Accuracy alone can be deceptive when evaluating the performance of a classifier, especially if the problem involves a high number of classes. This paper proposes an approach used for dealing with multi-class problems, which tries to avoid this issue. The approach is based on the Extreme Learning Machine (ELM) classifier, which is trained by using a Differential Evolution (DE) algorithm. Two error measures (Accuracy, $C$, and Sensitivity, S) are combined and applied as a fitness function for the algorithm. The proposed approach is able to obtain multi-class classifiers with a high classification rate level in the global dataset with an acceptable level of accuracy for each class. This methodology is evaluated over seven benchmark classification problems and one real problem, obtaining promising results.
The soil engineer needs to be able to readily identify difficult or problematic soils and to determine the amount of settlement that may occur. This paper deals with the assessment and identification of three types of difficult soils: collapsible soils, swelling soils, and liquefiable soils. In the first instance, the study investigates the effect of some soil properties on wetting-induced collapse strain and the swelling potential of soils. Also, two new methods for predicting soil collapse and swelling potential are developed. The proposed relationships correlate between collapse strain and swelling potential and some soil parameters which are believed to govern soil collapse and swelling. Validation of these two relationships with some data reported in literature is also examined. Furthermore, the paper describes the different steps suggested in a new procedure for soil liquefaction assessment. The procedure was presented in the form of an evaluation guide. In addition, a relationship was suggested for computing the potential for liquefaction. An application of the proposed procedure to a practical case is included in order to validate and illustrate the different steps to be followed in the suggested evaluation procedure.
Brown adipose tissue (BAT) physiology and imaging have recently attracted considerable attention. BAT is characterized both by enhanced perfusio
n and increased mitochondrial activity. 99mTc-sestamibi is a lipophilic cationic
tracer that concentrates in mitochondria. Data on the accumulation of 99mTc-sestamibi in BAT are currently lacking. This study investigates the
in vivo99mTc-sestamibi uptake in rat BAT. 99mTc-sestamibi was administered in male Wistar rats of various age and body size. 99mTc-sestamibi uptake was measured in vitro in BAT and white fat (WF) together with cytochrome c oxidase activity. Both 99mTc-sestamibi uptake and cytochrome c oxidase activity were higher in BAT than in WF (P<0.05). 99m
Tc-Sestamibi uptake in both BAT and WF was negatively related to body weight (r= -0.96 and -0.89, respectively) as was the BAT/WF uptake ratio (r = -0.85). These data show a higher 99mTc-sestamibi uptake in
BAT compared to WF, in agreement with the high mitochondrial content and respiratory activity of the former. The strong negative correlation between 99mTc-sestamibi uptake in BAT and body weight (negative allometry), is in accordance to increased needs of thermogenesis in smaller animals. Implications of increased 99mTc-sestamibi uptake in BAT in radionuclide imaging are also discussed.
Isogeometric analysis (IGA) has been recently introduced as a viable alternative to the standard, polynomial-based finite element analysis. One of the fundamental performance issues of the isogeometric analysis is the quadrature of individual components of the discretized governing differential equation. The capability of the isogeometric analysis to easily adopt basis functions implies that high order numerical quadrature schemes must be employed. This may become computationally prohibitive because the evaluation of the high degree basis functions and/or their derivatives at individual integration points is quite demanding. The situation tends to be critical in three-dimensional space where the total number of integration points can increase dramatically. The aim of this paper is to compare computational efficiency of several numerical quadrature concepts which are nowadays available in the isogeometric analysis. Their performance is asessed on the assembly of stifness matrix of B-spline based problems with special geometrical arrangement allowing to determine minimum number of integration points leading to exact results. and Článek zahrnuje seznam literatury a na str. 257-259 Appendix
An assessment of DNA integrity in erythrocytes using the alkaline comet assay was carried out to estimate the impacts of water pollution on Balkan loaches (Cobitis elongata Heckel et Kner, 1858) inhabiting the Sava and Kupa Rivers, rivers of varying different water quality. The amount of DNA damage in cells was estimated from three different parameters comet tail length as the extent of genetic material migration, tail intensity (% DNA in comet tail) and tail moment. The results suggest a genotoxicity of the aquatic environment in the Sava River and demonstrated significantly lower levels of DNA damage in fish captured from the Kupa River. This study confirmed that the comet assay, applied to fish erythrocytes, is a useful tool in determining potential genotoxicity of water pollutants. Although a good DNA damage pattern for Balkan loach was obtained, due to its global and regional conservation status, only restricted use of a small number of specimens per sampling site could be permitted.
The analysis of data of 97 children with brain tumors of supratentorial localization was carried out. To estimate treatment efficacy was used a rating scale of quality of life. It was determined that the quality of life of patients with brain gliomas depends on localization of neoplastic process, histological properties of tumor, preoperative neurologic deficit and the patient’s compensated condition., Jamshid Ashrapov, and Literatura
Hydrogen peroxide (H2O2) production in exhaled air was measured in ventilated preterm newborns at 5, 24 and 48 hours after delivery, using originally designed method of exhaled breath condensate (EBC) collection. H2O2 production in expired gas was 812±34 pmol/20 min during the first measurement and then declined to 389±21 at 24 hours and 259±26 pmol/20 min at 48 hours.
In the marketing area, new trends are emerging, as customers are not only interested in the quality of the products or delivered services, but also in a stimulating shopping experience. Creating and influencing customers' experiences has become a valuable differentiation strategy for retailers. Therefore, understanding and assessing the customers' emotional response in relation to products/services represents an important asset. The purpose of this paper consists of investigating whether the customer's facial expressions shown during product appreciation are positive or negative and also which types of emotions are related to product appreciation. We collected a database of emotional facial expressions, by presenting a set of forty product related pictures to a number of test subjects. Next, we analysed the obtained facial expressions, by extracting both geometric and appearance features. Furthermore, we modeled them both in an unsupervised and supervised manner. Clustering techniques proved to be efficient at differentiating between positive and negative facial expressions in 78\% of the cases. Next, we performed more refined analysis of the different types of emotions, by employing different classification methods and we achieved 84\% accuracy for seven emotional classes and 95\% for the positive vs. negative.