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.

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.

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

State of Sao Paulo Research Foundation (FAPESP)

Remote control of CNC machines using the CyberOPC communication system over public networks

During the last few years, the evolution of fieldbus and computers networks allowed the integration of different communication systems involving both production single cells and production cells, as well as other systems for business intelligence, supervision and control. Several well-adopted communication technologies exist today for public and non-public networks. Since most of the industrial applications are time-critical, the requirements of communication systems for remote control differ from common applications for computer networks accessing the Internet, such as Web, e-mail and file transfer. The solution proposed and outlined in this work is called CyberOPC. It includes the study and the implementation of a new open communication system for remote control of industrial CNC machines, making the transmission delay for time-critical control data shorter than other OPC-based solutions, and fulfilling cyber security requirements.

Comparison Between Voltage Control Structures of Synchronous Machines

This paper compares the behaviour of two different control structures of automatic voltage regulators of synchronous machines equipped with static excitation systems. These systems have a fully controlled thyristor bridge that supplies DC current to the rotor winding. The rectifier bridge is fed by the stator terminals through a step-down transformer. The first control structure, named ""Direct Control"", has a single proportional-integral (PI) regulator that compares stator voltage setpoint with measured voltage and acts directly on the thyristor bridge`s firing angle. This control structure is usually employed in commercial excitation systems for hydrogenerators. The second structure, named ""Cascade Control"", was inspired on control loops of commercial DC motor drives. Such drives employ two PIs in a cascade arrangement, the external PI deals with the motor speed while the internal one regulates the armature current. In the adaptation proposed, the external PI compares setpoint with the actual stator voltage and produces the setpoint to the internal PI-loop which controls the field current.

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.

Alternative body sites for heat stress measurement in milking cows under tropical conditions and their relationship to the thermal discomfort of the animals

This study was conducted to determine the relationship among temperatures measured at different anatomical sites of the animal body and their daily pattern as indicative of the thermal stress in lactating dairy cows under tropical conditions. Environmental dry bulb (DBT) and black globe (BGT) temperatures and relative humidity (RH) were recorded. Rectal temperature (RT), respiratory frequency (RF), body surface (BST), internal base of tail (TT), vulva (VT) and auricular temperatures (AT) were collected, from 37 Black and White Holstein cows at 0700, 1300 and 1800 hours. RT showed a moderately and positive correlations with all body temperatures, ranging from 0.59 with TT to 0.64 with BST. Correlations among AT, VT and TT with RF were very similar (from 0.63 to 0.64) and were greater than those observed for RF with RT (0.55) or with BST (0.54). RF and RT were positively correlated to TT (0.63 and 0.59, respectively), AT (r = 0.63 for both) and VT (r = 0.64 and 0.63, respectively). Positive and very high correlations were observed among AT, VT and TT (from 0.94 to 0.97) indicating good association of temperatures measured in these anatomical sites. Correlations of BST with AT and VT were positive and very similar (0.71 and 0.72, respectively) and lower with TT (0.66). The AT, TT, VT and BST presented similar patterns and follow the variations of DBT through the day. Temperatures measured at different anatomical sites of the animal body have the potential to be used as indicative of the thermal stress in lactating dairy cows.

Hormone release and behavior during suckling and milking in Gir, Gir x Holstein, and Holstein cows

There are several different milking management systems in Latin America, because Gir cattle are reputed to be easily stressed and not well adapted to machine-milking. This paper, therefore, provides an overview of hormone release and behavior during suckling and milking in Gir cows and their crossbred offspring. Several experiments were performed to study oxytocin release during exclusive suckling or exclusive hand- and machine-milking, oxytocin, and prolactin release during a mixed suckling-milking system and oxytocin release after weaning. Cortisol concentrations and behavior were also examined. Concentration of oxytocin, released during suckling, and both types of milking were high, but the maximum concentration measured during suckling was significantly greater than that observed during exclusive milking. In the mixed suckling-milking system, the greatest oxytocin and prolactin releases were measured during suckling. Cortisol concentrations measured before, during, and after milking demonstrated that Gir x Holstein and Holstein cows were not stressed. On the other hand, although Gir had greater concentrations of cortisol, the percentage of residual milk for Gir cows was less than for dairy cows exposed to different stressful situations. In general, Gir cows and their crossbred offspring adapted to machine-milking, although these breeds can react negatively to milkers. Gir, Gir x Holstein, and Holstein cows all had similar cortisol levels during and after milking.

Checking Completeness of Tests for Finite State Machines

In testing from a Finite State Machine (FSM), the generation of test suites which guarantee full fault detection, known as complete test suites, has been a long-standing research topic. In this paper, we present conditions that are sufficient for a test suite to be complete. We demonstrate that the existing conditions are special cases of the proposed ones. An algorithm that checks whether a given test suite is complete is given. The experimental results show that the algorithm can be used for relatively large FSMs and test suites.

Morfometria e distribuição de leite alveolar e cisternal na glândula mamária de vacas Holandesa e Girolanda

Estudaram-se a distribuição do leite nas porções alveolar e cisternal e a morfometria da glândula mamária de 14 vacas, sete da raça Holandesa, grupo H, e sete da Girolanda, grupo G, com ordem e dias de lactação semelhantes, ordenhadas duas vezes ao dia. A produção de leite foi mensurada diariamente, enquanto as frações de leite cisternal e alveolar foram medidas uma vez por semana. Durante o experimento, também foram realizadas medidas de ultrassonografia e morfometria da glândula mamária. As vacas Girolandas apresentaram úberes e tetos maiores que as vacas Holandesas. Diâmetro, espessura da parede e comprimento do canal do teto, medidos por imagens de ultrassom, também foram maiores nas Girolandas, mas a área de cisterna da glândula mamária foi maior nas Holandesas. Não houve diferença na produção de leite e nas frações de leite cisternal e alveolar entre as raças.

Productive performance and milk protein fraction composition of dairy cows supplemented with sodium monensin

The objective of this work was to evaluate the levels of sodium monensin on lactating cows and their effects on productive performance and milk protein fraction composition. It was used 12 Holstein cows, distributed in four balanced 3 × 3 Latin squares, and fed three diets: one control without monensin, and two diets with monensin at the levels of 24 or 48 mg/kg DM added to the concentrate. Milk production was daily measured throughout the entire experimental period. The samples used for analysis of milk composition were collected on two alternated days from the two daily milking. Non-protein nitrogen, total nitrogen and non-casein nitrogen contents were directly evaluated in the milk, and casein, whey protein and true protein contents were indirectly determined. The use of monensin in the rations reduced dry matter and nutrient intake, especially when diet with 48 mg/kg of dry matter was given. The ration with 24 mg/kg of DM increased milk production, with or without correction, and also fat and lactose yield, and it improved productive efficiency. The levels of monensin in the ratios did not influence contents of milk crude protein, non-protein nitrogen, non-casein nitrogen, true protein, casein, casein/true protein ratio, whey protein, and of all those fractions expressed as percentage of crude protein. The utilization of monensin in the ratio at the dose of 24 mg/kg of DM influences positively the productive performance of lactating cows, and it does not influence the composition of milk protein fractions.

Productive performance and composition of milk protein fraction in dairy cows supplemented with fat sources

The objective of this study was to evaluate the use of fat sources in rations for lactating cows on the productive performance and composition of milk protein fraction. Twelve Holstein cows were used, grouped in three balanced 4 × 4 Latin squares, fed with the following rations: control; refined soybean oil; whole raw soybean; and calcium salts of unsaturated fatty acid (Megalac-E). Dry matter and nutrient intake, and daily milk production were evaluated. The samples used to analyze milk composition were collected in two alternate days and were obtained from two daily milking. Milk composition and total nitrogen, non-protein nitrogen and non-casein nitrogen ratios were analyzed. The casein, serum protein and true protein ratios were obtained by difference. Dry matter and nutrient intakes were lower when cows received the diet containing calcium salts of fatty acids, in relation to the control diet. Among the diets with fat sources, the one with whole raw soybean and calcium salts decreased milk production. There was no effect of fat sources added to the diet on crude protein, non-protein nitrogen, non-casein nitrogen, true protein, casein, casein/milk true protein ratio and serum protein. Similarly, the experimental diets did not influence the protein fractions when expressed in percentage of milk crude protein. The utilization of fat sources in diets changes milk production and composition of lactating cows, but does not influence the composition of milk protein fractions.

Ornato e despojamento no mundo fabril

O artigo investiga algumas das tendências da arquitetura gerada por fábricas - galpões industriais, moradias, igrejas, escolas, clubes etc. -, erguida no Brasil entre as duas últimas décadas do século XIX e as primeiras do XX. Apoia-se em amplo inventário, como base para um esforço de análise que se propõe a identificar os temas e usos predominantes dos ornatos aplicados a construções geradas por fábricas, as referências historicistas mobilizadas e eventuais rupturas de signos arquitetônicos tipológicos, e, no limite, a abolição de ornatos e dos referidos signos. Assim, de um lado, trata da penetração da linguagem eclética nessas construções, investigando o repertório formal utilizado em diferentes tipologias. De outro, trata da simultânea difusão de uma estética tipicamente fabril, fundamentada em noções de economia, eficiência, utilidade e funcionalidade. Mostra como tais noções se expressam ora em uma simplificação ou ausência de ornatos, ora no uso de ornatos cujos temas remetem ao mundo das máquinas; às vezes, no distanciamento ou abandono de signos arquitetônicos tipológicos consagrados; ou, ainda, no emprego de materiais produzidos industrialmente e que se difundiram a partir, sobretudo, da arquitetura de fábricas.

Crowbar System in Doubly Fed Induction Wind Generators

In the last 15 years, the use of doubly fed induction machines in modern variable-speed wind turbines has increased rapidly. This development has been driven by the cost reduction as well as the low-loss generation of Insulated Gate Bipolar Transistors (IGBT). According to new grid code requirements, wind turbines must remain connected to the grid during grid disturbances. Moreover, they must also contribute to voltage support during and after grid faults. The crowbar system is essential to avoid the disconnection of the doubly fed induction wind generators from the network during faults. The insertion of the crowbar in the rotor circuits for a short period of time enables a more efficient terminal voltage control. As a general rule, the activation and the deactivation of the crowbar system is based only on the DC-link voltage level of the back-to-back converters. In this context, the authors discuss the critical rotor speed to analyze the instability of doubly fed induction generators during grid faults.