Results 1  10
of
12
Denoising Source Separation
"... A new algorithmic framework called denoising source separation (DSS) is introduced. The main benefit of this framework is that it allows for easy development of new source separation algorithms which are optimised for specific problems. In this framework, source separation algorithms are constuct ..."
Abstract

Cited by 30 (6 self)
 Add to MetaCart
A new algorithmic framework called denoising source separation (DSS) is introduced. The main benefit of this framework is that it allows for easy development of new source separation algorithms which are optimised for specific problems. In this framework, source separation algorithms are constucted around denoising procedures. The resulting algorithms can range from almost blind to highly specialised source separation algorithms. Both simple linear and more complex nonlinear or adaptive denoising schemes are considered. Some existing independent component analysis algorithms are reinterpreted within DSS framework and new, robust blind source separation algorithms are suggested. Although DSS algorithms need not be explicitly based on objective functions, there is often an implicit objective function that is optimised. The exact relation between the denoising procedure and the objective function is derived and a useful approximation of the objective function is presented. In the experimental section, various DSS schemes are applied extensively to artificial data, to real magnetoencephalograms and to simulated CDMA mobile network signals. Finally, various extensions to the proposed DSS algorithms are considered. These include nonlinear observation mappings, hierarchical models and overcomplete, nonorthogonal feature spaces. With these extensions, DSS appears to have relevance to many existing models of neural information processing.
The inverse EEG and MEG problems: The adjoint state approach I: The continuous case
, 1999
"... In this report, we study the problem of the threedimensional reconstruction of the electrical activity of the brain from electroencephalography (EEG) and magnetoencephalography (MEG). We use a variational approach based upon three main methods and ideas. The first one is the optimal control of syst ..."
Abstract

Cited by 11 (0 self)
 Add to MetaCart
In this report, we study the problem of the threedimensional reconstruction of the electrical activity of the brain from electroencephalography (EEG) and magnetoencephalography (MEG). We use a variational approach based upon three main methods and ideas. The first one is the optimal control of systems governed by elliptic partial differential equations, the second is the regularization of the solutions while preserving the discontinuities (the edges), and the third one is the use of geometric information obtained from magnetic resonance images (MRI) to constrain the solutions in an anatomically "reasonable" way.
Overlearning in Marginal DistributionBased ICA: Analysis and Solutions. JMach Learn Res 2003
"... The present paper is written as a word of caution, with users of independent component analysis (ICA) in mind, to overlearning phenomena that are often observed. We consider two types of overlearning, typical to highorder statistics based ICA. These algorithms can be seen to maximise the negentropy ..."
Abstract

Cited by 10 (4 self)
 Add to MetaCart
The present paper is written as a word of caution, with users of independent component analysis (ICA) in mind, to overlearning phenomena that are often observed. We consider two types of overlearning, typical to highorder statistics based ICA. These algorithms can be seen to maximise the negentropy of the source estimates. The first kind of overlearning results in the generation of spikelike signals, if there are not enough samples in the data or there is a considerable amount of noise present. It is argued that, if the data has power spectrum characterised by 1 / f curve, we face a more severe problem, which cannot be solved inside the strict ICA model. This overlearning is better characterised by bumps instead of spikes. Both overlearning types are demonstrated in the case of artificial signals as well as magnetoencephalograms (MEG). Several methods are suggested to circumvent both types, either by making the estimation of the ICA model more robust or by including further modelling of the data.
Model selection in electromagnetic source analysis with an application to VEF’s
 IEEE Transactions on Biomedical Engineering
, 2002
"... Abstract — In electromagnetic source analysis it is necessary to determine how many sources are required to describe the EEG or MEG adequately. Model selection procedures (MSP’s, or goodness of fit procedures) give an estimate of the required number of sources. Existing and new MSP’s are evaluated i ..."
Abstract

Cited by 7 (4 self)
 Add to MetaCart
Abstract — In electromagnetic source analysis it is necessary to determine how many sources are required to describe the EEG or MEG adequately. Model selection procedures (MSP’s, or goodness of fit procedures) give an estimate of the required number of sources. Existing and new MSP’s are evaluated in different source and noise settings: two sources which are close or distant, and noise which is uncorrelated or correlated. The commonly used MSP residual variance is seen to be ineffective, that is it often selects too many sources. Alternatives like the adjusted Hotelling’s test, Bayes information criterion, and the Wald test on source amplitudes are seen to be effective. The adjusted Hotelling’s test is recommended if a conservative approach is taken, and MSP’s such as Bayes information criterion or the Wald test on source amplitudes are recommended if a more liberal approach is desirable. The MSP’s are applied to empirical data (visual evoked fields). I.
MEG Source Localization using an MLP with a Distributed Output Representation
"... We present a system that takes realistic magnetoencephalographic (MEG) signals and localizes a single dipole to reasonable accuracy in real time. At its heart is a multilayer perceptron (MLP) which takes the sensor measurements as inputs, uses one hidden layer, and generates as outputs the amplitude ..."
Abstract

Cited by 6 (3 self)
 Add to MetaCart
We present a system that takes realistic magnetoencephalographic (MEG) signals and localizes a single dipole to reasonable accuracy in real time. At its heart is a multilayer perceptron (MLP) which takes the sensor measurements as inputs, uses one hidden layer, and generates as outputs the amplitudes of receptive fields holding a distributed representation of the dipole location. We trained this SoftMLP on dipolar sources with real brain noise and converted the network's output into an explicit Cartesian coordinate representation of the dipole location using two different decoding strategies. The proposed SoftMLPs are much more accurate than previous networks which output source locations in Cartesian coordinates. Hybrid SoftMLPstartLM systems, in which the SoftMLP output initializes LevenbergMarquardt, retained their accuracy of 0.28 cm with a decrease in computation time from 36 ms to 30 ms. We apply the SoftMLP localizer to real MEG data separated by a blind source separation algorithm, and compare the SoftMLP dipole locations to those of a conventional system.
Phase Synchronisation in Superimposed Electrophysiological Data
, 2007
"... There is experimental and theoretical evidence that functional units on various scales of the nervous system express properties of selfsustained oscillators. For example, this quality is present in several models for a neuron’s membrane potential dynamics. Perturbation theory then leads to a formul ..."
Abstract

Cited by 1 (0 self)
 Add to MetaCart
There is experimental and theoretical evidence that functional units on various scales of the nervous system express properties of selfsustained oscillators. For example, this quality is present in several models for a neuron’s membrane potential dynamics. Perturbation theory then leads to a formulation of the oscillator’s dynamic interactions solely based on phase evolutions. In such models mutual synchronisation can occur. Verification that this effect takes place in the nervous system and is relevant for information integration requires calculating quantities such as a matrix of bivariate phaselocking statistics from multiunit electrophysiological measurements. For this, data with high temporal resolution is favourable, rendering invasive recordings of local field potentials or noninvasive techniques like EEG or MEG suitable. This thesis provides interpretation for the spectral analysis of the synchronisation matrix with respect to phase reduced oscillator dynamics underlying the data. The relation of eigenvectors and order parameters as well as eigenvalues and population size are highlighted and the clustering into phase locked subpopulations is described.
Blind Source Separation of Neuromagnetic Responses
"... Magnetoencephalography (MEG) is a functional brain imaging technique with millisecond temporal resolution and millimeter spatial resolution. The high temporal resolution of MEG compared to fMRI and PET (milliseconds vs. seconds and tens of seconds) makes it ideal for measuring the precise time of ne ..."
Abstract
 Add to MetaCart
Magnetoencephalography (MEG) is a functional brain imaging technique with millisecond temporal resolution and millimeter spatial resolution. The high temporal resolution of MEG compared to fMRI and PET (milliseconds vs. seconds and tens of seconds) makes it ideal for measuring the precise time of neuronal responses, thereby oering a powerful tool for studying temporal dynamics. We applied blind source separation (BSS) to continuous 122channel human magnetoencephalographic data from two subjects and ve tasks. We demonstrate that without using any domain specic knowledge and without making the common assumption of single or multiple current dipole sources, BSS is capable of separating nonneuronal noise sources from neuronal responses and also of separating neuronal responses from dierent sensory modalities, and from dierent processing stages within a given modality. Key words: functional brain imaging; ICA; MEG; blind source separation. 1 Introduction The brain's neuromagnetic ...
MAXIMUM LIKELIHOOD ESTIMATION WITH A PARAMETRIC NOISE COVARIANCE MODEL FOR INSTANTANEOUS AND SPATIOTEMPORAL ELECTROMAGNETIC SOURCE ANALYSIS
"... In instantaneous encephalogram or magnetoencephalogram (EEG/MEG) source analysis, ordinary least squares estimation (OLS) requires that the spatial noise is homoscedastic and uncorrelated over sensors. In spatiotemporal analysis OLS also requires that the noise is homoscedastic and uncorrelated in ..."
Abstract
 Add to MetaCart
In instantaneous encephalogram or magnetoencephalogram (EEG/MEG) source analysis, ordinary least squares estimation (OLS) requires that the spatial noise is homoscedastic and uncorrelated over sensors. In spatiotemporal analysis OLS also requires that the noise is homoscedastic and uncorrelated in time (over samples). Generally, these assumptions are violated and, as a consequence, OLS can give rise to inaccuracies in the estimates of location and moment paramaters of sources underlying the EEG/MEG. To improve these estimates of the sources, generalized least squares (GLS) was developed, which uses the spatial or spatiotemporal noise covariances. In GLS these noise covariances are estimated from trial variation around the mean. Therefore, GLS requires many trials to accurately estimate the spatial noise covariances and thus the source parameters. Alternatively, with Maximum Likelihood (ML) the spatial or spatiotemporal noise covariances can be modeled parametrically. Here, only the modelparameters describing the noise covariances need to be estimated. Consequently, fewer trials are required to obtain accurate noise covariances and consequently accurate source parameters. In this paper ML estimation for spatiotemporal analysis is derived, and it is shown that the noise and source parameters can be estimated separately. Furthermore, the likelihood ratio function is proposed to estimate the spatial or spatiotemporal noise covariance model parameters, which can also be used to test whether the model is adequate. The Netherlands Organization for Scienti c Research (NWO) is gratefully acknowledged for funding this project. This research was conducted while Lourens Waldorp was supported by a grant of the NWO foundation for Behavioral and Educational Sciences of this organization (52725013) awarded to Hilde Huizenga.
Machine Learning
"... In this work, we propose a hierarchical latent dictionary approach to estimate the timevarying mean and covariance of a process for which we have only limited noisy samples. We fully leverage the limited sample size and redundancy in sensor measurements by transferring knowledge through a hierarchy ..."
Abstract
 Add to MetaCart
In this work, we propose a hierarchical latent dictionary approach to estimate the timevarying mean and covariance of a process for which we have only limited noisy samples. We fully leverage the limited sample size and redundancy in sensor measurements by transferring knowledge through a hierarchy of lower dimensional latent processes. As a case study, we utilize Magnetoencephalography (MEG) recordings of brain activity to identify the word being viewed by a human subject. Specifically, we identify the word category for a single noisy MEG recording, when only given limited noisy samples on which to train. 1