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.

Quantitative assessment of postural alignment in young adults based on photographs of anterior, posterior, and lateral views

Objective: Postural assessment through photography is a simple method that allows the acquisition of quantitative values to define the alignment of body segments. The purpose of this study was to quantitatively assess the postural alignment of several body segments in standing through anterior, posterior, and lateral views. Methods: In this cross-sectional study, 122 subjects were initially evaluated. Seven subjects were excluded from the study after cluster analysis. The final sample had 115 subjects, 75% women with a mean age of 26 + 7 years. Photographs were taken from anterior, posterior, and lateral views after placement of markers on specific anatomical points. Photographs were analyzed using free Postural Analysis Software/Software of Postural Analysis (PAS/SAPO). Quantitative values for postural analysis variables were ascertained for head, upper and lower limbs, and trunk, along with the frequency of inclinations to the left and to the right. Results: Regarding the head, 88% of the sample presented some inclination, 67% of which was to the right. There was a predominance of right inclination of the shoulder and pelvis in 68% and 43% of study subjects, respectively. Lower limbs presented mean alignment of 178 in the anterior view, and the trunk showed predominant right inclination in 66% of participants. Conclusion: Small asymmetries were observed in anterior and posterior views. This study suggests that there is no symmetry in postural alignment and that small asymmetries represent the normative standard for posture in standing. (J Manipulative Physiol Ther 2011;34:371-380)

Learning benefits of self-controlled knowledge of results in 10-year-old children

PIBIC-CNPq-Conselho Nacional de Desenvolvimento Cientifico e Technologico

Constant-random practice and the adaptive process in motor learning with varying amounts of constant practice

The adaptive process in motor learning was examined in terms of effects of varying amounts of constant practice performed before random practice. Participants pressed five response keys sequentially, the last one coincident with the lighting of a final visual stimulus provided by a complex coincident timing apparatus. Different visual stimulus speeds were used during the random practice. 33 children (M age=11.6 yr.) were randomly assigned to one of three experimental groups: constant-random, constant-random 33%, and constant-random 66%. The constant-random group practiced constantly until they reached a criterion of performance stabilization three consecutive trials within 50 msec. of error. The other two groups had additional constant practice of 33 and 66%, respectively, of the number of trials needed to achieve the stabilization criterion. All three groups performed 36 trials under random practice; in the adaptation phase, they practiced at a different visual stimulus speed adopted in the stabilization phase. Global performance measures were absolute, constant, and variable errors, and movement pattern was analyzed by relative timing and overall movement time. There was no group difference in relation to global performance measures and overall movement time. However, differences between the groups were observed on movement pattern, since constant-random 66% group changed its relative timing performance in the adaptation phase.

Effect of bandwidth knowledge of results on the learning of a grip force control task

An experiment was conducted to investigate the persistence of the effect of ""bandwidth knowledge of results (KR)"" manipulated during the learning phase of performing a manual force-control task. The experiment consisted of two phases, an acquisition phase with the goal of maintaining 60% maximum force in 30 trials, and a second phase with the objective of maintaining 40% of maximum force in 20 further trials. There were four bandwidths of KR: when performance error exceeded 5, 10, or 15% of the target, and a control group (0% bandwidth). Analysis showed that 5, 10, and 15% bandwidth led to better performance than 0% bandwidth KR at the beginning of the second phase and persisted during the extended trials.

A Semi-Tethered Test for Power Assessment in Running

We analyzed the usefulness of a semi-tethered field running test (STR) and the relationships between indices of anaerobic power, anaerobic capacity and running performance in 9 trained male sprinters (22.2 +/- 2.9 yrs, 176 +/- 1 cm, 68.0 +/- 9.4 kg). STR involved an all out 120 m run attached to an apparatus that enabled power calculation from force and velocity measures. Subjects also carried out a cycloergometer Win-gate Anaerobic Test (WT), an all out 300 m run and had accessed their maximal accumulated oxygen deficit (MAOD) on a treadmill. Peak and mean powers attained in STR (1 720 +/- 221 and 1 391 +/- 201 W) were greater but significantly related (r=0.82; P<0.01) to those in the WT (808 +/- 130 and 603 +/- 87 W). In addition, power measures derived from the STR were stronger related to running performance compared to those from the WT (r=0.81-0.94 vs. 0.68-0.84; P<0.05). Relationships between MAOD and most power indices were only weak to moderate. These results support the usefulness of STR for specific power assessment in field running and suggest that anaerobic power and capacity are not related entities, irrespective of having been evaluated using similar or dissimilar exercise modes.

Assessment of Depressive Symptoms and Cognitive Impairment in Elders From Rural Areas of the Brazilian State of Rio Grande do Sul

The main objective of this study was to examine the relationships among demographic characteristics, depressive symptoms, and cognitive impairment in oldest-old elders from rural areas of the Brazilian State of Rio Grande do Sul. A cross-sectional, descriptive correlational design was used to conduct the study. 137 Brazilian elders age 80 years or over. A target population data form, a county data form, a demographic questionnaire, the Mini-Mental State Examination, and the Depressive Cognition Scale were used to collect the data. A significant difference was found between males and females in regard to cognitive impairment. In addition, educational level and depressive symptoms were correlated with cognitive impairment. Depressive symptoms were a weak but significant predictor of cognitive impairment after controlling for the effect of age, gender, and educational level of the oldest-old elders. The findings need to be interpreted cautiously since the sample scored above the cutoff points for cognitive impairment, and had low scores on depressive symptoms. Despite several limitations, findings from this study can be a foundation for further studies, and well-designed correlational or experimental approaches, are warranted.

Roles assessment in families of children with chronic renal failure on peritoneal dialysis

Families with a child on chronic peritoneal dialysis have to assume a significant burden of care, intensifying the demands and the reorganization of roles in the families of children. The purpose of this study is to describe the implications of role changes in families of children with chronic renal disease on peritoneal dialysis. This is a case study of four families of children with chronic renal disease on peritoneal dialysis. Fourteen family members participate in the study. After the child`s chronic kidney failure and the start of treatment, each relative`s ways, acts and functions are changed, maintained or adapted to the new family dynamics, imposed by the child`s treatment conditions. Appropriate role assessment provides the nurse and the families of children with chronic renal failure on peritoneal dialysis with insight regarding current and potential health problems and aids in identifying the needs of the families.

Upper limb assessment in tetraplegia: clinical, functional and kinematic correlations

The aim of this study was to correlate clinical and functional evaluations with kinematic variables of upper limp reach-to-grasp movement in patients with tetraplegia. Twenty chronic patients were selected to perform reach-to-grasp kinematic assessment using a target placed at a distance equal to the arm`s length. Kinematic variables (hand peak velocity, movement time, percent time-to-maximal velocity, index of curvature, number of peaks, and joint range of motion) were correlated to clinical (Standard Neurological Classification of Spinal Cord Injury-American Spinal Injury Association) and functional [Functional Independence Measure (FIM) and Spinal Cord Independence Measure II (SCIM II)) evaluation scores. Twenty control participants were also selected to obtain normal reference parameters. There was a positive correlation between total motor index and FIM (r=0.6089; P=0.0044) and SCIM II (r=0.5229; P=0.018). Both functional scores showed positive correlation with each other (r=0.8283; P<0.0001). A correlation was also observed between the right and left motor indices, the motor AM, and the SCIM II in most of the reach-to-grasp kinematic variables studied (hand peak velocity, movement time, index of curvature, and number of peaks). In contrast, for the joint range of motion (shoulder, elbow, and wrist), only the wrist in the horizontal plane showed correlation with clinical variables. This study shows that muscle strength assessed by the American Spinal Injury Association motor index influences the reach-to-grasp kinematic variables of patients with tetraplegia. However, the functional assessments did not present the same influence.

Electrical stimulation and treadmill gait in tetraplegic patients: assessment of its effects on the knee with magnetic resonance imaging

Study design: Evaluation of knees of tetraplegic patients who have been walking for several months with the aid of a system that involves neuromuscular stimulation, treadmill and a harness support device. Objectives: To investigate if the training program could cause knee injury to tetraplegic patients. Setting: Hospital das Clinicas - UNICAMP. Campinas-SP, Brazil. Methods: Nine patients were evaluated. Clinical exam and magnetic resonance images (MRIs) were used for evaluation. MRIs were taken before and after the training program, in a 6-month interval for each patient. There were two sessions of training every week. Each session lasted 20 min. Results: No severe clinical abnormality was observed in any patient. Mild knee injury was observed in four of nine patients studied. Conclusions: Tetraplegic patients undergoing treadmill gait training deserve a close follow-up to prevent knee injury.

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.

Coupled reliability and boundary element model for probabilistic fatigue life assessment in mixed mode crack propagation

Fatigue and crack propagation are phenomena affected by high uncertainties, where deterministic methods fail to predict accurately the structural life. The present work aims at coupling reliability analysis with boundary element method. The latter has been recognized as an accurate and efficient numerical technique to deal with mixed mode propagation, which is very interesting for reliability analysis. The coupled procedure allows us to consider uncertainties during the crack growth process. In addition, it computes the probability of fatigue failure for complex structural geometry and loading. Two coupling procedures are considered: direct coupling of reliability and mechanical solvers and indirect coupling by the response surface method. Numerical applications show the performance of the proposed models in lifetime assessment under uncertainties, where the direct method has shown faster convergence than response surface method. (C) 2010 Elsevier Ltd. All rights reserved.

Biodegradability and toxicity assessment of bleach plant effluents treated anaerobically

As part of an experimental project on the treatment of bleach plant effluents the results of biodegradability and toxicity assessment of effluents from a bench-scale horizontal anaerobic immobilized bioreactor (HAIB) are discussed in this paper. The biodegradability of the bleach plant effluents from a Kraft pulp mill treated in the HAIB was evaluated using the modified Zahn-Wellens test. The inoculum came from a pulp mill wastewater treatment plant and the dissolved organic carbon (DOC) was used as the indicator of organic matter removal. The acute and chronic toxicity removal during the anaerobic treatment was estimated using Daphnia similis and Ceriodaphnia silvestrii respectively. Moreover, the evaluation of chromosome aberrations (CA), micronucleus frequencies (MN) and mitotic index (IM) in Allium cepa cells were used as genotoxicity indicators. The results indicate that the effluents from the anaerobic reactor are amenable to aerobic polishing. Acute and chronic toxicity were reduced by 90 and 81%, respectively. The largest CA and MN incidence in the meristematic cells of A. cepa were observed after exposure to the raw bleach plant effluent. The HAIB was able to reduce the acute and chronic toxicity as well as chromosome aberrations and the occurrence of micronucleus.

Assessment of groundwater recharge and water fluxes of the Guarani Aquifer System, Brazil

The groundwater recharge and water fluxes of the Guarani Aquifer System in the state of Sao Paulo in Brazil were assessed through a numeric model. The study area (6,748 km(2)) comprises Jacar,-Gua double dagger A(0) and Jacar,-Pepira River watersheds, tributaries of the Tiet River in the central region of the state. GIS based tools were used in the storage, processing and analysis of data. Main hydrologic phenomena were selected, leading to a groundwater conceptual model, taking into account the significant outcrops occurring in the study area. Six recharge zones were related to the geologic formation and structures of the semi-confined and phreatic aquifer. The model was calibrated against the baseflows and static water levels of the wells. The results emphasize the strong interaction of groundwater flows between watersheds and the groundwater inflow into the rivers. It has been concluded that lateral groundwater exchanges between basins, the deep discharges to the regional system, and well exploitation were not significant aquifer outflows when compared to the aquifer recharge. The results have shown that the inflows from the river into the aquifer are significant and have the utmost importance since the aquifer is potentially more vulnerable in these places.

Lifecycle assessment of fuel ethanol from sugarcane in Brazil

This paper presents the lifecycle assessment (LCA) of fuel ethanol, as 100% of the vehicle fuel, from sugarcane in Brazil. The functional unit is 10,000 km run in an urban area by a car with a 1,600-cm(3) engine running on fuel hydrated ethanol, and the resulting reference flow is 1,000 kg of ethanol. The product system includes agricultural and industrial activities, distribution, cogeneration of electricity and steam, ethanol use during car driving, and industrial by-products recycling to irrigate sugarcane fields. The use of sugarcane by the ethanol agribusiness is one of the foremost financial resources for the economy of the Brazilian rural area, which occupies extensive areas and provides far-reaching potentials for renewable fuel production. But, there are environmental impacts during the fuel ethanol lifecycle, which this paper intents to analyze, including addressing the main activities responsible for such impacts and indicating some suggestions to minimize the impacts. This study is classified as an applied quantitative research, and the technical procedure to achieve the exploratory goal is based on bibliographic revision, documental research, primary data collection, and study cases at sugarcane farms and fuel ethanol industries in the northeast of SA o pound Paulo State, Brazil. The methodological structure for this LCA study is in agreement with the International Standardization Organization, and the method used is the Environmental Design of Industrial Products. The lifecycle impact assessment (LCIA) covers the following emission-related impact categories: global warming, ozone formation, acidification, nutrient enrichment, ecotoxicity, and human toxicity. The results of the fuel ethanol LCI demonstrate that even though alcohol is considered a renewable fuel because it comes from biomass (sugarcane), it uses a high quantity and diversity of nonrenewable resources over its lifecycle. The input of renewable resources is also high mainly because of the water consumption in the industrial phases, due to the sugarcane washing process. During the lifecycle of alcohol, there is a surplus of electric energy due to the cogeneration activity. Another focus point is the quantity of emissions to the atmosphere and the diversity of the substances emitted. Harvesting is the unit process that contributes most to global warming. For photochemical ozone formation, harvesting is also the activity with the strongest contributions due to the burning in harvesting and the emissions from using diesel fuel. The acidification impact potential is mostly due to the NOx emitted by the combustion of ethanol during use, on account of the sulfuric acid use in the industrial process and because of the NOx emitted by the burning in harvesting. The main consequence of the intensive use of fertilizers to the field is the high nutrient enrichment impact potential associated with this activity. The main contributions to the ecotoxicity impact potential come from chemical applications during crop growth. The activity that presents the highest impact potential for human toxicity (HT) via air and via soil is harvesting. Via water, HT potential is high in harvesting due to lubricant use on the machines. The normalization results indicate that nutrient enrichment, acidification, and human toxicity via air and via water are the most significant impact potentials for the lifecycle of fuel ethanol. The fuel ethanol lifecycle contributes negatively to all the impact potentials analyzed: global warming, ozone formation, acidification, nutrient enrichment, ecotoxicity, and human toxicity. Concerning energy consumption, it consumes less energy than its own production largely because of the electricity cogeneration system, but this process is highly dependent on water. The main causes for the biggest impact potential indicated by the normalization is the nutrient application, the burning in harvesting and the use of diesel fuel. The recommendations for the ethanol lifecycle are: harvesting the sugarcane without burning; more environmentally benign agricultural practices; renewable fuel rather than diesel; not washing sugarcane and implementing water recycling systems during the industrial processing; and improving the system of gases emissions control during the use of ethanol in cars, mainly for NOx. Other studies on the fuel ethanol from sugarcane may analyze in more details the social aspects, the biodiversity, and the land use impact.