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.

Methods of imagetic information representation

The aim of this paper is to highlight some of the methods of imagetic information representation, reviewing the literature of the area and proposing a model of methodology adapted to Brazilian museums. An elaboration of a methodology of imagetic information representation is developed based on Brazilian characteristics of information treatment in order to adapt it to museums. Finally, spreadsheets that show this methodology are presented.

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.

Anthropometric characteristics and motor skills in talent selection and development in indoor soccer

Kick performance, anthropometric characteristics, slalom, and linear running were assessed in 49 (24 elite, 25 nonelite) postpubertal indoor soccer players in order to (a) verify whether anthropometric characteristics and physical and technical capacities can distinguish players of different competitive levels, (b) compare the kicking kinematics of these groups, with and without a defined target, and (c) compare results on the assessments and coaches` subjective rankings of the players. Thigh circumference and specific technical capacities differentiated the players by level of play; cluster analysis correctly classified 77.5% of the players. The correlation between players` standardized measures and the coaches` rankings was 0.29. Anthropometric characteristics and physical capacities do not necessarily differentiate players at post-pubertal stages and should not be overvalued during early development. Considering the coaches` rankings, performance measures outside the specific game conditions may not be useful in identification of talented players.

Prevalence, magnitude, and methods of rapid weight loss among judo competitors

ARTIOLI, G. G., B. GUALANO, E. FRANCHINI, F. B. SCAGLIUSI, M. TAKESIAN, M. FUCHS, and A. H. LANCHA. Prevalence, Magnitude, and Methods of Rapid Weight Loss among Judo Competitors. Med. Sci. Sports Exerc., Vol. 42, No. 3, pp. 436-442, 2010. Purpose: To identify the prevalence, magnitude, and methods of rapid weight loss among judo competitors. Methods: Athletes (607 males and 215 females; age = 19.3 +/- 5.3 yr, weight = 70 +/- 7.5 kg, height = 170.6 +/- 9.8 cm) completed a previously validated questionnaire developed to evaluate rapid weight loss in judo athletes, which provides a score. The higher the score obtained, the more aggressive the weight loss behaviors. Data were analyzed using descriptive statistics and frequency analyses. Mean scores obtained in the questionnaire were used to compare specific groups of athletes using, when appropriate, Mann-Whitney U-test or general linear model one-way ANOVA followed by Tamhane post hoc test. Results: Eighty-six percent of athletes reported that have already lost weight to compete. When heavyweights are excluded, this percentage rises to 89%. Most athletes reported reductions of up to 5% of body weight (mean +/- SD: 2.5 +/- 2.3%). The most weight ever lost was 2%-5%, whereas a great part of athletes reported reductions of 5%-10% (mean +/- SD: 6 +/- 4%). The number of reductions underwent in a season was 3 +/- 5. The reductions usually occurred within 7 +/- 7 d. Athletes began cutting weight at 12.6 +/- 6.1 yr. No significant differences were found in the score obtained by male versus female athletes as well as by athletes from different weight classes. Elite athletes scored significantly higher in the questionnaire than nonelite. Athletes who began cutting weight earlier also scored higher than those who began later. Conclusions: Rapid weight loss is highly prevalent in judo competitors. The level of aggressiveness in weight management behaviors seems to not be influenced by the gender or by the weight class, but it seems to be influenced by competitive level and by the age at which athletes began cutting weight.

Methods of quantification of training load in exercise performed at maximal lactate steady state

The aim of the present study was to compare and correlate training impulse (TRIMP) estimates proposed by Banister (TRIMP(Banister)), Stagno (TRIMP(Stagno)) and Manzi (TRIMP(Manzi)). The subjects were submitted to an incremental test on cycle ergometer with heart rate and blood lactate concentration measurements. In the second occasion, they performed 30 min. of exercise at the intensity corresponding to maximal lactate steady state, and TRIMP(Banister), TRIMP(Stagno) and TRIMP(Manzi) were calculated. The mean values of TRIMP(Banister) (56.5 +/- 8.2 u.a.) and TRIMP(Stagno) (51.2 +/- 12.4 u.a.) were not different (P > 0.05) and were highly correlated (r = 0.90). Besides this, they presented a good agreement level, which means low bias and relatively narrow limits of agreement. On the other hand, despite highly correlated (r = 0.93), TRIMP(Stagno) and TRIMP(Manzi) (73.4 +/- 17.6 u.a.) were different (P < 0.05), with low agreement level. The TRIMP(Banister) e TRIMP(Manzi) estimates were not different (P = 0.06) and were highly correlated (r = 0.82), but showed low agreement level. Thus, we concluded that the investigated TRIMP methods are not equivalent. In practical terms, it seems prudent monitor the training process assuming only one of the estimates.

Preparation and characterization of Mo/W bimetallic carbides by using different synthesis methods

Molybdenum and tungsten bimetallic oxides were synthetized according to the following methods: Pechini, coprecipitation and solid state reaction (SSR). After the characterization, those solids were carbureted at programmed temperature. The carburation process was monitored by checking the consumption of carburant hydrocarbon and CO produced. The monitoring process permits to avoid or to diminish the formation of pirolytic carbon.

Raspberry (Rubus idaeus L.) wine: Yeast selection, sensory evaluation and instrumental analysis of volatile and other compounds

To evaluate the potential for fermentation of raspberry pulp, sixteen yeast strains (S. cerevisiae and S. bayanus) were studied. Volatile compounds were determined by GC-MS, GC-FID, and GC-PFPD. Ethanol. glycerol and organic acids were determined by HPLC. HPLC-DAD was used to analyse phenolic acids. Sensory analysis was performed by trained panellists. After a screening step, CAT-1, UFLA FW 15 and S. bayanus CBS 1505 were previously selected based on their fermentative characteristics and profile of the metabolites identified. The beverage produced with CAT-1 showed the highest volatile fatty acid concentration (1542.6 mu g/L), whereas the beverage produced with UFLA FIN 15 showed the highest concentration of acetates (2211.1 mu g/L) and total volatile compounds (5835 mu g/L). For volatile sulphur compounds. 566.5 mu g/L were found in the beverage produced with S. bayanus CBS 1505. The lowest concentration of volatile sulphur compounds (151.9 mu g/L) was found for the beverage produced with UFLA FW 15. In the sensory analysis, the beverage produced with UFLA FW 15 was characterised by the descriptors raspberry, cherry, sweet, strawberry, floral and violet. In conclusion, strain UFLA FW 15 was the yeast that produced a raspberry wine with a good chemical and sensory quality. (C) 2010 Elsevier Ltd. All rights reserved.

Selection of new glass-forming compositions in Al-La system using a combination of topological instability and thermodynamic criteria

A combination of an extension of the topological instability ""lambda criterion"" and a thermodynamic criterion were applied to the Al-La system, indicating the best range of compositions for glass formation. Alloy compositions in this range were prepared by melt-spinning and casting in an arc-melting furnace with a wedge-section copper mold. The GFA of these samples was evaluated by X-ray diffraction, differential scanning calorimetry and scanning electron microscopy. The results indicated that the gamma* parameter of compositions with high GFA is higher, corresponding to a range in which the lambda parameter is greater than 0.1, which are compositions far from Al solid solution. A new alloy was identified with the best GFA reported so far for this system, showing a maximum thickness of 286 mu m in a wedge-section copper mold. Crown Copyright (C) 2009 Published by Elsevier B.V. All rights reserved.

Modeling associations between genetic markers using Bayesian networks

Motivation: Understanding the patterns of association between polymorphisms at different loci in a population ( linkage disequilibrium, LD) is of fundamental importance in various genetic studies. Many coefficients were proposed for measuring the degree of LD, but they provide only a static view of the current LD structure. Generative models (GMs) were proposed to go beyond these measures, giving not only a description of the actual LD structure but also a tool to help understanding the process that generated such structure. GMs based in coalescent theory have been the most appealing because they link LD to evolutionary factors. Nevertheless, the inference and parameter estimation of such models is still computationally challenging. Results: We present a more practical method to build GM that describe LD. The method is based on learning weighted Bayesian network structures from haplotype data, extracting equivalence structure classes and using them to model LD. The results obtained in public data from the HapMap database showed that the method is a promising tool for modeling LD. The associations represented by the learned models are correlated with the traditional measure of LD D`. The method was able to represent LD blocks found by standard tools. The granularity of the association blocks and the readability of the models can be controlled in the method. The results suggest that the causality information gained by our method can be useful to tell about the conservability of the genetic markers and to guide the selection of subset of representative markers.

Ecodesign methods focused on remanufacturing

Understanding the product`s `end-of-life` is important to reduce the environmental impact of the products` final disposal. When the initial stages of product development consider end-of-life aspects, which can be established by ecodesign (a proactive approach of environmental management that aims to reduce the total environmental impact of products), it becomes easier to close the loop of materials. The `end-of-life` ecodesign methods generally include more than one `end-of-life` strategy. Since product complexity varies substantially, some components, systems or sub-systems are easier to be recycled, reused or remanufactured than others. Remanufacture is an effective way to maintain products in a closed-loop, reducing both environmental impacts and costs of the manufacturing processes. This paper presents some ecodesign methods focused on the integration of different `end-of-life` strategies, with special attention to remanufacturing, given its increasing importance in the international scenario to reduce the life cycle impacts of products. (C) 2009 Elsevier Ltd. All rights reserved.

A Study on Unconditionally Stable FDTD Methods for the Modeling of Metamaterials

We assess the performance of three unconditionally stable finite-difference time-domain (FDTD) methods for the modeling of doubly dispersive metamaterials: 1) locally one-dimensional FDTD; 2) locally one-dimensional FDTD with Strang splitting; and (3) alternating direction implicit FDTD. We use both double-negative media and zero-index media as benchmarks.

Aerodynamic study of three-dimensional larynx models using finite element methods

The airflow velocities and pressures are calculated from a three-dimensional model of the human larynx by using the finite element method. The laryngeal airflow is assumed to be incompressible, isothermal, steady, and created by fixed pressure drops. The influence of different laryngeal profiles (convergent, parallel, and divergent), glottal area, and dimensions of false vocal folds in the airflow are investigated. The results indicate that vertical and horizontal phase differences in the laryngeal tissue movements are influenced by the nonlinear pressure distribution across the glottal channel, and the glottal entrance shape influences the air pressure distribution inside the glottis. Additionally, the false vocal folds increase the glottal duct pressure drop by creating a new constricted channel in the larynx, and alter the airflow vortexes formed after the true vocal folds. (C) 2007 Elsevier Ltd. All rights reserved.

Data Mining Applied to Harmonic Current Sources Identification in Residential Consumers

This work proposes a method based on both preprocessing and data mining with the objective of identify harmonic current sources in residential consumers. In addition, this methodology can also be applied to identify linear and nonlinear loads. It should be emphasized that the entire database was obtained through laboratory essays, i.e., real data were acquired from residential loads. Thus, the residential system created in laboratory was fed by a configurable power source and in its output were placed the loads and the power quality analyzers (all measurements were stored in a microcomputer). So, the data were submitted to pre-processing, which was based on attribute selection techniques in order to minimize the complexity in identifying the loads. A newer database was generated maintaining only the attributes selected, thus, Artificial Neural Networks were trained to realized the identification of loads. In order to validate the methodology proposed, the loads were fed both under ideal conditions (without harmonics), but also by harmonic voltages within limits pre-established. These limits are in accordance with IEEE Std. 519-1992 and PRODIST (procedures to delivery energy employed by Brazilian`s utilities). The results obtained seek to validate the methodology proposed and furnish a method that can serve as alternative to conventional methods.

Assessment of the Performance of Acoustic and Mass Balance Methods for Leak Detection in Pipelines for Transporting Liquids

On-line leak detection is a main concern for the safe operation of pipelines. Acoustic and mass balance are the most important and extensively applied technologies in field problems. The objective of this work is to compare these leak detection methods with respect to a given reference situation, i.e., the same pipeline and monitoring signals acquired at the inlet and outlet ends. Experimental tests were conducted in a 749 m long laboratory pipeline transporting water as the working fluid. The instrumentation included pressure transducers and electromagnetic flowmeters. Leaks were simulated by opening solenoid valves placed at known positions and previously calibrated to produce known average leak flow rates. Results have clearly shown the limitations and advantages of each method. It is also quite clear that acoustics and mass balance technologies are, in fact, complementary. In general, an acoustic leak detection system sends out an alarm more rapidly and locates the leak more precisely, provided that the rupture of the pipeline occurs abruptly enough. On the other hand, a mass balance leak detection method is capable of quantifying the leak flow rate very accurately and of detecting progressive leaks.