Classification of brain hemorrhage computed tomography images using OzNet hybrid algorithm

Classification of brain hemorrhage computed tomography (CT) images provides a better diagnostic implementation for emergency patients. Attentively, each brain CT image must be examined by doctors. This situation is time-consuming, exhausting, and sometimes leads to making errors. Hence, we aim to find the best algorithm owing to a requirement for automatic classification of CT images to detect brain hemorrhage. In this study, we developed OzNet hybrid algorithm, which is a novel convolution neural networks (CNN) algorithm. Although OzNet achieves high classification performance, we combine it with Neighborhood Component Analysis (NCA) and many classifiers: Artificial neural networks (ANN), Adaboost, Bagging, Decision Tree, K-Nearest Neighbor (K-NN), Linear Discriminant Analysis (LDA), Naïve Bayes and Support Vector Machines (SVM). In addition, Oznet is utilized for feature extraction, where 4096 features are extracted from the fully connected layer. These features are reduced to have significant and informative features with minimum loss by NCA. Eventually, we use these classifiers to classify these significant features. Finally, experimental results display that OzNet-NCA-ANN excellent classifier model and achieves 100% accuracy with created Dataset 2 from Brain Hemorrhage CT images.     

Investigation of Ant System parameter interactions by using design of experiments for job-shop scheduling problems

In recent years, one of the most important and promising research fields has been metaheuristics to find optimal or near-optimal solutions for NP-hard combinatorial optimization problems. Improving the quality of the solution or the solution time is basic research area on metaheuristics. Modifications of the existing ones or creation of hybrid approaches are the focus of these efforts. Another area of improving the solution quality of metaheuristics is finding the optimal combination of algorithm control parameters. This is usually done by design of experiments or one-at-a-time approach in genetic algorithms, simulated annealing and similar metaheuristics. We observe that, in studies which use Ant Colonies Optimization (ACO) as an optimization technique; the levels of control parameters are determined by some non-systematic initial experiments and the interactions of the parameters are not studied yet.In this study, the parameters of Ant System have been investigated on different sized and randomly generated job-shop scheduling problems by using design of experiments. The effects and interactions of the parameters have been interpreted with the outputs of the experiments. Referring to the statistical analysis it is observed that none of the interactions between the Ant System parameters has a significant effect on makespan value. A specific fractional experimental design is suggested instead of the full factorial design. Depending on the findings from the benchmark problems it will be a reliable approach to use the suggested design for saving time and effort in experiments without sacrificing the solution quality.     

Interface feature prioritization for web services: Case of online flight reservations

Acceptance, utility, and usability of system designs have become a focal interest in human–computer interaction (HCI) research, yet at present there is a lack detailed understandings of which system design features influence them. The purpose of the study is to examine the effects of five product design features; customization, adaptive behavior, memory load, content density, and speed on user preference through an experimental study by using conjoint analysis. In experimental study, instead of classical conjoint cards, prototypes were generated for products. Besides, desirability and market segments of product prototypes were identified. In line with the results, among the five product design features, speed is the most and customization is the least important features that affect user preference. Contrary to the expectations, customization has a relatively small importance value in this research. Subsequent design features that influence user preference after speed are minimal memory load, adaptive behavior, and content density, respectively. According to findings, interfaces that have high-speed, minimal memory load, adaptive behavior, low content density, and customization features are more preferable than those that do not.     

DNA immobilization and SAW response in ZnO nanotips grown on LiNbO3 substrates.

DNA immobilization enhancement is demonstrated in a structure consisting of ZnO nanotips on 128 degrees Y-cut LiNbO3. The ZnO nanotips are grown by metalorganic chemical vapor deposition (MOCVD) on the top of a SiO2 layer that is deposited and patterned on the LiNbO3 SAW delay path. The effects of ZnO nanotips on the SAW response are investigated. X-ray diffraction and scanning electron microscopy are used to analyze the ZnO nanotips, which are of single crystalline quality, and they are uniformly aligned with their c-axis perpendicular to the substrate surface. The photoluminescence (PL) spectrum of the ZnO nanotips shows strong near bandedge transition with insignificant deep level emission, confirming their good optical property. DNA immobilization enhancement is experimentally validated by radioactive labeling tests and SAW response changes. The ZnO nanotips enhance the DNA immobilization by a factor of 200 compared to ZnO film with flat surface. DNA hybridization with complementary and noncomplementary second strand DNA oligonucleotides is used to study the selective binding of the structure. This device structure possesses the advantages of both traditional SAW sensors and ZnO nanostructures.     

Response Surface Modeling and Evaluation of the Influence of Deposition Parameters on the Electrolytic Cu-Sn Alloy Powders Production

In this article, the electrodeposition process of Cu-Sn alloy powders from tripolyphosphate (TPP)-based electrolytes was investigated as a function of deposition parameters. The effects of deposition parameters such as current density, electrolyte composition (Cu/Sn mole ratio), mechanical stirring speed, and temperature on the Cu content of alloy powder and cathodic current efficiency were evaluated using the response surface methodology (RSM). The empirical models developed in terms of deposition parameters were found to be statistically adequate to describe the process responses. The study revealed that as far as the copper content was concerned in the alloyed powders, all parameters selected had positive correlations. However, a high stirring speed and low current density led to a greater current efficiency. The morphology and chemical composition of the electrodeposited Cu-Sn alloy powders were investigated using scanning electron microscopy (SEM), energy-dispersive X-ray spectroscopy (EDS), X-ray diffraction (XRD), and inductively coupled plasma (ICP) analysis. An SEM analysis showed that the powder morphology was affected considerably by the cathodic current density and stirring speed.     

A review of the day-ahead natural gas consumption in Denmark:starting point towards forecasting accuracy improvement

Natural gas consumption forecasting is crucial for transmission system operators,distribution system operators,traders,and other players in the market.This work...     

Production of activated carbon coated polystyrene resins under hydrothermal conditions and their use for gold cyanide adsorption

Polystyrene beads were coated with activated carbon under hydrothermal conditions above the glass transition temperature of polystyrene. By precisely controlling the temperature between 140 and 145 °C under vigorous mixing conditions in the presence of an excess of activated carbon, the surface of polystyrene beads were made sufficiently tacky so that finely sized activated carbon particles adhered to their surfaces, producing polystyrene/activated carbon, PS-AC, beads. The usefulness of these beads, as an alternative to pure activated carbon particles, for adsorption of gold cyanide ions under industrial conditions, was also demonstrated experimentally.     

The effect of replacing fat with oat bran on fatty acid composition and physicochemical properties of meatballs

Oat bran was used as a fat substitute in the production of meatballs. The effect of oat bran addition on the fatty acid composition, trans fatty acids, total fat, some physicochemical and sensory properties of the samples was studied. Meatballs were produced with four different formulations; the addition of 5, 10, 15 and 20% oat bran. Control samples were formulated with 25% fat addition as in commercial production. The major fatty acids were cis-oleic, palmitic and stearic acid in all the meatball samples, those with oat bran added as well as the control. Meatballs containing oat bran had lower concentrations of total fat and total trans fatty acids than the control samples. Meatballs made with 20% oat bran had the highest protein, salt and ash contents, L value (lightness), b value (yellowness), and the lowest moisture content and a value (redness). There was no significant difference among the meatball samples with respect to sensory properties, and all samples had high acceptability.     

Determination of potential methane production capacity of a granular sludge from a pilot‐scale upflow anaerobic sludge blanket reactor using a specific methanogenic activity test

A 450 dm³ pilot‐scale upflow anaerobic sludge blanket (UASB) reactor was used for the treatment of a fermentation‐based pharmaceutical wastewater. The UASB reactor performed well up to an organic loading rate (OLR) of 10.7 kg COD m^?3 d^?1 at which point 94% COD removal efficiency was achieved. This high treatment efficiency did not continue, however and the UASB reactor was then operated at lower OLRs for the remainder of the study. Specific methanogenic activity (SMA) tests were, therefore, carried out to determine the potential loading capacity of the UASB reactor. For this purpose, the SMA tests were carried out at four different initial acetate concentrations, namely 500 mg dm^?3, 1000 mg dm^?3, 1500 mg dm^?3 and 2000 mg dm^?3 so that substrate limitation could not occur. The results showed that the sludge sample taken from the UASB reactor (OLR of 6.1 kg COD m^?3 d^?1) had a potential acetoclastic methane production (PMP) rate of 72 cm³ CH₄ g^?1 VSS d^?1. When the PMP rate was compared with the actual methane production rate (AMP) of 67 cm³ CH₄ g^?1 VSS d^?1 obtained from the UASB reactor, the AMP/PMP ratio was found to be 0.94 which ensured that the UASB reactor was operated using its maximum potential acetoclastic methanogenic capacity. In order to achieve higher OLRs with desired COD removal efficiencies it was recommended that the UASB reactor should be loaded with suitable OLRs pre‐determined by SMA tests. © 2001 Society of Chemical Industry