Rolando J. Biscay

A solution to the dynamical inverse problem of EEG generation using spatiotemporal Kalman filtering

We present a new approach for estimating solutions of the dynamical inverse problem of EEG generation. In contrast to previous approaches, we reinterpret this problem as a filtering problem in a state space framework; for the purpose of its solution, we propose a new extension of Kalman filtering to the case of spatiotemporal dynamics. The temporal evolution of the distributed generators of the EEG can be reconstructed at each voxel of a discretisation of the gray matter of brain. By fitting linear autoregressive models with neighbourhood interactions to EEG time series, new classes of inverse solutions with improved resolution and localisation ability can be explored. For the purposes of model comparison and parameter estimation from given data, we employ a likelihood maximisation approach. Both for instantaneous and dynamical inverse solutions, we derive estimators of the time-dependent estimation error at each voxel. The performance of the algorithm is demonstrated by application to simulated and clinical EEG recordings. It is shown that by choosing appropriate dynamical models, it becomes possible to obtain inverse solutions of considerably improved quality, as compared to the usual instantaneous inverse solutions.

Recursive penalized least squares solution for dynamical inverse problems of EEG generation

In the dynamical inverse problem of electroencephalogram (EEG) generation where a specific dynamics for the electrical current distribution is assumed, we can impose general spatiotemporal constraints onto the solution by casting the problem into a state space representation and assuming a specific class of parametric models for the dynamics. The Akaike Bayesian Information Criterion (ABIC), which is based on the Type II likelihood, was used to estimate the parameters and evaluate the model. In addition, dynamic low‐resolution brain electromagnetic tomography (LORETA), a new approach for estimating the current distribution is introduced. A recursive penalized least squares (RPLS) step forms the main element of our implementation. To obtain improved inverse solutions, dynamic LORETA exploits both spatial and temporal information, whereas LORETA uses only spatial information. A considerable improvement in performance compared to LORETA was found when dynamic LORETA was applied to simulated EEG data, and the new method was applied also to clinical EEG data. Hum. Brain Mapp. 21:221–235, 2004.

Dynamic properties of the local linearization method for initial-value problems

Some dynamic properties of the local linearization (LL) scheme for the numerical integration of initial-value problems in ordinary differential equations (ODEs) are investigated. Specifically, the general conditions under which this scheme preserves the stationary points and periodic orbits of the ODEs and the local stability at these steady states are studied. These dynamic properties are also examined by means of numerical experiments and the results are compared with those achieved by other numerical schemes. In addition, a brief review of the computational implementations of the LL scheme is also presented.

Assessing direct paths of intracortical causal information flow of oscillatory activity with the isolated effective coherence (iCoh)

Functional connectivity is of central importance in understanding brain function. For this purpose, multiple time series of electric cortical activity can be used for assessing the properties of a network: the strength, directionality, and spectral characteristics (i.e., which oscillations are preferentially transmitted) of the connections. The partial directed coherence (PDC) of Baccala and Sameshima (2001) is a widely used method for this problem. The three aims of this study are: (1) To show that the PDC can misrepresent the frequency response under plausible realistic conditions, thus defeating the main purpose for which the measure was developed; (2) To provide a solution to this problem, namely the “isolated effective coherence” (iCoh), which consists of estimating the partial coherence under a multivariate autoregressive model, followed by setting all irrelevant associations to zero, other than the particular directional association of interest; and (3) To show that adequate iCoh estimators can be obtained from non-invasively computed cortical signals based on exact low resolution electromagnetic tomography (eLORETA) applied to scalp EEG recordings. To illustrate the severity of the problem with the PDC, and the solution achieved by the iCoh, three examples are given, based on: (1) Simulated time series with known dynamics; (2) Simulated cortical sources with known dynamics, used for generating EEG recordings, which are then used for estimating (with eLORETA) the source signals for the final connectivity assessment; and (3) EEG recordings in rats. Lastly, real human recordings are analyzed, where the iCoh between six cortical regions of interest are calculated and compared under eyes open and closed conditions, using 61-channel EEG recordings from 109 subjects. During eyes closed, the posterior cingulate sends alpha activity to all other regions. During eyes open, the anterior cingulate sends theta-alpha activity to other frontal regions.

Random Field–Union Intersection tests for EEG/MEG imaging

Electrophysiological (EEG/MEG) imaging challenges statistics by providing two views of the same spatiotemporal data: topographic and tomographic. Until now, statistical tests for these two situations have developed separately. This work introduces statistical tests for assessing simultaneously the significance of spatiotemporal event-related potential/event-related field (ERP/ERF) components and that of their sources. The test for detecting a component at a given time instant is provided by a Hotellings T(2) statistic. This statistic is constructed in such a manner to be invariant to any choice of reference and is based upon a generalized version of the average reference transform of the data. As a consequence, the proposed test is a generalization of the well-known Global Field Power statistic. Consideration of tests at all time instants leads to a multiple comparison problem addressed by the use of Random Field Theory (RFT). The Union-Intersection (UI) principle is the basis for testing hypotheses about the topographic and tomographic distributions of such ERP/ERF components. The performance of the method is illustrated with actual EEG recordings obtained from a visual experiment of pattern reversal stimuli.

Support vector regression for functional data in multivariate calibration problems

Quantitative analyses involving instrumental signals, such as chromatograms, NIR, and MIR spectra have been successfully applied nowadays for the solution of important chemical tasks. Multivariate calibration is very useful for such purposes and the commonly used methods in chemometrics consider each sample spectrum as a sequence of discrete data points. An alternative way to analyze spectral data is to consider each sample as a function, in which a functional data is obtained. Concerning regression, some linear and nonparametric regression methods have been generalized to functional data. This paper proposes the use of the recently introduced method, support vector regression for functional data (FDA-SVR) for the solution of linear and nonlinear multivariate calibration problems. Three different spectral datasets were analyzed and a comparative study was carried out to test its performance with respect to some traditional calibration methods used in chemometrics such as PLS, SVR and LS-SVR. The satisfactory results obtained with FDA-SVR suggest that it can be an effective and promising tool for multivariate calibration tasks.

A numerical method for the computation of the Lyapunov exponents of nonlinear ordinary differential equations

In this paper, an alternative method to compute the Lyapunov exponents of dynamical systems described by ordinary differential equations (ODEs) is introduced. The Lyapunov exponents are computed in terms of the solutions of two piecewise linear ODEs that approximate, respectively, the solutions of the original ODE and its associated variational equation. This approach is strongly connected with the local linearization (LL) method for ODEs and its major advantage is that these piecewise linear ODEs might be exactly integrated in a non-simultaneous way. The performance of the method is illustrated with a numerical example.

Support vector regression methods for functional data

Many regression tasks in practice dispose in low gear instance of digitized functions as predictor variables. This has motivated the development of regression methods for functional data. In particular, Naradaya-Watson Kernel (NWK) and Radial Basis Function (RBF) estimators have been recently extended to functional nonparametric regression models. However, these methods do not allow for dimensionality reduction. For this purpose, we introduce Support Vector Regression (SVR) methods for functional data. These are formulated in the framework of approximation in reproducing kernel Hilbert spaces. On this general basis, some of its properties are investigated, emphasizing the construction of nonnegative definite kernels on functional spaces. Furthermore, the performance of SVR for functional variables is shown on a real world benchmark spectrometric data set, as well as comparisons with NWK and RBF methods. Good predictions were obtained by these three approaches, but SVR achieved in addition about 20% reduction of dimensionality.

Morphology-based hypothesis testing in discrete random fields: a non-parametric method to address the multiple-comparison problem in neuroimaging.

A new method for detecting activations in random fields, which may be useful for addressing the issue of multiple comparisons in neuroimaging, is presented. This method is based on some constructs of mathematical morphology--specifically, morphological erosions and dilations--that enable the detection of active regions in random fields possessing moderate activation levels and relatively large spatial extension, which may not be detected by the standard methods that control the family-wise error rate. The method presented here permits an appropriate control of the false positive errors, without having to adjust any threshold values, other than the significance level. The method is easily adapted to permutation-based procedures (with the usual restrictions), and therefore does not require strong assumptions about the distribution and spatio-temporal correlation structure of the data. Some examples of applications to synthetic data, including realistic fMRI simulations, as well as to real fMRI and electroencephalographic data are presented, illustrating the power of the presented technique. Comparisons with other methods that combine voxel intensity and cluster size, as well as some extensions of the method presented here based on their basic ideas are presented as well.A new method for detecting activations in random fields, which may be useful for addressing the issue of multiple comparisons in neuroimaging, is presented. This method is based on some constructs of mathematical morphology - specifically, morphological erosions and dilations - that enable the detection of active regions in random fields possessing moderate activation levels and relatively large spatial extension, which may not be detected by the standard methods that control the family-wise error rate. The method presented here permits an appropriate control of the false positive errors, without having to adjust any threshold values, other than the significance level. The method is easily adapted to permutation-based procedures (with the usual restrictions), and therefore does not require strong assumptions about the distribution and spatio-temporal correlation structure of the data. Some examples of applications to synthetic data, including realistic fMRI simulations, as well as to real fMRI and electroencephalographic data are presented, illustrating the power of the presented technique. Comparisons with other methods that combine voxel intensity and cluster size, as well as some extensions of the method presented here based on their basic ideas are presented as well.

A non-Bayesian predictive approach for statistical calibration

A non-Bayesian predictive approach for statistical calibration is introduced. This is based on particularizing to the calibration setting the general definition of non-Bayesian (or frequentist) predictive probability density proposed by Harris [Predictive fit for natural exponential families, Biometrika 76 (1989), pp. 675–684]. The new method is elaborated in detail in case of Gaussian linear univariate calibration. Through asymptotic analysis and simulation results with moderate sample size, it is shown that the non-Bayesian predictive estimator of the unknown parameter of interest in calibration (commonly, a substance concentration) favourably compares with previous estimators such as the classical and inverse estimators, especially for extrapolation problems. A further advantage of the non-Bayesian predictive approach is that it provides not only point estimates but also a predictive likelihood function that allows the researcher to explore the plausibility of any possible parameter value, which is also briefly illustrated. Furthermore, the introduced approach offers a general framework that can be applied for calibrating on the basis of any parametric statistical model, so making it potentially useful for nonlinear and non-Gaussian calibration problems.