Several studies dealing with independent component analysis (ICA)-based brain-computer interface (BCI) systems have been reported. Most of them have only explored a limited number of ICA methods, mainly FastICA and INFOMAX. The aim of this article is to help the BCI community researchers, especially those who are not familiar with ICA techniques, to choose an appropriate ICA method. For this purpose, the concept of ICA is reviewed and different measures of statistical independence are reported. Then, the application of these measures is illustrated through a brief description of the widely used algorithms in the ICA community, namely SOBI, COM2, JADE, ICAR, FastICA, and INFOMAX. The implementation of these techniques in the BCI field is also explained. Finally, a comparative study of these algorithms, conducted on simulated electroencephalography (EEG) data, shows that an appropriate selection of an ICA algorithm may significantly improve the capabilities of BCI systems.

Electroencephalographic (EEG) recordings are often contaminated with muscle artifacts. This disturbing myogenic activity not only strongly affects the visual analysis of EEG, but also most surely impairs the results of EEG signal processing tools such as source localization. This article focuses on the particular context of the contamination epileptic signals (interictal spikes) by muscle artifact, as EEG is a key diagnosis tool for this pathology. In this context, our aim was to compare the ability of two stochastic approaches of blind source separation, namely independent component analysis (ICA) and canonical correlation analysis (CCA), and of two deterministic approaches namely empirical mode decomposition (EMD) and wavelet transform (WT) to remove muscle artifacts from EEG signals. To quantitatively compare the performance of these four algorithms, epileptic spike-like EEG signals were simulated from two different source configurations and artificially contaminated with different levels of real EEG-recorded myogenic activity. The efficiency of CCA, ICA, EMD, and WT to correct the muscular artifact was evaluated both by calculating the normalized mean-squared error between denoised and original signals and by comparing the results of source localization obtained from artifact-free as well as noisy signals, before and after artifact correction. Tests on real data recorded in an epileptic patient are also presented. The results obtained in the context of simulations and real data show that EMD outperformed the three other algorithms for the denoising of data highly contaminated by muscular activity. For less noisy data, and when spikes arose from a single cortical source, the myogenic artifact was best corrected with CCA and ICA. Otherwise when spikes originated from two distinct sources, either EMD or ICA offered the most reliable denoising result for highly noisy data, while WT offered the better denoising result for less noisy data. These results suggest that the performance of muscle artifact correction methods strongly depend on the level of data contamination, and of the source configuration underlying EEG signals. Eventually, some insights into the numerical complexity of these four algorithms are given.

CODEN: IEMBDE INSPEC Accession Number:4930363International audienceThe authors' study made use of wavelet transforms to describe and recognize isolated cardiac beats. The choice of the wavelet family as well as the selection of the analyzing function into these families are discussed. The criterion used in the first case was the correct classification rate, and in the second case, the correlation coefficient between the original pattern and the reconstructed one. Two types of description have been considered-the energy-based representation and the extrema distribution estimated at each decomposition level-and their quality has been assessed by using principal component analysis. Their capability of discrimination between normal, premature ventricular contraction, and ischemic beats has been studied by means of linear discriminant analysis. This work leads also, for the problem at hand, to the identification of the most relevant resolution level

The Extended Kalman Filter (EKF) is a very popular tool dealing with state estimation. Its continuous-discrete version (CD-EKF) estimates the state trajectory of continuous-time nonlinear models, whose internal state is described by a stochastic differential equation and which is observed through a noisy nonlinear form of the sampled state. The prediction step of the CD-EKF leads to solve a differential equation that cannot be generally solved in a closed form. This technical note presents an overview of the numerical methods, including recent works, usually implemented to approximate this filter. Comparisons of theses methods on two different nonlinear models are finally presented. The first one is the Van der Pol oscillator which is widely used as a benchmark. The second one is a neuronal population model. This more original model is used to simulate EEG activity of the cortex. Experiments showed better stability properties of implementations for which the positivity of the prediction matrix is guaranteed.

Independent Component Analysis (ICA) plays an important role in biomedical engineering. Indeed, the complexity of processes involved in biomedicine and the lack of reference signals make this blind approach a powerful tool to extract sources of interest. However, in practice, only few ICA algorithms such as SOBI, (extended) InfoMax and FastICA are used nowadays to process biomedical signals. In this paper we raise the question whether other ICA methods could be better suited in terms of performance and computational complexity. We focus on ElectroEncephaloGraphy (EEG) data denoising, and more particularly on removal of muscle artifacts from interictal epileptiform activity. Assumptions required by ICA are discussed in such a context. Then fifteen ICA algorithms, namely JADE, CoM2, SOBI, SOBIrob, (extended) InfoMax, PICA, two different implementations of FastICA, ERICA, SIMBEC, FOBIUMJAD, TFBSS, ICAR3, FOOBI1 and 4- CANDHAPc are briefly described. Next they are studied in terms of performance and numerical complexity. Quantitative results are obtained on simulated epileptic data generated with a physiologically-plausible model. These results are also illustrated on real epileptic recordings.