a modeling study.

Neurons in cortical area MT or V5 of primates have a large, modulatory region surrounding the classical receptive field. This 'surround' has been suggested to be involved in motion segmentation, as well as in shape-from-motion processing. Our hypothesis is that it plays a functional role in both. We verify this by modeling the electrophysiological data obtained by Orban and co-workers in the macaque, and by developing a novel stimulus paradigm. Our results indicate an almost perfect dichotomy between both functionalities: our model neurons code for the object's edge if present, and for the first-order shape otherwise. We further show that small populations of model neurons can code linearly for the orientation-in-depth of translating planes.

Encoding of categories by noncategory-specific neurons in the inferior temporal cortex.

In order to understand how the brain codes natural categories, e.g., trees and fish, recordings were made in the anterior part of the macaque inferior temporal (IT) cortex while the animal was performing a tree/nontree categorization task. Most single cells responded to exemplars of more than one category while other neurons responded only to a restricted set of exemplars of a given category. Since it is still not known which type of cells contribute and what is the nature of the code used for categorization in IT, we have performed an analysis on single-cell data. A Kohonen self-organizing map (SOM), which uses an unsupervised (competitive) learning algorithm, was used to study the single cell responses to tree and nontree images. Results from the Kohonen SOM indicated that the collected neuronal data consisting of spike counts was sufficient to account for a good level of categorization success (approximately 83%) when categorizing a group of 200 trees and nontrees. Contrary to intuition, the results of the investigation suggest that the population of category-specific neurons (neurons that respond only to trees or only to nontrees) was unimportant to the categorization. Instead, a large majority of the neurons that were most important to the categorization was found to belong to a class of more broadly tuned cells, namely, cells that responded to both categories but that favored one category over the other by seven or more images. A simple algebraic operation (without the Kohonen SOM) between the above-mentioned noncategory-specific neurons confirmed the contribution of these neurons to categorization. Thus, the modeling results suggest (1) that broadly tuned neurons are critical for categorization, and (2) that only one additional layer of processing is required to extract the categories from a population of IT neurons.

Faithful representations with topographic maps.

Topographic map algorithms that are aimed at building "faithful representations" also yield maps that transfer the maximum amount of information available about the distribution from which they receive input. The weight density (magnification factor) of these maps is proportional to the input density, or the neurons of these maps have an equal probability to be active (equiprobabilistic map). As MSE minimization is not compatible with equiprobabilistic map formation in general, a number of heuristics have been devised in order to compensate for this discrepancy in competitive learning schemes, e.g. by adding a "conscience" to the neurons' firing behavior. However, rather than minimizing a modified MSE criterion, we introduce a new unsupervised competitive learning rule, called the kernel-based Maximum Entropy learning Rule (kMER), for topographic map formation, that optimizes an information-theoretic criterion directly. To each neuron a radially symmetric kernel is associated, with a given center and radius, and the two are updated in such a way that the (unconditional) information-theoretic entropy of the neurons' outputs is maximized. We review a number of competitive learning rules for building equiprobabilistic maps. As benchmark tests for the faithfulness of the representations, we consider two types of distributions and compare the performances of these rules and kMER, for batch and incremental learning. As a first example application, we consider non-parametric density estimation where the maps are used for generating "pilot" estimates in kernel-based density estimation. The second application we envisage for kMER is "on-line" adaptive filtering of speech signals, using Gabor functions as wavelet filters. The topographic feature maps that are developed in this way differ in several respects from those obtained with Kohonen's Adaptive-Subspace SOM algorithm.

Density-based clustering with topographic maps.

A new unsupervised competitive learning rule is introduced, called the kernel-based Maximum Entropy learning Rule (kMER), for equiprobabilistic topographic map formation. The application envisaged is density-based clustering. An empirical study is conducted to compare the clustering performance of kMER with that of a number of other unsupervised competitive learning rules.

Modeling the surround of MT cells and their selectivity for surface orientation in depth specified by motion.

The projective transformation onto the retina loses the explicit 3D shape description of a moving object. Theoretical studies show that the reconstruction of 3D shape from 2D motion information (shape from motion, SFM) is feasible provided that the first- and second-order directional derivatives of the 2D velocity field are available. Experimental recordings have revealed that the receptive fields of the majority of the cells in macaque area middle temporal (MT) display an antagonistic (suppressive) surround and that a sizable portion of these surrounds are asymmetrical. This has led to the conjecture that these cells provide a local measure for the directional derivatives of the 2D velocity field. In this article, we adopt a nonparametric and biologically plausible approach to modeling the role played by the MT surrounds in the recovery of the orientation in depth (the slant and tilt) of a moving (translating) plane. A three-layered neural network is trained to represent the slant and tilt from the projected motion vectors. The hidden units of the network have speed-tuning characteristics and represent the MT model neurons with their surrounds. We conjecture that the MT surround results from lateral inhibitory connections with other MT cells and that populations of these cells, with different surround types, code linearly for slant and tilt of translating planes.

Size and shape of receptive fields in the medial superior temporal area (MST) of the macaque.

Ninety-one single units were recorded in area MSTd of anesthetized and paralyzed macaques. Receptive fields (RFs) were mapped quantitatively using small patches of moving random dots in 25 different positions (the two-dimensional position test, or P2D). The dimensions of the receptive fields (RFs) were estimated by fitting P2D data with a generalized Gaussian function. The half-height areas of the RFs in MSTd were found to average 1085 deg2 and were not dependent upon eccentricity, in contrast to those in MT/V5 (n = 295) which averaged 31 deg2 at the fovea but at the periphery approached the RFs of MSTd in size. The RFs of some MSTd neurons extended 30-40 degrees into the ipsilateral hemifield. In comparison, the overlap was only 10-15 degrees in area MT/V5.

Topographic map formation by maximizing unconditional entropy: a plausible strategy for "online" unsupervised competitive learning and nonparametric density estimation.

An unsupervised competitive learning rule, called the vectorial boundary adaptation rule (VBAR), is introduced for topographic map formation. Since VBAR is aimed at producing an equiprobable quantization of the input space, it yields a nonparametric model of the input probability density function. Furthermore, since equiprobable quantization is equivalent to unconditional entropy maximization, we argue that this is a plausible strategy for maximizing mutual information (Shannon information rate) in the case of "online" learning. We use mutual information as a tool for comparing the performance of our rule with Kohonen's self-organizing (feature) map algorithm.

Shape and spatial distribution of receptive fields and antagonistic motion surrounds in the middle temporal area (V5) of the macaque.

The spatial organization of receptive fields in the middle temporal (MT) area of anaesthetized and paralysed macaque monkeys was studied. In all, 288 neurons were successfully recorded. The size and shape of the receptive field (RF) was mapped with small patches of translating random dots and the resulting data were fitted with a generalized Gaussian. Results show that the RF area increases with eccentricity, and is larger in lamina 5 than in other layers. Most of these RFs are elongated, and the axis of elongation tends to be orthogonal to the preferred direction of motion. The direction selectivity is maintained in all positions in the RF, but layer 5 cells are less direction-selective than cells in other layers. In a second series of experiments, radial dimensions of the classical RF and the antagonistic surround were estimated from area summation tests. These data were fitted with the difference of the integrals of two Gaussians. Surrounds were weakest in layer 4 and strongest in layer 2. Optimal stimulus diameters, also estimated from the area summation curve, were larger in the infragranular layers than in the other layers. The maximum sensitivity of the surround was clearly displaced from the classical RF (CRF) centre, indicating that the surround is not concentric with the CRF. This radial offset and the extent of the surround were largest in layers 2 and 5 and smallest in 3a. The extent of the surround half-height equalled, on average, 3-4 times that of the CRF. These results suggest that antagonistic surrounds are constructed in MT, probably through horizontal connections, and that a strong vertical organization exists in area MT, as has been shown for V1.

On a novel unsupervised competitive learning algorithm for scalar quantization.

This letter presents a novel unsupervised competitive learning rule called the boundary adaptation rule (BAR), for scalar quantization. It is shown both mathematically and by simulations that BAR converges to equiprobable quantizations of univariate probability density functions and that, in this way, it outperforms other unsupervised competitive learning rules.