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.

DOES THE CHRONOTYPE CLASSIFICATION NEED TO BE UPDATED? PRELIMINARY FINDINGS

Traditionally, chronotype classification is based on the Morningness-Eveningness Questionnaire (MEQ). It is implicit in the classification that intermediate individuals get intermediate scores to most of the MEQ questions. However, a small group of individuals has a different pattern of answers. In some questions, they answer as ""morning-types"" and in some others they answer as ""evening-types,"" resulting in an intermediate total score. ""Evening-type"" and ""Morning-type"" answers were set as A(1) and A(4), respectively. Intermediate answers were set as A(2) and A(3). The following algorithm was applied: Bimodality Index = (Sigma A(1) x Sigma A(4))(2) - (Sigma A(2) x Sigma A(3))(2). Neither-types that had positive bimodality scores were classified as bimodal. If our hypothesis is validated by objective data, an update of chronotype classification will be required. (Author correspondence: brunojm@ymail.com)

A study on chemical constituents and sugars extraction from spent coffee grounds

Spent coffee grounds (SCG) the residual materials obtained during the processing of raw coffee powder to prepare instant coffee are the main coffee Industry residues In the present work this material was chemically characterized and subsequently submitted to a dilute acid hydrolysis aiming to recover the hemicellulose sugars Reactions were performed according to experimental designs to verify the effects of the variables H(2)SO(4) concentration liquid-to-solid ratio temperature and reaction time on the efficiency of hydrolysis SCG was found to be rich in sugars (45 3% w/w) among of which hemicellulose (constituted by mannose galactose and arabinose) and cellulose (glucose homopolymer) correspond to 367% (w/w) and 8 6% (w/w) respectively Optimal conditions for hemicellulose sugars extraction consisted in using 100 mg acid/g dry matter 10g liquid/g solid at 163 degrees C for 45 min Under these conditions hydrolysis efficiencies of 100% 774% and 895% may be achieved for galactan mannan and arabinan respectively corresponding to a hemicellulose hydrolysis efficiency of 874% (C) 2010 Elsevier Ltd All rights reserved

Influence of gelation time on the morphological and physico-chemical properties of the sol-gel entrapped lipase

Different gelation times (4, 18, 24 and 48 h) were used for the preparation of silica sol-gel supports and encapsulated Candida rugosa lipase using tetraethoxysilane (TEOS) as precursor. The hydrophobic matrices and immobilized lipases produced were characterized with regard to pore volume and size by nitrogen adsorption (BJH method), weight loss upon heating (TGA), differential scanning calorimetry (DSC), scanning electron microscopy (SEM), chemical composition (FTIR) and percentage of hydrolysis (POH%) of olive oil. These structural parameters were found to change with the gelation time, but no direct relation was found between the percentage of oil hydrolysis (POH%) and the gelation time. The best combination of high thermal stability and high POH% (99.5%) occurred for encapsulated lipase produced with 24 h gelation time. (C) 2007 Elsevier B.V. All rights reserved.

Chemical composition and sensory analysis of cheese whey-based beverages using kefir grains as starter culture

P>The aim of the present work was to evaluate the use of the kefir grains as a starter culture for tradicional milk kefir beverage and for cheese whey-based beverages production. Fermentation was performed by inoculating kefir grains in milk (ML), cheese whey (CW) and deproteinised cheese whey (DCW). Erlenmeyers containing kefir grains and different substrates were statically incubated for 72 h at 25 degrees C. Lactose, ethanol, lactic acid, acetic acid, acetaldehyde, ethyl acetate, isoamyl alcohol, isobutanol, 1-propanol, isopentyl alcohol and 1-hexanol were identified and quantified by high-performance liquid chromatography and GC-FID. The results showed that kefir grains were able to utilise lactose in 60 h from ML and 72 h from CW and DCW and produce similar amounts of ethanol (similar to 12 g L-1), lactic acid (similar to 6 g L-1) and acetic acid (similar to 1.5 g L-1) to those obtained during milk fermentation. Based on the chemical characteristics and acceptance in the sensory analysis, the kefir grains showed potential to be used for developing cheese whey-based beverages.

Multipoint covalent immobilization of lipase on chitosan hybrid hydrogels: influence of the polyelectrolyte complex type and chemical modification on the catalytic properties of the biocatalysts

This work aimed at the production of stabilized derivatives of Thermomyces lanuginosus lipase (TLL) by multipoint covalent immobilization of the enzyme on chitosan-based matrices. The resulting biocatalysts were tested for synthesis of biodiesel by ethanolysis of palm oil. Different hydrogels were prepared: chitosan alone and in polyelectrolyte complexes (PEC) with kappa-carrageenan, gelatin, alginate, and polyvinyl alcohol (PVA). The obtained supports were chemically modified with 2,4,6-trinitrobenzene sulfonic acid (TNBS) to increase support hydrophobicity, followed by activation with different agents such as glycidol (GLY), epichlorohydrin (EPI), and glutaraldehyde (GLU). The chitosan-alginate hydrogel, chemically modified with TNBS, provided derivatives with higher apparent hydrolytic activity (HA(app)) and thermal stability, being up to 45-fold more stable than soluble lipase. The maximum load of immobilized enzyme was 17.5 mg g(-1) of gel for GLU, 7.76 mg g(-1) of gel for GLY, and 7.65 mg g(-1) of gel for EPI derivatives, the latter presenting the maximum apparent hydrolytic activity (364.8 IU g(-1) of gel). The three derivatives catalyzed conversion of palm oil to biodiesel, but chitosan-alginate-TNBS activated via GLY and EPI led to higher recovered activities of the enzyme. Thus, this is a more attractive option for both hydrolysis and transesterification of vegetable oils using immobilized TLL, although industrial application of this biocatalyst still demands further improvements in its half-life to make the enzymatic process economically attractive.

Classification of normal swallowing and oropharyngeal dysphagia using wavelet

Oropharyngeal dysphagia is characterized by any alteration in swallowing dynamics which may lead to malnutrition and aspiration pneumonia. Early diagnosis is crucial for the prognosis of patients with dysphagia, and the best method for swallowing dynamics assessment is swallowing videofluoroscopy, an exam performed with X-rays. Because it exposes patients to radiation, videofluoroscopy should not be performed frequently nor should it be prolonged. This study presents a non-invasive method for the pre-diagnosis of dysphagia based on the analysis of the swallowing acoustics, where the discrete wavelet transform plays an important role to increase sensitivity and specificity in the identification of dysphagic patients. (C) 2008 Elsevier Inc. All rights reserved.

A classification methodology for the risk of weed infestation using fuzzy logic

Despite modern weed control practices, weeds continue to be a threat to agricultural production. Considering the variability of weeds, a classification methodology for the risk of infestation in agricultural zones using fuzzy logic is proposed. The inputs for the classification are attributes extracted from estimated maps for weed seed production and weed coverage using kriging and map analysis and from the percentage of surface infested by grass weeds, in order to account for the presence of weed species with a high rate of development and proliferation. The output for the classification predicts the risk of infestation of regions of the field for the next crop. The risk classification methodology described in this paper integrates analysis techniques which may help to reduce costs and improve weed control practices. Results for the risk classification of the infestation in a maize crop field are presented. To illustrate the effectiveness of the proposed system, the risk of infestation over the entire field is checked against the yield loss map estimated by kriging and also with the average yield loss estimated from a hyperbolic model.

Atmospheric impacts of the life cycle emissions of fuel ethanol in Brazil: based on chemical exergy

An assessment is made of the atmospheric emissions from the life cycle of fuel ethanol coupled with the cogeneration of electricity from sugarcane in Brazil. The total exergy loss from the most quantitative relevant atmospheric emission substances produced by the life cycle of fuel ethanol is 3.26E+05 kJ/t of C(2)H(5)OH, Compared with the chemical exergy of 1 t of ethanol (calculated as 34.56E + 06 kJ). the exergy loss from the life cycle`s atmospheric emission represents 1.11% of the product`s exergy. The activity that most contributes to atmospheric emission chemical exergy losses is the harvesting of sugarcane through the methane emitted in burning. Suggestions for improved environmental quality and greater efficiency of the life cycle of fuel ethanol with cogenerated energy are: harvesting the sugarcane without burning, renewable fuels should be used in tractors, trucks and buses instead of fossil fuel and the transportation of products and input should be logistically optimized. (C) 2009 Elsevier Ltd. All rights reserved.

Physical-chemical and operational performance of an anaerobic baffled reactor (ABR) treating swine wastewater

Since hog raising concentrates a huge amount of swine manure in small areas, it is considered by the environmental government organizations to be one of the most potentially pollutant activities. Therefore the main objective of this research was to evaluate by operational criteria and removal efficiency, the performance of a Anaerobic Baffled Reactor (ABR), working as a biological pre-treatment of swine culture effluents. The physical-chemical analyses carried out were: total COD, BOD(5), total solids (TS), fix (TFS) and volatiles (TVS), temperature, pH, total Kjeldahl nitrogen, phosphorus, total acidity and alkalinity. The ABR unit worked with an average efficiency of 65.2 and 76.2%, respectively, concerning total COD and BOD(5), with a hydraulic retention time (HRT) about 15 hours. The results for volumetric organic loading rate (VOLR), organic loading rate (OLR) and hydraulic loading rate (HLR) were: 4.46 kg BOD m(-3) day(-1); 1.81 kg BOD(5) kg TVS(-1) day(-1) and 1.57 m(3) m(-3) day(-1), respectively. The average efficiency of the whole treatment system for total COD and BOD(5) removal were 66.5 and 77.8%, showing an adequate performance in removing die organic matter from swine wastewater.

On the classification of mixed construction and demolition waste aggregate by porosity and its impact on the mechanical performance of concrete

The properties of recycled aggregate produced from mixed (masonry and concrete) construction and demolition (C&D) waste are highly variable, and this restricts the use of such aggregate in structural concrete production. The development of classification techniques capable of reducing this variability is instrumental for quality control purposes and the production of high quality C&D aggregate. This paper investigates how the classification of C&D mixed coarse aggregate according to porosity influences the mechanical performance of concrete. Concretes using a variety of C&D aggregate porosity classes and different water/cement ratios were produced and the mechanical properties measured. For concretes produced with constant volume fractions of water, cement, natural sand and coarse aggregate from recycled mixed C&D waste, the compressive strength and Young modulus are direct exponential functions of the aggregate porosity. Sink and float technique is a simple laboratory density separation tool that facilitates the separation of cement particles with lower porosity, a difficult task when done only by visual sorting. For this experiment, separation using a 2.2 kg/dmA(3) suspension produced recycled aggregate (porosity less than 17%) which yielded good performance in concrete production. Industrial gravity separators may lead to the production of high quality recycled aggregate from mixed C&D waste for structural concrete applications.

Chemical characterization of a high nitrogen stainless steel by optimized electron probe microanalysis

The distribution of Cr and N in a high-temperature gas-nitrided stainless steel was measured by using a scanning electron microscope-coupled wavelength-dispersive X-ray spectrometer and the results were related to the microhardness profile of the hardened case. The experimental spectrometric procedure was optimized to consistently measure N contents varying between 0.1 and 0.8 wt.% in martensite and between 18.3 and 21.6 wt.% in nitrides, as well as Cr contents ranging from 11.5 to 17.0 wt.%. (C) 2010 Acta Materialia Inc. Published by Elsevier Ltd. All rights reserved.

Chemical characterization and anticorrosion properties of corrosion products formed on pure copper in synthetic rainwater of Rio de Janeiro and Sao Paulo

This work aims to characterize corrosion products formed on copper samples exposed to synthetic rainwater of Rio Janeiro and Sao Paulo. XRD and XPS were employed to determine their composition, while electrochemical techniques were used to evaluate their protective properties. XRD and XPS indicated the thickening of the corrosion layer with time. Electrochemical results showed that the protectiveness of the corrosion layer depends on the solution composition. Based on our findings a corrosion mechanism for copper in simulated rainwater is proposed where the role of NH(4)(+) ions in the cuprite layer partial regeneration is taken into account. (C) 2009 Elsevier Ltd. All rights reserved.

THE EFFECT OF REFRIGERATED STORAGE ON SENSORY PROFILE AND PHYSICAL-CHEMICAL CHARACTERISTICS OF MINIMALLY PASTEURIZED ORANGE JUICE

Minimal pasteurization of orange juice (OJ) consists of using minimum holding time and temperature to ensure partial inactivation of pectin methylesterase (PME). This process produces juice with preserved sensory attributes and has a better acceptance by consumers when compared with commercially pasteurized OJ. Sensory profile and physical-chemical characteristics of minimally processed OJ was determined, during refrigerated storage, for two OJ blends with different pH values and the same level of PME thermal inactivation. A selected and trained sensorial panel (n = 16) performed sensory analysis, based on a quantitative descriptive analysis, twice a week for 30 days, evaluating the attributes of appearance (suspended particles and color intensity), odor (natural orange and fermented orange) and flavor (orange characteristic, fermented orange, acid and bitter taste). Storage presented great effect on OJ sensory profile; however, it was not noticeable on physical-chemical characteristics.

Influence of substrate surface topography in the deposition of nanostructured diamond-like carbon films by high density plasma chemical vapor deposition

In this work, we have studied the influence of the substrate surface condition on the roughness and the structure of the nanostructured DLC films deposited by High Density Plasma Chemical Vapor Deposition. Four methods were used to modify the silicon wafers surface before starting the deposition processes of the nanostructured DLC films: micro-diamond powder dispersion, micro-graphite powder dispersion, and roughness generation by wet chemical etching and roughness generation by plasma etching. The reference wafer was only submitted to a chemical cleaning. It was possible to see that the final roughness and the sp(3) hybridization degree strongly depend on the substrate surface conditions. The surface roughness was observed by AFM and SEM and the hybridization degree of the DLC films was analyzed by Raman Spectroscopy. In these samples, the final roughness and the sp(3) hybridization quantity depend strongly on the substrate surface condition. Thus, the effects of the substrate surface on the DLC film structure were confirmed. These phenomena can be explained by the fact that the locally higher surface energy and the sharp edges may induce local defects promoting the nanostructured characteristics in the DLC films. (C) 2008 Elsevier B.V. All rights reserved.