Normal Versus Pathological Voice Signals Using Wavelet Analysis and Least Squares Support-Vector Machines

State of Sao Paulo Research Foundation (FAPESP)

Support vector machines for detecting age-related changes in running kinematics

Age-related changes in running kinematics have been reported in the literature using classical inferential statistics. However, this approach has been hampered by the increased number of biomechanical gait variables reported and subsequently the lack of differences presented in these studies. Data mining techniques have been applied in recent biomedical studies to solve this problem using a more general approach. In the present work, we re-analyzed lower extremity running kinematic data of 17 young and 17 elderly male runners using the Support Vector Machine (SVM) classification approach. In total, 31 kinematic variables were extracted to train the classification algorithm and test the generalized performance. The results revealed different accuracy rates across three different kernel methods adopted in the classifier, with the linear kernel performing the best. A subsequent forward feature selection algorithm demonstrated that with only six features, the linear kernel SVM achieved 100% classification performance rate, showing that these features provided powerful combined information to distinguish age groups. The results of the present work demonstrate potential in applying this approach to improve knowledge about the age-related differences in running gait biomechanics and encourages the use of the SVM in other clinical contexts. (C) 2010 Elsevier Ltd. All rights reserved.

An fMRI Normative Database for Connectivity Networks Using One-Class Support Vector Machines

The application of functional magnetic resonance imaging (fMRI) in neuroscience studies has increased enormously in the last decade. Although primarily used to map brain regions activated by specific stimuli, many studies have shown that fMRI can also be useful in identifying interactions between brain regions (functional and effective connectivity). Despite the widespread use of fMRI as a research tool, clinical applications of brain connectivity as studied by fMRI are not well established. One possible explanation is the lack of normal pattern, and intersubject variability-two variables that are still largely uncharacterized in most patient populations of interest. In the current study, we combine the identification of functional connectivity networks extracted by using Spearman partial correlation with the use of a one-class support vector machine in order construct a normative database. An application of this approach is illustrated using an fMRI dataset of 43 healthy Subjects performing a visual working memory task. In addition, the relationships between the results obtained and behavioral data are explored. Hum Brain Mapp 30:1068-1076, 2009. (C) 2008 Wiley-Liss. Inc.

The impact of functional connectivity changes on support vector machines mapping of fMRI data

Functional magnetic resonance imaging (fMRI) is currently one of the most widely used methods for studying human brain function in vivo. Although many different approaches to fMRI analysis are available, the most widely used methods employ so called ""mass-univariate"" modeling of responses in a voxel-by-voxel fashion to construct activation maps. However, it is well known that many brain processes involve networks of interacting regions and for this reason multivariate analyses might seem to be attractive alternatives to univariate approaches. The current paper focuses on one multivariate application of statistical learning theory: the statistical discrimination maps (SDM) based on support vector machine, and seeks to establish some possible interpretations when the results differ from univariate `approaches. In fact, when there are changes not only on the activation level of two conditions but also on functional connectivity, SDM seems more informative. We addressed this question using both simulations and applications to real data. We have shown that the combined use of univariate approaches and SDM yields significant new insights into brain activations not available using univariate methods alone. In the application to a visual working memory fMRI data, we demonstrated that the interaction among brain regions play a role in SDM`s power to detect discriminative voxels. (C) 2008 Elsevier B.V. All rights reserved.

Near infrared spectroscopy for soil bulk density assessment

P>Soil bulk density values are needed to convert organic carbon content to mass of organic carbon per unit area. However, field sampling and measurement of soil bulk density are labour-intensive, costly and tedious. Near-infrared reflectance spectroscopy (NIRS) is a physically non-destructive, rapid, reproducible and low-cost method that characterizes materials according to their reflectance in the near-infrared spectral region. The aim of this paper was to investigate the ability of NIRS to predict soil bulk density and to compare its performance with published pedotransfer functions. The study was carried out on a dataset of 1184 soil samples originating from a reforestation area in the Brazilian Amazon basin, and conventional soil bulk density values were obtained with metallic ""core cylinders"". The results indicate that the modified partial least squares regression used on spectral data is an alternative method for soil bulk density predictions to the published pedotransfer functions tested in this study. The NIRS method presented the closest-to-zero accuracy error (-0.002 g cm-3) and the lowest prediction error (0.13 g cm-3) and the coefficient of variation of the validation sets ranged from 8.1 to 8.9% of the mean reference values. Nevertheless, further research is required to assess the limits and specificities of the NIRS method, but it may have advantages for soil bulk density predictions, especially in environments such as the Amazon forest.

Kernel machines for epilepsy diagnosis via EEG signal classification: A comparative study

Objective: We carry out a systematic assessment on a suite of kernel-based learning machines while coping with the task of epilepsy diagnosis through automatic electroencephalogram (EEG) signal classification. Methods and materials: The kernel machines investigated include the standard support vector machine (SVM), the least squares SVM, the Lagrangian SVM, the smooth SVM, the proximal SVM, and the relevance vector machine. An extensive series of experiments was conducted on publicly available data, whose clinical EEG recordings were obtained from five normal subjects and five epileptic patients. The performance levels delivered by the different kernel machines are contrasted in terms of the criteria of predictive accuracy, sensitivity to the kernel function/parameter value, and sensitivity to the type of features extracted from the signal. For this purpose, 26 values for the kernel parameter (radius) of two well-known kernel functions (namely. Gaussian and exponential radial basis functions) were considered as well as 21 types of features extracted from the EEG signal, including statistical values derived from the discrete wavelet transform, Lyapunov exponents, and combinations thereof. Results: We first quantitatively assess the impact of the choice of the wavelet basis on the quality of the features extracted. Four wavelet basis functions were considered in this study. Then, we provide the average accuracy (i.e., cross-validation error) values delivered by 252 kernel machine configurations; in particular, 40%/35% of the best-calibrated models of the standard and least squares SVMs reached 100% accuracy rate for the two kernel functions considered. Moreover, we show the sensitivity profiles exhibited by a large sample of the configurations whereby one can visually inspect their levels of sensitiveness to the type of feature and to the kernel function/parameter value. Conclusions: Overall, the results evidence that all kernel machines are competitive in terms of accuracy, with the standard and least squares SVMs prevailing more consistently. Moreover, the choice of the kernel function and parameter value as well as the choice of the feature extractor are critical decisions to be taken, albeit the choice of the wavelet family seems not to be so relevant. Also, the statistical values calculated over the Lyapunov exponents were good sources of signal representation, but not as informative as their wavelet counterparts. Finally, a typical sensitivity profile has emerged among all types of machines, involving some regions of stability separated by zones of sharp variation, with some kernel parameter values clearly associated with better accuracy rates (zones of optimality). (C) 2011 Elsevier B.V. All rights reserved.

NEAR INFRARED SPECTROSCOPY FOR ESTIMATING SUGARCANE BAGASSE CONTENT IN MEDIUM DENSITY FIBERBOARD

Medium density fiberboard (MDF) is an engineered wood product formed by breaking down selected lignin-cellulosic material residuals into fibers, combining it with wax and a resin binder, and then forming panels by applying high temperature and pressure. Because the raw material in the industrial process is ever-changing, the panel industry requires methods for monitoring the composition of their products. The aim of this study was to estimate the ratio of sugarcane (SC) bagasse to Eucalyptus wood in MDF panels using near infrared (NIR) spectroscopy. Principal component analysis (PCA) and partial least square (PLS) regressions were performed. MDF panels having different bagasse contents were easily distinguished from each other by the PCA of their NIR spectra with clearly different patterns of response. The PLS-R models for SC content of these MDF samples presented a strong coefficient of determination (0.96) between the NIR-predicted and Lab-determined values and a low standard error of prediction (similar to 1.5%) in the cross-validations. A key role of resins (adhesives), cellulose, and lignin for such PLS-R calibrations was shown. PLS-DA model correctly classified ninety-four percent of MDF samples by cross-validations and ninety-eight percent of the panels by independent test set. These NIR-based models can be useful to quickly estimate sugarcane bagasse vs. Eucalyptus wood content ratio in unknown MDF samples and to verify the quality of these engineered wood products in an online process.

Estimation and prediction of parameters and breeding values in soybean using REML/BLUP and Least Squares

The aim of this study was to compare REML/BLUP and Least Square procedures in the prediction and estimation of genetic parameters and breeding values in soybean progenies. F(2:3) and F(4:5) progenies were evaluated in the 2005/06 growing season and the F(2:4) and F(4:6) generations derived thereof were evaluated in 2006/07. These progenies were originated from two semi-early, experimental lines that differ in grain yield. The experiments were conducted in a lattice design and plots consisted of a 2 m row, spaced 0.5 m apart. The trait grain yield per plot was evaluated. It was observed that early selection is more efficient for the discrimination of the best lines from the F(4) generation onwards. No practical differences were observed between the least square and REML/BLUP procedures in the case of the models and simplifications for REML/BLUP used here.

[O/Fe] ESTIMATES FOR CARBON-ENHANCED METAL-POOR STARS FROM NEAR-INFRARED SPECTROSCOPY

We report on oxygen abundances determined from medium-resolution near-infrared spectroscopy for a sample of 57 carbon-enhanced metal-poor (CEMP) stars selected from the Hamburg/ESO Survey. The majority of our program stars exhibit oxygen-to-iron ratios in the range +0.5 < [O/Fe]< + 2.0. The [O/Fe] values for this sample are statistically compared to available high-resolution estimates for known CEMP stars as well as to high-resolution estimates for a set of carbon-normal metal-poor stars. Carbon, nitrogen, and oxygen abundance patterns for a sub-sample of these stars are compared to yield predictions for very metal-poor asymptotic giant branch (AGB) abundances in the recent literature. We find that the majority of our sample exhibit patterns that are consistent with previously studied CEMP stars having s-process-element enhancements and thus have very likely been polluted by carbon- and oxygen-enhanced material transferred from a metal-poor AGB companion.

Estimation of hexenuronic acids and kappa number in kraft pulps of Eucalyptus globulus by Fourier transform near infrared spectroscopy and multivariate analysis

Fourier transform near infrared (FT-NIR) spectroscopy was evaluated as an analytical too[ for monitoring residual Lignin, kappa number and hexenuronic acids (HexA) content in kraft pulps of Eucalyptus globulus. Sets of pulp samples were prepared under different cooking conditions to obtain a wide range of compound concentrations that were characterised by conventional wet chemistry analytical methods. The sample group was also analysed using FT-NIR spectroscopy in order to establish prediction models for the pulp characteristics. Several models were applied to correlate chemical composition in samples with the NIR spectral data by means of PCR or PLS algorithms. Calibration curves were built by using all the spectral data or selected regions. Best calibration models for the quantification of lignin, kappa and HexA were proposed presenting R-2 values of 0.99. Calibration models were used to predict pulp titers of 20 external samples in a validation set. The lignin concentration and kappa number in the range of 1.4-18% and 8-62, respectively, were predicted fairly accurately (standard error of prediction, SEP 1.1% for lignin and 2.9 for kappa). The HexA concentration (range of 5-71 mmol kg(-1) pulp) was more difficult to predict and the SEP was 7.0 mmol kg(-1) pulp in a model of HexA quantified by an ultraviolet (UV) technique and 6.1 mmol kg(-1) pulp in a model of HexA quantified by anion-exchange chromatography (AEC). Even in wet chemical procedures used for HexA determination, there is no good agreement between methods as demonstrated by the UV and AEC methods described in the present work. NIR spectroscopy did provide a rapid estimate of HexA content in kraft pulps prepared in routine cooking experiments.

An Array Recursive Least-Squares Algorithm With Generic Nonfading Regularization Matrix

We present a novel array RLS algorithm with forgetting factor that circumvents the problem of fading regularization, inherent to the standard exponentially-weighted RLS, by allowing for time-varying regularization matrices with generic structure. Simulations in finite precision show the algorithm`s superiority as compared to alternative algorithms in the context of adaptive beamforming.

Nuclear and extended spectra of NGC 1068-I. Hints from near-infrared spectroscopy

We report the first simultaneous zJHK spectroscopy on the archetypical Seyfert 2 galaxy NGC 1068 covering the wavelength region 0.9-2.4 mu m. The slit, aligned in the north-south direction and centred in the optical nucleus, maps a region 300 pc in radius at subarcsec resolution, with a spectral resolving power of 360 km s-1. This configuration allows us to study the physical properties of the nuclear gas including that of the north side of the ionization cone, map the strong excess of continuum emission in the K band and attributed to dust and study the variations, both in flux and profile, in the emission lines. Our results show the following. (1) Mid- to low-ionization emission lines are split into two components, whose relative strengths vary with the position along the slit and seem to be correlated with the jet. (2) The coronal lines are single-peaked and are detected only in the central few hundred of pc from the nucleus. (3) The absorption lines indicate the presence of intermediate age stellar population, which might be a significant contributor to the continuum in the near-IR spectra. (4) Through some simple photoionization models we find photoionization as the main mechanism powering the emitting gas. (5) Calculations using stellar features point to a mass concentration inside the 100-200 pc of about 1010 M(circle dot).

Front tracking with moving-least-squares surfaces

The representation of interfaces by means of the algebraic moving-least-squares (AMLS) technique is addressed. This technique, in which the interface is represented by an unconnected set of points, is interesting for evolving fluid interfaces since there is]to surface connectivity. The position of the surface points can thus be updated without concerns about the quality of any surface triangulation. We introduce a novel AMLS technique especially designed for evolving-interfaces applications that we denote RAMLS (for Robust AMLS). The main advantages with respect to previous AMLS techniques are: increased robustness, computational efficiency, and being free of user-tuned parameters. Further, we propose a new front-tracking method based on the Lagrangian advection of the unconnected point set that defines the RAMLS surface. We assume that a background Eulerian grid is defined with some grid spacing h. The advection of the point set makes the surface evolve in time. The point cloud can be regenerated at any time (in particular, we regenerate it each time step) by intersecting the gridlines with the evolved surface, which guarantees that the density of points on the surface is always well balanced. The intersection algorithm is essentially a ray-tracing algorithm, well-studied in computer graphics, in which a line (ray) is traced so as to detect all intersections with a surface. Also, the tracing of each gridline is independent and can thus be performed in parallel. Several tests are reported assessing first the accuracy of the proposed RAMLS technique, and then of the front-tracking method based on it. Comparison with previous Eulerian, Lagrangian and hybrid techniques encourage further development of the proposed method for fluid mechanics applications. (C) 2008 Elsevier Inc. All rights reserved.

Structural Phase Transition Studies on PMN-0.35PT using Infrared Spectroscopy

The purpose of the present work is to report studies on structural phase transition for PMN-xPT ferroelectric, with melt PbTiO3 composition around the MPB (x = 0.35 mol %), using infrared spectroscopy technique. The study was centered on monitoring the behavior of the 1-(NbO), 1-(TiO) and 1-(MgO) stretching modes as a function of temperature. The increasing as a function of temperature for 1-(TiO) and 1-(MgO) modes, observed between 230 and 300 K, can be related to the monoclinic (MC) + tetragonal (T) phase coexistence in the PMN-PT.

Synthesis, Infrared Spectroscopy and Crystal Structure Determination of a New Decavanadate

Synthesis, infrared spectroscopy and crystal structure of a new potassium decavanadate decahydrate, K(6)[V(10)O(28)] 10H(2)O, has been reported The infrared spectrum is dominated by decavanadate polyanion and water bands The X-ray crystallography analysis found the compound crystallizes in a triclinic system with the parameters a = 10 5334 (4) angstrom, b = 10 6600 (4) angstrom, c = 17 7351 (5) angstrom, alpha = 76 940 (2)degrees, beta = 75 836 (2)degrees, gamma = 64 776 (2)degrees, V = 1,729 86 (11) A(3), Z = 2, space group P (1) over bar The polyanion consists of ten [VO(6)] octahedra sharing edges, in which the V-O distances are in good agreement with those reported for other decavanadates The crystal structure is stabilized by potassium cations and water molecules forming a complex pattern of hydrogen bonding and short contact ionic interactions