A new approach to predict ulcerative colitis activity through standard clinical–biological parameters using a robust neural network model

Neural Computing and Applications - Colonoscopy is the “gold” standard for evaluating disease activity in ulcerative colitis (UC). An important area of research is finding a...     

Predictive control architecture for real-time image moments based servoing of robot manipulators

This paper presents a real-time architecture for visual servoing of robot manipulators using nonlinear based predictive control. In order to increase the robustness of the control algorithm, image moments were chosen to be the visual features which describe the objects from the image. A visual predictive architecture is designed to solve tasks addressed to robot manipulators with an eye-in-hand configuration. An implementation of the proposed architecture is done so that the capabilities of a 6 d.o.f robot manipulator are extended. The results of different experiments conducted with two types of image moments based controllers (proportional and predictive with reference trajectory) are presented and discussed.     

Non‐catalytic,solvent‐free synthesis of poly(tartronic‐co‐glycolic acid) as a versatile coating for different surfaces

The synthesis of poly(tartronic‐co‐glycolic acid) from tartronic acid is achieved by a simple thermal polycondensation method. This novel polyester was characterized by NMR and Fourier transform infrared spectroscopy as well as by high‐resolution electrospray ionization mass spectrometry. It contains pendent carboxyl groups at the tartronic acid units which therefore render it a more hydrophilic and more versatile analogue of poly(glycolic acid) combining the known biodegradability with the functionality of the pendent carboxyl groups. Thus, it is of interest for application in the synthesis of drug‐carrying biodegradable matrices. The copolymer was further used for coating different surfaces of magnetic nanoparticles such as magnetite, silica, titanium dioxide and exploited as a platform for further functionalization. © 2017 Society of Chemical Industry     

Improving classification performance of Support Vector Machine by genetically optimising kernel shape and hyper-parameters

Support Vector Machines (SVMs) deliver state-of-the-art performance in real-world applications and are now established as one of the standard tools for machine learning and data mining. A key problem of these methods is how to choose an optimal kernel and how to optimise its parameters. The real-world applications have also emphasised the need to consider a combination of kernels—a multiple kernel—in order to boost the classification accuracy by adapting the kernel to the characteristics of heterogeneous data. This combination could be linear or non-linear, weighted or un-weighted. Several approaches have been already proposed to find a linear weighted kernel combination and to optimise its parameters together with the SVM parameters, but no approach has tried to optimise a non-linear weighted combination. Therefore, our goal is to automatically generate and adapt a kernel combination (linear or non-linear, weighted or un-weighted, according to the data) and to optimise both the kernel parameters and SVM parameters by evolutionary means in a unified framework. We will denote our combination as a kernel of kernels (KoK). Numerical experiments show that the SVM algorithm, involving the evolutionary kernel of kernels (eKoK) we propose, performs better than well-known classic kernels whose parameters were optimised and a state of the art convex linear and an evolutionary linear, respectively, kernel combinations. These results emphasise the fact that the SVM algorithm could require a non-linear weighted combination of kernels.     

A fractional order control strategy for visual servoing systems

In this paper, a control strategy based on fractional calculus for visual servoing systems is proposed. The image-based control strategy is designed using a point features based fractional-order PI controller. A real-time visual servoing system, composed of a manipulator robot with 6 degrees of freedom (d.o.f.) with an eye-in-hand camera, is used for performance evaluation of the proposed control strategy. The image acquisition and processing, together with the computing of the image-based control law are implemented in MATLAB. Using planar static objects, real-time experiments are conducted and the results reveal that the image-based fractional-order PI controller outperforms the conventional image-based integer-order PI controller.     

Phase transfer catalysis in the polycondensation processes

Summary Polyesters from 3,3-bis(chloromethyl)oxacyclobutane and dipotassium isophthalate were obtained by phase transfer catalysis using different catalysts and solvents. The products were characterised by IR,¹H-NMR and DSC.     

Structural and oxidative changes in the kidney of crucian carp induced by silicon-based quantum dots

Silicon-based quantum dots were intraperitoneally injected in Carassius auratus gibelio specimens and, over one week, the effects on renal tissue were investigated by following their distribution and histological effects, as well as antioxidative system modifications. After three and seven days, detached epithelial cells from the basal lamina, dilated tubules and debris in the lumen of tubules were observed. At day 7, nephrogenesis was noticed. The reduced glutathione (GSH) concentration decreased in the first three days and started to rise later on. The superoxide dismutase (SOD) activity increased only after one week, whereas catalase (CAT) was up-regulated in a time-dependent manner. The activities of glutathione reductase (GR) and glutathione peroxidise (GPX) decreased dramatically by approximately 50% compared to control, whereas the glutathione-S-transferase (GST) and glucose-6-phosphate dehydrogenase (G6PDH) increased significantly after 3 and 7 days of treatment. Oxidative modifications of proteins and the time-dependent increase of Hsp70 expression were also registered. Our data suggest that silicon-based quantum dots induced oxidative stress followed by structural damages. However, renal tissue is capable of restoring its integrity by nephron development.     

Proline‐Functionalized Magnetic Core‐Shell Nanoparticles as Efficient and Recyclable Organocatalysts for Aldol Reactions

Novel magnetically tagged organocatalysts have been developed based on core‐shell nanoparticles consisting of magnetite cores and polyacrylate shells containing 4‐hydroxyproline moieties. These catalysts allow the performance of direct asymmetric aldol reactions of aromatic aldehydes with ketones in the presence of benzoic acid providing high yields and ees. Straightforward magnetic separation and recycling of a catalyst for up to 9 runs is possible without a significant loss of efficiency.     

Some Aspects of Thermal Stability and the Characteristics of Poly(ethylene terephthalate) (PET) under Stress

In this work we use thermal shrinkage for estimating the internal stresses accumulated in a sample during a technological process. This can be a precious instrument available for every manufacturer interested in the thermal treatment efficiency. Based on the Kelvin‐Voight rheological model, we have established a correlation between the internal stresses appearing during the technological formation processes of yarns and their shrinkage at different temperatures. In this work (PET) fibers were used for study, with different birefringences ranging between 4.2×10^–3–2.2×10^–3. Thermal treatment was performed with warm air at temperatures between 333–453 K. The applied unitary stress changed within the range 5.09×10¹⁰–18.84×10¹³ N·m^–2. From the examination of the curves obtained for free contraction Δε = f (T) for different birefringences Δn for the preoriented PET fibers, contraction increases with increasing temperature up to a maximum situated at ≈ 353 K and then decreases to a constant value. From the examination of the curves, the dimensional change vs. contraction σ = f (Δε), to a thermal treatment under stress for different birefringences Δn, when an external stress σ is applied the thermal stability of the fibers already having on orientation, made evident by the birefringence magnitude, that in the case of a slight orientation, the retraction decreases with increasing temperature. Singular points registered for fibers with Δn = 22×10^–3 for a temperature exceeding 393 K indicate that for the partially orientated fibers the sample is subjected to a stretching process during the thermal stability under stress. We established experimentally a correlation between the strain σ and Δn, Δn = ct. σ/T, i. e., a decrease of the birefringence with increasing temperature.