Vincent Vigneron

Fetal electrocardiogram extraction based on non-stationary ICA and wavelet denoising

Fetal electrocardiogram (fECG) monitoring is a technique for obtaining important information about the condition of the fetus during pregnancy and labour by measuring electrical signals generated by the fetal heart as measured from multi-channel potential recordings on the mother body surface. It is shown in this paper that the fetal ECG can be reconstructed by means of higher order statistical tools exploiting ECG nonstationarity associated with post-denoising with wavelets. The method is illustrated on real fetal ECG data.

A New Decentralized Bayesian Approach for Cooperative Vehicle Localization Based on Fusion of GPS and VANET Based Inter-Vehicle Distance Measurement

Accurate and reliable vehicle localization is a key component of numerous automotive and Intelligent Transportation System (ITS) applications, including active vehicle safety systems, real time estimation of traffic conditions, and high occupancy tolling. Various safety critical vehicle applications in particular, such as collision avoidance or mitigation, lane change management or emergency braking assistance systems, rely principally on the accurate and reliable knowledge of vehicles? positioning within given vicinity.

A new decentralized Bayesian approach for cooperative vehicle localization based on fusion of GPS and inter-vehicle distance measurements

Embedded intelligence in vehicular applications is becoming of great interest since the last two decades. The significant growth of sensing, communication and computing capabilities over the recent years has opened new fields of applications, such as ADAS and active safety systems, and has brought the ability of exchanging information between vehicles. In this paper, a new method for improving vehicle positioning is proposed. This method is a decentralized method based on sharing GPS data and inter-vehicular distance measurements within a cluster of vehicles. A Bayesian approach is used to fuse the GPS data and inter-vehicular distances. In order to investigate the performance of this new approach on vehicle localization, a Kalman filter has been employed to incorporate the dynamics of the vehicle. The effect of this method on the reduction of the localization uncertainty, over-convergence issues and identification of the vehicles are also discussed in this paper.

Improving independent component analysis performances by variable selection

Blind source separation (BSS) consists in recovering unobserved signals from observed mixtures of them. In most cases the whole set of mixtures is used for the separation, possibly after a dimension reduction by PCA. This paper aims to show that in many applications the quality of the separation can be improved by first selecting a subset of some mixtures among the available ones, possibly by an information content criterion, and performing PCA and BSS afterwards. The benefit of this procedure is shown on simulated electrocardiographic data by extracting the fetal electrocardiogram signal from mixtures recorded on the abdomen of a pregnant woman.

Electrode Selection for Noninvasive Fetal Electrocardiogram Extraction using Mutual Information Criteria

Blind source separation (BSS) techniques have revealed to be promising approaches for the noninvasive extraction of fetal cardiac signals from maternal abdominal recordings. From previous studies, it is now believed that a carefully selected array of electrodes well-placed over the abdomen of a pregnant woman contains the required ‘information’ for BSS, to extract the complete fetal components. Based on this idea, previous works have involved array recording systems and sensor selection strategies based on the Mutual Information (MI) criterion. In this paper the previous works have been extended, by considering the 3-dimensional aspects of the cardiac electrical activity. The proposed method has been tested on simulated and real maternal abdominal recordings. The results show that the new sensor selection strategy together with the MI criterion, can be effectively used to select the channels containing the most ‘information’ concerning the fetal ECG components from an array of 72 recordings. The method is hence believed to be useful for the selection of the most informative channels in online applications, considering the different fetal positions and movements.

Analytical Solution of the Blind Source Separation Problem Using Derivatives

In this paper, we consider independence property between a random process and its first derivative. Then, for linear mixtures, we show that cross-correlations between mixtures and their derivatives provide a sufficient number of equations for analytically computing the unknown mixing matrix. In addition to its simplicity, the method is able to separate Gaussian sources, since it only requires second order statistics. For two mixtures of two sources, the analytical solution is given, and a few experiments show the efficiency of the method for the blind separation of two Gaussian sources.

Face localization by neural networks trained with Zernike moments and Eigenfaces feature vectors. A comparison

Face localization using neural network is presented in this communication. Neural network was trained with two different kinds of feature parameters vectors; Zernike moments and eigenfaces. In each case, coordinate vectors of pixels surrounding faces in images were used as target vectors on the supervised training procedure. Thus, trained neural network provides on its output layer a coordinates vector (rho,thetas) representing pixels surrounding the face contained in treated image. This way to proceed gives accurate faces contours which are well adapted to their shapes. Performances obtained for the two kinds of training feature parameters were recorded using a quantitative measurement criterion according to experiments carried out on the XM2VTS database.

Wavelet De-noising for Blind Source Separation in Noisy Mixtures

Blind source separation, which supposes that the sources are independent, is a well known domain in signal processing. However, in a noisy environment the estimation of the criterion is harder due to the noise. In strong noisy mixtures, we propose two new principles based on the combination of wavelet de-noising processing and blind source separation. We compare them in the cases of white/correlated Gaussian noise.

Fisher information in source separation problems

The ability to estimate a specific set of parameters, without regard to an unknown set of other parameters that influence the measured data, or nuisance parameters, is described by the Fisher Information matrix (FIM), and its inverse the Cramer-Rao bound. In many adaptive gradient algorithm, the effect of multiplication by the latter is to make the update larger in directions in which the variations of the parameter θ have less statistical significance. In this paper, we examine the relationship between the Fisher information and the covariance of the estimation error under the scope of the source separation problem.

Nonlinear Blind Parameter Estimation

This note deals with parameter estimation of nonlinear continuous-time models when the input signals of the corresponding system are not measured. The contribution of the note is to show that, with simple priors about the unknown input signals and using derivatives of the output signals, one can perform the estimation procedure. As an illustration, we consider situations where the simple priors, e.g., independence or Gaussianity of the unknown inputs, is assumed.