Adaptive Neuro-Fuzzy Inference System and a Multilayer Perceptron Model Trained with Grey Wolf Optimizer for Predicting Solar Diffuse Fraction

The accurate prediction of the solar diffuse fraction (DF), sometimes called the diffuse ratio, is an important topic for solar energy research. In the present study, the current state of Diffuse irradiance research is discussed and then three robust, machine learning (ML) models are examined using a large dataset (almost eight years) of hourly readings from Almeria, Spain. The ML models used herein, are a hybrid adaptive network-based fuzzy inference system (ANFIS), a single multi-layer perceptron (MLP) and a hybrid multi-layer perceptron grey wolf optimizer (MLP-GWO). These models were evaluated for their predictive precision, using various solar and DF irradiance data, from Spain. The results were then evaluated using frequently used evaluation criteria, the mean absolute error (MAE), mean error (ME) and the root mean square error (RMSE). The results showed that the MLP-GWO model, followed by the ANFIS model, provided a higher performance in both the training and the testing procedures.     

An ultra-small heterostructure wavelength division multiplexer (WDM) with the ability to select two wavelengths from the s-band

In this article, a photonic crystal channel drop filter (CDF) based on \(2\times 3\) ring resonators is presented. At first, the effects of changing the radius of lattice rods and the lattice dielectric constant on the dropping efficiency of a 3-port CDF with one resonator are investigated. Then by developing this base structure, a new 4-port heterostructure CDF composed of two regions with rods made of silicone and germanium is presented, which can operate in the ‘S’ band of the communication window. The photonic crystal heterostructure CDF consists of a horizontal waveguide and two ring resonators that have been installed, in symmetry to the horizontal axis, in two regions with different refractive indices. These ring resonators act as energy couplers and capture at their resonant frequencies the electromagnetic energy which is propagated in the bus waveguide. For the analysis of transmission characteristics and the band structure of the filter, two methods have been employed: the two-dimensional Finite–difference time domain method and the Plane Wave Expansion method. In the final structure, dropping efficiencies of 97 and 89 % can be achieved at ports D and B, respectively, and also an acceptable quality factor can be obtained in the communication window. The overall size of this device is 174.14  \(\upmu \hbox {m}^{2}\) . Due to its small size, this structure can be used in Wavelength Division Multiplexer applications in the Optical Integrated Circuits.     

Training Multilayer Perceptron with Genetic Algorithms and Particle Swarm Optimization for Modeling Stock Price Index Prediction

Predicting stock market (SM) trends is an issue of great interest among researchers, investors and traders since the successful prediction of SMs’ direction may promise various benefits. Because of the fairly nonlinear nature of the historical data, accurate estimation of the SM direction is a rather challenging issue. The aim of this study is to present a novel machine learning (ML) model to forecast the movement of the Borsa Istanbul (BIST) 100 index. Modeling was performed by multilayer perceptron–genetic algorithms (MLP–GA) and multilayer perceptron–particle swarm optimization (MLP–PSO) in two scenarios considering Tanh (x) and the default Gaussian function as the output function. The historical financial time series data utilized in this research is from 1996 to 2020, consisting of nine technical indicators. Results are assessed using Root Mean Square Error (RMSE), Mean Absolute Percentage Error (MAPE) and correlation coefficient values to compare the accuracy and performance of the developed models. Based on the results, the involvement of the Tanh (x) as the output function, improved the accuracy of models compared with the default Gaussian function, significantly. MLP–PSO with population size 125, followed by MLP–GA with population size 50, provided higher accuracy for testing, reporting RMSE of 0.732583 and 0.733063, MAPE of 28.16%, 29.09% and correlation coefficient of 0.694 and 0.695, respectively. According to the results, using the hybrid ML method could successfully improve the prediction accuracy.     

Synthesis and characterization of new hybrid inorganic–organic polymer nanocomposite as efficient catalyst for oxidative desulfurization of real fuel

Sulfur-containing compounds are responsible for much air pollution, and therefore eliminating these compounds is of importance. Herein, a hybrid organic–inorganic recyclable nanocatalyst (TBA-PW₁₁Ni@PANI) was synthesized successfully to investigate its effects on the catalytic oxidative desulfurization (CODS) process of real gasoline/model fuel. To this end, the Keggin-based mono-lacunary polyoxometalate [PW₁₁NiO₃₉] was prepared and modified with quaternary cation tetrabutylammonium (TBA). Then, this was further immobilized on polyaniline (PANI) via the sol–gel method. The synthesized nanocomposite was characterized using various techniques. The high dispersion of polyoxometalate on PANI was confirmed. Also, it was found that the crystalline structure remained unaltered after immobilization. In addition, the effects of various parameters such as dosage and temperature on the CODS of model fuel in the presence of H₂O₂–acetic acid (1:2 v/v) were studied in detail. Moreover, the kinetics of the CODS process was also studied and a mechanism proposed. According to the results, TBA-PW₁₁Ni@PANI showed an efficiency of up to 97% with 0.1 g at 35°C (optimum values) which implies its good catalytic functionality in the CODS process. Finally, the TBA-PW₁₁Ni@PANI catalyst displayed long-term stability and good reusability after five runs.     

Electrodeposition of Cobalt Oxide Nanostructure on the Glassy Carbon Electrode for Electrocatalytic Determination of para‐Nitrophenol

Cobalt oxide nanostructure (CoO_xNS) deposited on the glassy carbon (GC) electrode surface is proposed as a novel electrocatalytic system for the reduction of para‐Nitrophenol. Cyclic voltammetry, electrochemical impedance spectroscopy, atomic force microscopy and scanning electron microscopy were used for characterization of deposited CoO_xNS. CoO_xNS deposited by cycling at positive potentials (0 to +1.3 V) show less charge‐transfer resistance (Rct) and more catalytic activity for the electroreduction of p‐nitrophenol compared to those CoO_xNS obtained by scanning the applied potential throughout a negative V range. The GC/CoO_xNS electrode showed good electrocatalytic activity toward the reduction of p‐nitrophenol at different pH values.     

Numerical characterizations of unstable optical resonators and evaluation of the geometry effects

Unstable resonators have been widely used in high-power gas lasers as well as solid-state lasers. The phase and the spatial distribution of intensity of these lasers are very important in some applications such as material processing. In this paper, unstable resonators with three different geometries have been characterized numerically and the results have been compared and evaluated. Based on the Fresnel-Kirchhoff integral, the two-dimensional phase and intensity have been calculated for three different positive branch unstable resonators. The results show that the resonators with rectangular geometry have the best performance for near-field as well as far-field intensity, which is more suitable for material processing. The calculations also show that the maximum output power can be extracted from the rectangular resonator with spherical surface, while the circular resonator with spherical surface has minimum output power. The results also show that the laser has a higher divergence for the cylindrical resonator in compare with those for the circular and rectangular resonators.     

Efficient electrosynthesis of 1,2,4-triazino[3,4-b]-1,3,4-thiadiazine derivatives

Electrochemical oxidation of catechols 1a-d has been studied in the presence of 4-amino-6-methyl-1,2,4-triazine-3-thion-5-one 3 as a nucleophile in aqueous solutions, using cyclic voltammetry and controlled-potential coulometry, leading to the efficient synthesis of 1,2,4-triazino[3,4-b]-1,3,4-thiadiazines.     

Exact solutions to the space–time fractional Schrödinger–Hirota equation and the space–time modified KDV–Zakharov–Kuznetsov equation

In this paper, the first integral method and the functional variable method are used to establish exact traveling wave solutions of the space–time fractional Schrödinger–Hirota equation and the space–time fractional modified KDV–Zakharov–Kuznetsov equation in the sense of conformable fractional derivative. The results obtained confirm that proposed methods are efficient techniques for analytic treatment of a wide variety of the space–time fractional partial differential equations.