Artificial Neural Networks for Prediction of COVID-19 in Saudi Arabia

In this study, we have proposed an artificial neural network (ANN) model to estimate and forecast the number of confirmed and recovered cases of COVID-19 in the upcoming days until September 17, 2020. The proposed model is based on the existing data (training data) published in the Saudi Arabia Coronavirus disease (COVID-19) situation—Demographics. The Prey-Predator algorithm is employed for the training. Multilayer perceptron neural network (MLPNN) is used in this study. To improve the performance of MLPNN, we determined the parameters of MLPNN using the prey-predator algorithm (PPA). The proposed model is called the MLPNN–PPA. The performance of the proposed model has been analyzed by the root mean squared error (RMSE) function, and correlation coefficient (R). Furthermore, we tested the proposed model using other existing data recorded in Saudi Arabia (testing data). It is demonstrated that the MLPNN-PPA model has the highest performance in predicting the number of infected and recovering in Saudi Arabia. The results reveal that the number of infected persons will increase in the coming days and become a minimum of 9789. The number of recoveries will be 2000 to 4000 per day.     

Multifractal analysis of Mg-doped ZnO thin films deposited by sol–gel spin coating method

A multifractal analysis has been performed on the 3D (three-dimensional) surface microtexture of magnesium-doped zinc oxide (ZnO:Mg) thin films with doping concentration of 0, 2, 4, and 5%. Thin films were deposited onto the glass substrates via the sol–gel spin coating method. The effect of magnesium doping, on the crystal structure, morphology, and band gap for ZnO:Mg thin films has been analyzed by X-ray diffraction (XRD), scanning electron microscopy (SEM), atomic force microscopy (AFM), and UV–Vis spectroscopy. It has been observed that the surface of ZnO thin films is multifractal in nature. However, multifractality and complexity observed to decrease with increasing content of Mg in ZnO thin films due to formation of islands on the surface in accordance with Volmer–Weber growth mechanism. The investigations revealed that crystallinity, microtexture, morphology, and optical properties of the thin films can be tuned by controlling the Mg content within the ZnO lattice. In particular, their optical band gap energies were 3.27, 3.31, 3.34, and 3.33 eV at 0, 2, 4, and 5%, respectively. The prepared thin films of ZnO:Mg with tuned characteristics would have promising applications in optoelectronic devices.     

Structural,dielectric and electrical properties of Sol–gel auto-combustion technic of CuFeCr0.5Ni0.5O4 ferrite

Journal of Materials Science - The CuFeCr0.5Ni0.5O4 (CFO) compound was synthesized using sol–gel reaction combustion technic. The structural analysis showed that the obtained composites have...     

On-site low-pressure diesel HDS for fuel cell applications: Deepening the sulfur content to ?1 ppm

This work investigates the feasibility of ultra-deep hydrodesulfurization (i.e. ?1 ppm of sulfur content) of several diesel feedstocks, viz., regular (R), premium (P) and hydrotreated straight-run (HSR) at low pressures, i.e. 10 bar, to lower significantly the operation costs. The premium and regular diesel contain additive packages with several components such as cetane boosters, antioxidants that show to negatively affect the sulfur conversion at low pressures. In the hydrotreated straight-run diesel fuel, which does not contain an additive package, total desulfurization can be obtained at 10 bar, T = 340 °C and LHSV = 1 h⁻¹. As a model for the additive package, FAME (fatty acid methyl ester), an ingredient that encounters the demands of a sustainable future, was added to the hydrotreated straight-run diesel (HSR + FAME) in order to check its influence on the total sulfur conversion. Results show that this biofuel component hindered tremendously the sulfur removal process by lowering the sulfur removal from 98% to zero at 10 bar, probably by competitive adsorption. At higher pressures, e.g. 30 bar, when FAME was present, new sulfur compounds were formed during the HDS process and the effective sulfur removal was very low.     

Study and optimization of water repellence stability in fluoroacrylate photopolymers

Fluoropolymers have attracted a lot of attention in the past 20 years mainly due to their hydrophobic properties. Unfortunately, they have also shown some stability issues mainly in hot water due to the easy disorganization of the fluorine chains. In this paper Confocal Raman Microscopy (CRM) has been used as an indirect probe to optimize the fluoroacrylate content in an acrylic photocurable resin in order to reduce the effect of hot water. Advancing and receding contact angles have also been measured to characterize the surface repellence both before and after immersion in hot water. Results show that despite an improvement of the stability of the fluoroacrylate coating with a careful selection of the concentration range, water still has a negative effect on the surface properties of the coating. This effect can be partly counterbalanced by successive thermal annealings at 100 °C which help to stabilize the hydrophobicity of the coating.     

Sentence similarity based on semantic nets and corpus statistics

Sentence similarity measures play an increasingly important role in text-related research and applications in areas such as text mining, Web page retrieval, and dialogue systems. Existing methods for computing sentence similarity have been adopted from approaches used for long text documents. These methods process sentences in a very high-dimensional space and are consequently inefficient, require human input, and are not adaptable to some application domains. This paper focuses directly on computing the similarity between very short texts of sentence length. It presents an algorithm that takes account of semantic information and word order information implied in the sentences. The semantic similarity of two sentences is calculated using information from a structured lexical database and from corpus statistics. The use of a lexical database enables our method to model human common sense knowledge and the incorporation of corpus statistics allows our method to be adaptable to different domains. The proposed method can be used in a variety of applications that involve text knowledge representation and discovery. Experiments on two sets of selected sentence pairs demonstrate that the proposed method provides a similarity measure that shows a significant correlation to human intuition.