High-density electroencephalographic recordings have recently been proved to bring useful information during the pre-surgical evaluation of patients suffering from drug-resistant epilepsy. However, these recordings ca...
详细信息
ISBN:
(纸本)9781424492701
High-density electroencephalographic recordings have recently been proved to bring useful information during the pre-surgical evaluation of patients suffering from drug-resistant epilepsy. However, these recordings can be particularly obscured by noise and artifacts. This paper focuses on the denoising of dense-array EEG data (e.g. 257 channels) contaminated with muscle artifacts. In this context, we compared the efficiency of several Independent Component Analysis (ICA) methods, namely SOBI, SOBIrob, PICA, InfoMax, two different implementations of FastICA, COM2, ERICA, and SIMBEC, as well as that of Canonical Correlation Analysis (CCA). We evaluated the performance using the Normalized Mean Square Error (NMSE) criterion and calculated the numerical complexity. Quantitative results obtained on realistic simulated data show that some of the ICA methods as well as CCA can properly remove muscular artifacts from dense-array EEG.
Deformulation of a commercial surfactant mixture using Raman spectroscopy and advanced chemometric tools have been investigated. Since the use of surfactants is drastically expanding, their fine identification and qua...
详细信息
Deformulation of a commercial surfactant mixture using Raman spectroscopy and advanced chemometric tools have been investigated. Since the use of surfactants is drastically expanding, their fine identification and quantification are required for quality control and regulation. Dilution of the detergent mixtures combined with Raman spectroscopy for signal extraction tools allowed the extraction of the first information concerning the composition of the mixture. The raw materials identified were thus used in an experimental design to obtain a robust model for the determination of detergent composition. The combination of chemometric tools (independent component analysis and Partial Least Square) and spectroscopic methods provided pertinent information for detergent composition. This methodology can easily be transposed to the industrial world.
In this paper, a blindsourceseparation method for bilinear mixtures of two source signals is presented, that relies on nonlinear correlation between separating system outputs. An estimate of each source is created b...
详细信息
ISBN:
(纸本)9783319937649;9783319937632
In this paper, a blindsourceseparation method for bilinear mixtures of two source signals is presented, that relies on nonlinear correlation between separating system outputs. An estimate of each source is created by linearly combining observed mixtures and maximizing a cost function based on the correlation between the element-wise product of the estimated sources and the corresponding quadratic term. A proof of the method separability, i.e. of the uniqueness of the solution to the cost function maximization problem, is also given. The algorithm used in this work is also presented. Its effectiveness is demonstrated through tests with artificial mixtures created with real Earth observation spectra. The proposed method is shown to yield much better performance than a state-of-the-art method.
暂无评论