Showing papers by "Klaus-Robert Müller published in 2011"

3-D Video Representation Using Depth Maps

Abstract: Current 3-D video (3DV) technology is based on stereo systems. These systems use stereo video coding for pictures delivered by two input cameras. Typically, such stereo systems only reproduce these two camera views at the receiver and stereoscopic displays for multiple viewers require wearing special 3-D glasses. On the other hand, emerging autostereoscopic multiview displays emit a large numbers of views to enable 3-D viewing for multiple users without requiring 3-D glasses. For representing a large number of views, a multiview extension of stereo video coding is used, typically requiring a bit rate that is proportional to the number of views. However, since the quality improvement of multiview displays will be governed by an increase of emitted views, a format is needed that allows the generation of arbitrary numbers of views with the transmission bit rate being constant. Such a format is the combination of video signals and associated depth maps. The depth maps provide disparities associated with every sample of the video signal that can be used to render arbitrary numbers of additional views via view synthesis. This paper describes efficient coding methods for video and depth data. For the generation of views, synthesis methods are presented, which mitigate errors from depth estimation and coding.

Toward Unsupervised Adaptation of LDA for Brain–Computer Interfaces

Abstract: There is a step of significant difficulty experienced by brain-computer interface (BCI) users when going from the calibration recording to the feedback application. This effect has been previously studied and a supervised adaptation solution has been proposed. In this paper, we suggest a simple unsupervised adaptation method of the linear discriminant analysis (LDA) classifier that effectively solves this problem by counteracting the harmful effect of nonclass-related nonstationarities in electroencephalography (EEG) during BCI sessions performed with motor imagery tasks. For this, we first introduce three types of adaptation procedures and investigate them in an offline study with 19 datasets. Then, we select one of the proposed methods and analyze it further. The chosen classifier is offline tested in data from 80 healthy users and four high spinal cord injury patients. Finally, for the first time in BCI literature, we apply this unsupervised classifier in online experiments. Additionally, we show that its performance is significantly better than the state-of-the-art supervised approach.

Depth Image-Based Rendering With Advanced Texture Synthesis for 3-D Video

Abstract: A depth image-based rendering (DIBR) approach with advanced inpainting methods is presented. The DIBR algorithm can be used in 3-D video applications to synthesize a number of different perspectives of the same scene, e.g., from a multiview-video-plus-depth (MVD) representation. This MVD format consists of video and depth sequences for a limited number of original camera views of the same natural scene. Here, DIBR methods allow the computation of additional new views. An inherent problem of the view synthesis concept is the fact that image information which is occluded in the original views may become visible, especially in extrapolated views beyond the viewing range of the original cameras. The presented algorithm synthesizes these occluded textures. The synthesizer achieves visually satisfying results by taking spatial and temporal consistency measures into account. Detailed experiments show significant objective and subjective gains of the proposed method in comparison to the state-of-the-art methods.

Co-adaptive calibration to improve BCI efficiency.

Abstract: All brain–computer interface (BCI) groups that have published results of studies involving a large number of users performing BCI control based on the voluntary modulation of sensorimotor rhythms (SMR) report that BCI control could not be achieved by a non-negligible number of subjects (estimated 20% to 25%). This failure of the BCI system to read the intention of the user is one of the greatest problems and challenges in BCI research. There are two main causes for this problem in SMR-based BCI systems: either no idle SMR is observed over motor areas of the user, or this idle rhythm is not modulated during motor imagery, resulting in a classification performance lower than 70% (criterion level) that renders the control of a BCI application (like a speller) difficult or impossible. Previously, we introduced the concept of machine learning based co-adaptive calibration, which provided substantially improved performance for a variety of users. Here, we use a similar approach and investigate to what extent co-adaptive learning enables significant BCI control for completely novice users, as well as for those who could not achieve control with a conventional SMR-based BCI.

Analysis of Multimodal Neuroimaging Data

Abstract: Each method for imaging brain activity has technical or physiological limits. Thus, combinations of neuroimaging modalities that can alleviate these limitations such as simultaneous recordings of neurophysiological and hemodynamic activity have become increasingly popular. Multimodal imaging setups can take advantage of complementary views on neural activity and enhance our understanding about how neural information processing is reflected in each modality. However, dedicated analysis methods are needed to exploit the potential of multimodal methods. Many solutions to this data integration problem have been proposed, which often renders both comparisons of results and the choice of the right method for the data at hand difficult. In this review we will discuss different multimodal neuroimaging setups, the advances achieved in basic research and clinical application and the methods used. We will provide a comprehensive overview of mathematical tools reoccurring in multimodal neuroimaging studies for artifact removal, data-driven and model-driven analyses, enabling the practitioner to try established or new combinations from these algorithmic building blocks.

Kernel Analysis of Deep Networks

Abstract: When training deep networks it is common knowledge that an efficient and well generalizing representation of the problem is formed. In this paper we aim to elucidate what makes the emerging representation successful. We analyze the layer-wise evolution of the representation in a deep network by building a sequence of deeper and deeper kernels that subsume the mapping performed by more and more layers of the deep network and measuring how these increasingly complex kernels fit the learning problem. We observe that deep networks create increasingly better representations of the learning problem and that the structure of the deep network controls how fast the representation of the task is formed layer after layer.

Visual Interpretation of Kernel-Based Prediction Models.

Abstract: Statistical models are frequently used to estimate molecular properties, e.g., to establish quantitative structure-activity and structure-property relationships. For such models, interpretability, knowledge of the domain of applicability, and an estimate of confidence in the predictions are essential. We develop and validate a method for the interpretation of kernel-based prediction models. As a consequence of interpretability, the method helps to assess the domain of applicability of a model, to judge the reliability of a prediction, and to determine relevant molecular features. Increased interpretability also facilitates the acceptance of such models. Our method is based on visualization: For each prediction, the most contributing training samples are computed and visualized. We quantitatively show the effectiveness of our approach by conducting a questionnaire study with 71 participants, resulting in significant improvements of the participants' ability to distinguish between correct and incorrect predictions of a Gaussian process model for Ames mutagenicity.

CSP patches: an ensemble of optimized spatial filters. An evaluation study.

Abstract: Laplacian filters are widely used in neuroscience. In the context of brain-computer interfacing, they might be preferred to data-driven approaches such as common spatial patterns (CSP) in a variety of scenarios such as, e.g., when no or few user data are available or a calibration session with a multi-channel recording is not possible, which is the case in various applications. In this paper we propose the use of an ensemble of local CSP patches (CSPP) which can be considered as a compromise between Laplacian filters and CSP. Our CSPP only needs a very small number of trials to be optimized and significantly outperforms Laplacian filters in all settings studied. Additionally, CSPP also outperforms multi-channel CSP and a regularized version of CSP even when only very few calibration data are available, acting as a CSP regularizer without the need of additional hyperparameters and at a very low cost: 2-5 min of data recording, i.e. ten times less than CSP.

StructRank: a new approach for ligand-based virtual screening.

Abstract: Screening large libraries of chemical compounds against a biological target, typically a receptor or an enzyme, is a crucial step in the process of drug discovery. Virtual screening (VS) can be seen as a ranking problem which prefers as many actives as possible at the top of the ranking. As a standard, current Quantitative Structure−Activity Relationship (QSAR) models apply regression methods to predict the level of activity for each molecule and then sort them to establish the ranking. In this paper, we propose a top-k ranking algorithm (StructRank) based on Support Vector Machines to solve the early recognition problem directly. Empirically, we show that our ranking approach outperforms not only regression methods but another ranking approach recently proposed for QSAR ranking, RankSVM, in terms of actives found.

Revealing the neural response to imperceptible peripheral flicker with machine learning

Abstract: 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

The Stationary Subspace Analysis Toolbox

Abstract: The Stationary Subspace Analysis (SSA) algorithm linearly factorizes a high-dimensional time series into stationary and non-stationary components. The SSA Toolbox is a platform-independent efficient stand-alone implementation of the SSA algorithm with a graphical user interface written in Java, that can also be invoked from the command line and from Matlab. The graphical interface guides the user through the whole process; data can be imported and exported from comma separated values (CSV) and Matlab's .mat files.

Uniqueness of Non-Gaussianity-Based Dimension Reduction

Abstract: Dimension reduction is a key step in preprocessing large-scale data sets. A recently proposed method named non-Gaussian component analysis searches for a projection onto the non-Gaussian part of a given multivariate recording, which is a generalization of the deflationary projection pursuit model. In this contribution, we discuss the uniqueness of the subspaces of such a projection. We prove that a necessary and sufficient condition for uniqueness is that the non-Gaussian signal subspace is of minimal dimension. Furthermore, we propose a measure for estimating this minimal dimension and illustrate it by numerical simulations. Our result guarantees that projection algorithms uniquely recover the underlying lower dimensional data signals.

Editorial: Charting Chemical Space: Challenges and Opportunities for Artificial Intelligence and Machine Learning.

Abstract: In spite of its central role and position between physics and biology, chemistry has remained in a somewhat backward state of informatics development compared to its two close scientific relatives, primarily for historical reasons. Computers, open public databases, and large collaborative projects have become the pervasive hallmark of research in physics and biology, but are still at a comparably early stage of development in chemistry. Recently, however, data banks containing millions of small molecules have become freely available, and large repositories of chemical reactions have been developed. These data create a wealth of fascinating informatics and machine learning challenges to efficiently store, search, and predict the physical, chemical, and biological properties of small molecules and reactions and chart “chemical space”. Profound understanding of its structure and appropriate computational models will have significant scientific and technological impact.

l1-penalized linear mixed-effects models for BCI

Abstract: A recently proposed novel statistical model estimates population effects and individual variability between subgroups simultaneously, by extending Lasso methods. We apply this l1-penalized linear regression mixed-effects model to a large scale real world problem: by exploiting a large set of brain computer interface data we are able to obtain a subject-independent classifier that compares favorably with prior zero-training algorithms. This unifying model inherently compensates shifts in the input space attributed to the individuality of a subject. In particular we are now able to differentiate within-subject and between-subject variability. A deeper understanding both of the underlying statistical and physiological structure of the data is gained.

Directional Variance Adjustment: improving covariance estimates for high-dimensional portfolio optimization

Abstract: Robust and reliable covariance estimation plays a decisive role in nancial applications. An important class of estimators is based on Factor models. Here, we show by extensive Monte Carlo simulations that covariance matrices derived from the statistical Factor Analysis model exhibit a systematic error, which is similar to the well-known systematic error of the spectrum of the sample covariance matrix. Moreover, we introduce the Directional Variance Adjustment (DVA) algorithm, which diminishes the systematic error. In a thorough empirical study for the US, European, and Hong Kong market we evince that our proposed method leads to improved portfolio allocation.

Brain-Computer Interfaces and Visual Activity

Abstract: There is growing interest in the use of brain signals for communication and operation of devices – in particular, for physically disabled people. Brain states can be detected and translated into actions such as selecting a letter from a virtual keyboard, playing a video game, or moving a robot arm. This chap‐ ter presents what is known about the effects of visual stimuli on brain activity and introduces means of monitoring brain activity. Possibilities of brain‐controlled interfaces, either with the brain signals as the sole input or in combination with the measured point of gaze, are discussed.

Regression for sets of polynomial equations

Abstract: We propose a method called ideal regression for approximating an arbitrary system of polynomial equations by a system of a particular type. Using techniques from approximate computational algebraic geometry, we show how we can solve ideal regression directly without resorting to numerical optimization. Ideal regression is useful whenever the solution to a learning problem can be described by a system of polynomial equations. As an example, we demonstrate how to formulate Stationary Subspace Analysis (SSA), a source separation problem, in terms of ideal regression, which also yields a consistent estimator for SSA. We then compare this estimator in simulations with previous optimization-based approaches for SSA.

Pitfalls in EEG-based brain effective connectivity analysis

Abstract: We consider the problem of estimating brain effective connectivity from electroencephalographic (EEG) measurements, which is challenging due to instantaneous correlations in the sensor data caused by volume conduction in the head. We present selected results of a larger realistic simulation study in which we tested the ability of various measures of effective connectivity to recover the information flow between the underlying sources, as well as the ability of linear and nonlinear inverse source reconstruction approaches to improve the estimation. It turns out that factors related to volume conduction dramatically limit the neurophysiological interpretability of sensor-space connectivity maps and may even (depending on the connectivity measure used) lead to conflicting results. The success of connectivity estimation on inverse source estimates crucially depends on the correctness of the source demixing. This in turn depends on the capability of the method to model (multiple) interacting sources, which is in general not achievable by linear inverses.

A new scatter-based multi-class support vector machine

Abstract: We provide a novel interpretation of the dual of support vector machines (SVMs) in terms of scatter with respect to class prototypes and their mean. As a key contribution, we extend this framework to multiple classes, providing a new joint Scatter SVM algorithm, at the level of its binary counterpart in the number of optimization variables. We identify the associated primal problem and develop a fast chunking-based optimizer. Promising results are reported, also compared to the state-of-the-art, at lower computational complexity.

Non-separable spatiotemporal brain hemodynamics contain neural information

Abstract: The goal of many functional Magnetic Resonance Imaging (fMRI) studies is to infer neural activity from hemodynamic signals. Classical fMRI analysis approaches assume a canonical hemodynamic response function (HRF), which is identical in every voxel. Canonical HRFs imply space-time separability. Many studies explored the relevance of non-separable HRFs. These studies were focusing on the relationship between stimuli or electroencephalographic data and fMRI data. It is not clear from these studies whether non-separable spatiotemporal dynamics of fMRI signals contain neural information. This study provides direct empirical evidence that non-separable spatiotemporal deconvolutions of multivariate fMRI time series predict intracortical neural signals better than standard canonical HRF models. Our results demonstrate that there is more neural information in fMRI signals than detected by most analysis methods.

Slow Feature Analysis as a Potential Preprocessing Tool in BCI

Abstract: Here we present initial results of the unsupervised preprocessing method Slow Feature Analysis (SFA) for a BCI data set. It is the first time SFA is applied to EEG. SFA optimizes the signal representation with respect to temporal slowness. Its objective as well as its computational properties render it a possibly useful candidate for the preprocessing of BCI EEG data in order to detect task relevant components as well as components that represent artifacts or non-stationarities of the background brain activity or external sources.