Showing papers by "Klaus-Robert Müller published in 2005"

Spatio-spectral filters for improving the classification of single trial EEG

Abstract: Data recorded in electroencephalogram (EEG)-based brain-computer interface experiments is generally very noisy, nonstationary, and contaminated with artifacts that can deteriorate discrimination/classification methods. In this paper, we extend the common spatial pattern (CSP) algorithm with the aim to alleviate these adverse effects. In particular, we suggest an extension of CSP to the state space, which utilizes the method of time delay embedding. As we will show, this allows for individually tuned frequency filters at each electrode position and, thus, yields an improved and more robust machine learning procedure. The advantages of the proposed method over the original CSP method are verified in terms of an improved information transfer rate (bits per trial) on a set of EEG-recordings from experiments of imagined limb movements.

Input-Dependent Estimation of Generalization Error under Covariate Shift

Abstract: A common assumption in supervised learning is that the training and test input points follow the same probability distribution. However, this assumption is not fulfilled, e.g., in interpolation, extrapolation, active learning, or classification with imbalanced data. The violation of this assumption—known as the covariate shift— causes a heavy bias in standard generalization error estimation schemes such as cross-validation or Akaike’s information criterion, and thus they result in poor model selection. In this paper, we propose an alternative estimator of the generalization error for the squared loss function when training and test distributions are different. The proposed generalization error estimator is shown to be exactly unbiased for finite samples if the learning target function is realizable and asymptotically unbiased in general. We also show that, in addition to the unbiasedness, the proposed generalization error estimator can accurately estimate the difference of the generalization error among different models, which is a desirable property in model selection. Numerical studies show that the proposed method compares favorably with existing model selection methods in regression for extrapolation and in classification with imbalanced data.

Sensor system and methods for the capacitive measurement of electromagnetic signals having a biological origin

Abstract: The invention relates to a sensor system and several method for the capacitive measurement of electromagnetic signals having a biological origin. Such a sensor system comprises a capacitive electrode device (10), an electrode shielding element (20) which surrounds the electrode device (10) at least in part in order to shield the same (10) from interfering external electromagnetic fields, and a signal processing device (30) for processing electromagnetic signals that can be detected by means of the electrode device (10). According to the invention, additional shielding means (21) three-dimensionally surround the electrode device (10) and the electrode shielding element (20) at least in part in order to block out interfering external electromagnetic fields. The changes in the electrode capacity of the capacitive sensor system are determined with the aid of several methods which particularly use the inventive sensor system in order to take said changes into account when the test signals are evaluated.

Improving the Caenorhabditis elegans Genome Annotation Using Machine Learning

Abstract: For modern biology, precise genome annotations are of prime importance, as they allow the accurate definition of genic regions. We employ state-of-the-art machine learning methods to assay and improve the accuracy of the genome annotation of the nematode Caenorhabditis elegans. The proposed machine learning system is trained to recognize exons and introns on the unspliced mRNA, utilizing recent advances in support vector machines and label sequence learning. In 87% (coding and untranslated regions) and 95% (coding regions only) of all genes tested in several out-of-sample evaluations, our method correctly identified all exons and introns. Notably, only 37% and 50%, respectively, of the presently unconfirmed genes in the C. elegans genome annotation agree with our predictions, thus we hypothesize that a sizable fraction of those genes are not correctly annotated. A retrospective evaluation of the Wormbase WS120 annotation [1] of C. elegans reveals that splice form predictions on unconfirmed genes in WS120 are inaccurate in about 18% of the considered cases, while our predictions deviate from the truth only in 10%–13%. We experimentally analyzed 20 controversial genes on which our system and the annotation disagree, confirming the superiority of our predictions. While our method correctly predicted 75% of those cases, the standard annotation was never completely correct. The accuracy of our system is further corroborated by a comparison with two other recently proposed systems that can be used for splice form prediction: SNAP and ExonHunter. We conclude that the genome annotation of C. elegans and other organisms can be greatly enhanced using modern machine learning technology.

Classifying 'drug-likeness' with kernel-based learning methods.

Abstract: In this article we report about a successful application of modern machine learning technology, namely Support Vector Machines, to the problem of assessing the ‘drug-likeness' of a chemical from a given set of descriptors of the substance. We were able to drastically improve the recent result by Byvatov et al. (2003) on this task and achieved an error rate of about 7% on unseen compounds using Support Vector Machines. We see a very high potential of such machine learning techniques for a variety of computational chemistry problems that occur in the drug discovery and drug design process.

Predictive compression of dynamic 3D meshes

Abstract: An efficient algorithm for compression of dynamic time-consistent 3D meshes is presented. Such a sequence of meshes contains a large degree of temporal statistical dependencies that can be exploited for compression using DPCM. The vertex positions are predicted at the encoder from a previously decoded mesh. The difference vectors are further clustered in an octree approach. Only a representative for a cluster of difference vectors is further processed providing a significant reduction of data rate. The representatives are scaled and quantized and finally entropy coded using CABAC, the arithmetic coding technique used in H.264/MPEG4-AVC. The mesh is then reconstructed at the encoder for prediction of the next mesh. In our experiments we compare the efficiency of the proposed algorithm in terms of bit-rate and quality compared to static mesh coding and interpolator compression indicating a significant improvement in compression efficiency.

Optimizing spatio-temporal filters for improving Brain-Computer Interfacing

Abstract: Brain-Computer Interface (BCI) systems create a novel communication channel from the brain to an output device by bypassing conventional motor output pathways of nerves and muscles. Therefore they could provide a new communication and control option for paralyzed patients. Modern BCI technology is essentially based on techniques for the classification of single-trial brain signals. Here we present a novel technique that allows the simultaneous optimization of a spatial and a spectral filter enhancing discriminability of multi-channel EEG single-trials. The evaluation of 60 experiments involving 22 different subjects demonstrates the superiority of the proposed algorithm. Apart from the enhanced classification, the spatial and/or the spectral filter that are determined by the algorithm can also be used for further analysis of the data, e.g., for source localization of the respective brain rhythms.

Measuring phase synchronization of superimposed signals.

Abstract: (Received 7 September 2004; published 3 March 2005)Phase synchronization is an important phenomenon that occurs in a wide variety of complex oscillatoryprocesses. Measuring phase synchronization can therefore help to gain fundamental insight into nature. Inthis Letter we point out that synchronization analysis techniques can detect spurious synchronization, ifthey are fed with a superposition of signals such as in electroencephalography or magnetoencephalog-raphy data. We show how techniques from blind source separation can help to nevertheless measure thetrue synchronization and avoid such pitfalls.

3-D reconstruction of a dynamic environment with a fully calibrated background for traffic scenes

Abstract: Vision-based traffic surveillance systems are more and more employed for traffic monitoring, collection of statistical data and traffic control. We present an extension of such a system that additionally uses the captured image content for 3-D scene modeling and reconstruction. A basic goal of surveillance systems is to get a good coverage of the observed area with as few cameras as possible to keep the costs low. Therefore, the 3-D reconstruction has to be done from only a few original views with limited overlap and different lighting conditions. To cope with these specific restrictions we developed a model-based 3-D reconstruction scheme that exploits a priori knowledge about the scene. The system is fully calibrated offline by estimating camera parameters from measured 3-D-2-D correspondences. Then the scene is divided into static parts, which are modeled offline and dynamic parts, which are processed online. Therefore, we segment all views into moving objects and static background. The background is modeled as multitexture planes using the original camera textures. Moving objects are segmented and tracked in each view. All segmented views of a moving object are combined to a 3-D object, which is positioned and tracked in 3-D. Here we use predefined geometric primitives and map the original textures onto them. Finally the static and dynamic elements are combined to create the reconstructed 3-D scene, where the user can freely navigate, i.e., choose an arbitrary viewpoint and direction. Additionally, the system allows analyzing the 3-D properties of the scene and the moving objects.

Visualization of anomaly detection using prediction sensitivity

Abstract: Visualization of learning-based intrusion detection methods is a challenging problem. In this paper we propose a novel method for visualization of anomaly detection and feature selection, based on prediction sensitivity. The method allows an expert to discover informative features for separation of normal and attack instances. Experiments performed on the KDD Cup dataset show that explanations provided by prediction sensitivity reveal the nature of attacks. Application of prediction sensitivity for feature selection yields a major improvement of detection accuracy.

Model selection under covariate shift

Abstract: A common assumption in supervised learning is that the training and test input points follow the same probability distribution. However, this assumption is not fulfilled, e.g., in interpolation, extrapolation, or active learning scenarios. The violation of this assumption-- known as the covariate shift--causes a heavy bias in standard generalization error estimation schemes such as cross-validation and thus they result in poor model selection. In this paper, we therefore propose an alternative estimator of the generalization error. Under covariate shift, the proposed generalization error estimator is unbiased if the learning target function is included in the model at hand and it is asymptotically unbiased in general. Experimental results show that model selection with the proposed generalization error estimator is compared favorably to crossvalidation in extrapolation.

Estimating Functions for Blind Separation When Sources Have Variance Dependencies

Abstract: A blind separation problem where the sources are not independent, but have variance dependencies is discussed. For this scenario Hyvarinen and Hurri (2004) proposed an algorithm which requires no assumption on distributions of sources and no parametric model of dependencies between components. In this paper, we extend the semiparametric approach of Amari and Cardoso (1997) to variance dependencies and study estimating functions for blind separation of such dependent sources. In particular, we show that many ICA algorithms are applicable to the variance-dependent model as well under mild conditions, although they should in principle not. Our results indicate that separation can be done based only on normalized sources which are adjusted to have stationary variances and is not affected by the dependent activity levels. We also study the asymptotic distribution of the quasi maximum likelihood method and the stability of the natural gradient learning in detail. Simulation results of artificial and realistic examples match well with our theoretical findings.

Generalization Error Estimation under Covariate Shift

Abstract: In supervised learning, it is almost always assumed that the training and test input points follow the same probability distribution. However, this assumption is violated, e.g., in interpolation, extrapolation, active learning, or classification with imbalanced data. In such situations—known as the covariate shift, cross-validation estimate of the general- ization error is biased, which results in poor model selection. In this paper, we propose an alternative estimator of the generalization error which is under the covariate shift exactly unbiased if model includes the learning target function and is asymptotically unbiased in general. We also show that, in addition to the unbiasedness, the proposed generalization error estimator can accurately estimate the dierence of the generalization error among dierent models, which is a desirable property in model selection. Numerical studies show that the proposed method compares favorably with cross-validation.

Automatic Identification of Faked and Fraudulent Interviews in the German SOEP

Abstract: Based on data from the German Socio-Economic Panel (SOEP), this paper presents two new tools for the identification of faked interviews in surveys. One method is based on Benford's Law, and the other exploits the empirical observation that fakers most often produce answers with less variability than could be expected from the whole survey. We focus on fabricated data, which was taken out of the survey before the data was disseminated to external users. For two samples, the resulting rankings of the interviewers with respect to their cheating behavior are given. For both methods all of the evident fakers are identified.

The Berlin Brain-Computer Interface: Report from the Feedback Sessions

Abstract: Brain-Computer Interface (BCI) systems establish a direct communication channel from the brain to an output device. These systems use brain signals recorded from the scalp, the surface of the cortex, or from inside the brain to enable users to control a vari ety of applications. BCI systems that bypass conventional motor output pathways of nerves and muscles can provide novel control options for paralyzed patients. The classical approach to establis h EEG-based control is to set up a system that is controlled by a specific EEG feature which is known to b e susceptible to conditioning and to let the subjects learn the voluntary control of that feature. In contrast, the Berlin Brain-Computer Interface (BBCI) uses well established motor competences in control paradigms and a machine learning approach to extract subject-specific discriminability pat terns from high-dimensional features. Thus the long subject training is replaced by a short calibration measurement (20 minutes) and machine training (1 minute). We report results from a study with six s ubjects who had no or little experience with BCI feedback. The experiment encompassed three kinds of feedback that were all controlled by voluntary brain signals, independent from peripheral nerv ous system activity and without resorting to evoked potentials. Two of the feedback protocols were asynchronous and one was synchronous (i.e., commands can only be emitted synchronously with an external pace). The information transfer rate in the best session was above 35 bits per minute (bpm) for 3 subjects, above 24 and 15 bpm for further two subjects, while one subject could achieve no BCI control. Compared to other BCI systems which need longer subject training to achieve comparable results we believe that the key to success in the BBCI system is its flexibility due to complex fe atures and its adaptivity which respects the enormous inter-subject variability.

Non-Gaussian Component Analysis: a Semi-parametric Framework for Linear Dimension Reduction

Abstract: We propose a new linear method for dimension reduction to identify non-Gaussian components in high dimensional data. Our method, NGCA (non-Gaussian component analysis), uses a very general semi-parametric framework. In contrast to existing projection methods we define what is uninteresting (Gaussian): by projecting out uninterestingness, we can estimate the relevant non-Gaussian subspace. We show that the estimation error of finding the non-Gaussian components tends to zero at a parametric rate. Once NGCA components are identified and extracted, various tasks can be applied in the data analysis process, like data visualization, clustering, denoising or classification. A numerical study demonstrates the usefulness of our method.

3D video objects for interactive applications

Abstract: In this paper we present a 3D scene representation with standardized components to be used in interactive applications. For this representation we also show efficient coding of 3D geometry and textures as well as a 3D reconstruction system for creating 3D video objects (3DVOs). Similar to computer graphics objects, 3DVOs provide functionalities, like free scene navigation and animation. In contrast, they describe real world appearance and natural motion. The presented object description combines a 3D mesh model with a number of original video textures. These videos are weighted in the final object rendering according to the particular point of view. For coding the object meshes over time, we present a novel algorithm that exploits spatial and temporal dependencies in the mesh sequence and outperforms comparable coding methods. For the multi-texture coding, we preprocessed the video textures w.r.t. their shapes and applied H.264/AVC, the MPEG-4 state-of-the-art video coder.

Inlier-based ICA with an application to superimposed images

Abstract: This paper proposes a new independent component analysis (ICA) method which is able to unmix overcomplete mixtures of sparce or structured signals like speech, music or images. Furthermore, the method is designed to be robust against outliers, which is a favorable feature for ICA algorithms since most of them are extremely sensitive to outliers. Our approach is based on a simple outlier index. However, instead of robustifying an existing algorithm by some outlier rejection technique we show how this index can be used directly to solve the ICA problem for super-Gaussian sources. The resulting inlier-based ICA (IBICA) is outlier-robust by construction and can be used for standard ICA as well as for overcomplete ICA (i.e. more source signals than observed signals). (c) 2005 Wiley Periodicals, Inc

Analyzing Coupled Brain Sources: Distinguishing True from Spurious Interaction

Abstract: When trying to understand the brain, it is of fundamental importance to analyse (e.g. from EEG/MEG measurements) what parts of the cortex interact with each other in order to infer more accurate models of brain activity. Common techniques like Blind Source Separation (BSS) can estimate brain sources and single out artifacts by using the underlying assumption of source signal independence. However, physiologically interesting brain sources typically interact, so BSS will—by construction— fail to characterize them properly. Noting that there are truly interacting sources and signals that only seemingly interact due to effects of volume conduction, this work aims to contribute by distinguishing these effects. For this a new BSS technique is proposed that uses anti-symmetrized cross-correlation matrices and subsequent diagonalization. The resulting decomposition consists of the truly interacting brain sources and suppresses any spurious interaction stemming from volume conduction. Our new concept of interacting source analysis (ISA) is successfully demonstrated on MEG data.

Method and device for detection of splice form and alternative splice forms in dna or rna sequences

Abstract: The invention relates to a method and a device for detection of splice sites in DNA or RNA sequences comprising three steps: a) Examining a training set of sequences comprising DNA or RNA sequences with known splice sites by an automated, discriminative training device for detecting splicing patterns, especially in a predetermined window around the known splice sites; b) Scanning a sequence comprising DNA or RNA sequences containing unknown splice sites for the occurrence of the splicing patterns detected in step a); and c) Calculation of a cumulative splice score in dependence of a maximisation of the margin between the true splice forms and all wrong splice forms in the sequence. The invention also relates to a method and a device for detection of splice forms and alternative splice forms in DNA or RNA sequences.

Methods for reducing influences resulting from movement artefacts of a sensor system comprising a capacitive electrode

Abstract: The invention relates to a sensor system and several method for the capacitive measurement of electromagnetic signals having a biological origin. Such a sensor system comprises a capacitive electrode device (10), an electrode shielding element (20) which surrounds the electrode device (10) at least in part in order to shield the same (10) from interfering external electromagnetic fields, and a signal processing device (30) for processing electromagnetic signals that can be detected by means of the electrode device (10). According to the invention, additional shielding means (21) three-dimensionally surround the electrode device (10) and the electrode shielding element (20) at least in part in order to block out interfering external electromagnetic fields. The changes in the electrode capacity of the capacitive sensor system are determined with the aid of several methods which particularly use the inventive sensor system in order to take said changes into account when the test signals are evaluated.