Comparison of new activation functions in neural network for forecasting financial time series

In artificial neural networks (ANNs), the activation function most used in practice are the logistic sigmoid function and the hyperbolic tangent function. The activation functions used in ANNs have been said to play an important role in the convergence of the learning algorithms. In this paper, we evaluate the use of different activation functions and suggest the use of three new simple functions, complementary log-log, probit and log-log, as activation functions in order to improve the performance of neural networks. Financial time series were used to evaluate the performance of ANNs models using these new activation functions and to compare their performance with some activation functions existing in the literature. This evaluation is performed through two learning algorithms: conjugate gradient backpropagation with Fletcher–Reeves updates and Levenberg–Marquardt.     

A hybridized artificial neural network and imperialist competitive algorithm optimization approach for prediction of soil compaction in soil bin facility

We were inspired to furnish information concerning the promising applicability of a hybrid approach involving artificial neural networks (ANNs), with manifold network functions, and a meta-heuristic optimization algorithm for prediction of soil compaction indices. The employed network functions were the prevailed feed-forward network and the novel cascade-forward network algorithms to accommodate multivariate inputs of wheel load, tire inflation pressure, number of passage, slippage, and velocity each at three different levels for estimating the study objectives of soil compaction (i.e. penetration resistance and soil sinkage). The experimentations were carried out in a soil bin facility utilizing a single wheel-tester. Each ANN trials was developed merely and then by merging with the recently introduced evolutionary optimization technique of imperialist competitive algorithm (ICA). The results were compared on the basis of a modified performance function (MSEREG) and coefficient of determination (R²). Our results elucidated that hybrid ICA–ANN further succeeded to denote lower modeling error amongst which, cascade-forward network optimized by ICA managed to yield the highest quality solutions.     

Effects of meteorological variables on exergetic efficiency of wind turbine power plants

This present paper deals with exergy efficiency results of the Wind Turbine Power Plants (WTPPs). Effects of meteorological variables such as air density, pressure difference between state points, humidity, and ambient temperature on exergy efficiency are discussed in a satisfactory way. Some key parameters are given monthly for the three turbines. Exergy efficiency differs from 0.23 to 0.27 while temperature is changing from 268.15 K to 308.15 K with air density 1.368–1.146 (kg/m³). While pressure difference (ΔP) between inlet and outlet of the turbine differs from 100 to 1100 (Pa), exergy efficiency decreases fairly for different wind speeds. While specific humidity is changing from 0.001 to 0.015 (kg_water/kg_{dry air}), exergy efficiency decreases gently. Generally these meteorological variables are neglected while planning WTPPs, but this neglect can cause important errors in calculations and energy plans. Obtained results indicate that while planning WTPPs meteorological variables must be taken into account.     

Microwave-assisted sol–gel synthesis of alpha alumina nanopowder and study of the rheological behavior

In the present work, alpha alumina nanopowder was synthesized via a sol–gel route. After preparation of bohemite (AlOOH) sol, carbon black was added and the resultant sol was dried and calcined in microwave furnace for 10 min. XRD results showed that alpha alumina was the only crystalline phase with specific surface area, mean diameter and crystallite size of 51 m² g^?1, 100 and 25 nm, respectively. Rheological measurements revealed that the optimal content of Tiron at pH=10 is 1 and 0.1 g per 100 g nano- and micron-alumina (1.5 m² g^?1), respectively. Furthermore, the optimum solid content of the slips was determined as 35–45 and 70 wt.% for nano- and micron-alumina, respectively.     

Rapid prototyping of a miniaturized Electrospinning setup for the production of polymer nanofibers

Fabrication of polymeric micro/nanofibers with controllable size, density, orientation, and composition is required for their translation into functional devices and materials. Electrospinning (ES) is a frequently used fiber fabrication technique, where ES parameters such as the applied electric field strength, architecture of the setup, and solution composition are manipulated to control the fiber properties. Here, we present a bench‐top method for fabricating miniaturized, integrated, and highly tunable ES setups based on shrinkable polymer substrates. We show that using a combination of numerical modeling and controlling different parameters in the ES setup, including the spinneret to collector distance, and spinneret and collector designs, it is possible to tune the density, alignment, and orientation of electrospun fibers. In this way, we have produced 300–600 nm wide poly(ethylene oxide) fibers arranged as nonwoven mats on planar electrodes, aligned fibers on electrode edges, and individual suspended fibers spanning gaps between collector electrodes. The ability to rapidly prototype ES setups should enable us to study the effects of spinneret–collector configurations on fiber morphology, distribution, and conformation and to aid in the development of miniaturized ES setups designed to serve specific applications. © 2014 Wiley Periodicals, Inc. J. Appl. Polym. Sci. 2014 , 131, 40629.     

Selective extraction of phosphatidylcholine from lecithin by supercritical carbon dioxide/ethanol mixture

Selective extraction of phosphatidylcholine (PC) from deoiled soybean lecithin using supercritical fluid (SCF) mixtures of carbon dioxide (CO₂) and ethanol was studied at moderate pressures. Temperature was varied between 60 and 80°C at pressures of 17.2 and 20.7 MPa. Ethanol was added as co-solvent to supercritical CO₂ at the levels of 10 and 12.5 wt%. Constant rate of extraction of the individual phospholipids (PL) was observed for 150 min during which the extractions were carried out. Pressure and ethanol fraction had a positive effect on the selective extraction of PC, whereas temperature had a negative effect. Under all the conditions studied, the extracts were mainly composed of PC while the extraction of the other PL was very low. Extraction at 60°C and 20.7 MPa with 10 wt% ethanol/90 wt% CO₂ SCF mixture resulted in 95% selectivity to PC.     

Spouted bed and microwave-assisted spouted bed drying of parboiled wheat

The effect of spouted bed and microwave-assisted spouted bed drying on drying rates of parboiled wheat was investigated. In addition, the effective moisture diffusivities of parboiled wheat were calculated. The drying experiments were performed using 200 g of parboiled wheat, at three different air temperatures (50, 70, 90 °C) and at two different microwave powers (3.5 W/g (db), 7.5 W/g (db)). Microwave-assisted spouted bed drying at microwave power of 3.5 W/g and 7.5 W/g reduced drying time by at least 60% and 85%, respectively compared to spouted bed drying. The effective diffusivity values were in the range of 1.44 × 10^?10–3.32 × 10^?10 in spouted bed drying while they were between 5.06 × 10^?10 and 11.3 × 10^?10 in microwave-assisted spouted bed drying at different experimental conditions.     

Assessment of mean and fluctuating velocity and temperature of CuO/water nanofluid in a horizontal channel: Large eddy simulation

Abstract

A comprehensive investigation applying the large eddy simulation approach to turbulent forced convection of CuO/water nanofluid flowing through a horizontal channel is carried out. Dealing with the sub-grid scale stress tensor and heat flux vector, the wall-adopting local eddy-viscosity model is employed. The periodic boundary condition is imposed to the streamwise and spanwise directions, while the no-slip and constant heat flux are applied to the walls. The results indicate that adding nanoparticles into the base fluid increases the dimensionless mean velocity and fluctuations of velocity and temperature. This increment is more evident for turbulent Reynolds stress and turbulent heat flux in the streamwise direction than the other directions. Therefore, higher energy is transferred between nanofluid layers which results in a higher amount of heat transfer than the pure water. It is also observed that the nanoparticles enhance the turbulence energy at all frequencies, and the decay in the fluctuations occurs at the higher wavenumbers.     

Extending the Colloidal Transition Metal Dichalcogenide Library to ReS2 Nanosheets for Application in Gas Sensing and Electrocatalysis

Among the large family of transition metal dichalcogenides, recently ReS₂ has stood out due to its nearly layer‐independent optoelectronic and physicochemical properties related to its 1T distorted octahedral structure. This structure leads to strong in‐plane anisotropy, and the presence of active sites at its surface makes ReS₂ interesting for gas sensing and catalysts applications. However, current fabrication methods use chemical or physical vapor deposition (CVD or PVD) processes that are costly, time‐consuming and complex, therefore limiting its large‐scale production and exploitation. To address this issue, a colloidal synthesis approach is developed, which allows the production of ReS₂ at temperatures below 360 °C and with reaction times shorter than 2h. By combining the solution‐based synthesis with surface functionalization strategies, the feasibility of colloidal ReS₂ nanosheet films for sensing different gases is demonstrated with highly competitive performance in comparison with devices built with CVD‐grown ReS₂ and MoS₂. In addition, the integration of the ReS₂ nanosheet films in assemblies together with carbon nanotubes allows to fabricate electrodes for electrocatalysis for H₂ production in both acid and alkaline conditions. Results from proof‐of‐principle devices show an electrocatalytic overpotential competitive with devices based on ReS₂ produced by CVD, and even with MoS₂, WS₂, and MoSe₂ electrocatalysts.     

Audio watermarking scheme based on embedding strategy in low frequency components with a binary image

With the recent development of information technology and computer network, digital format of data has become more and more popular. However, a major problem faced by digital data providers and owners is protecting data from unauthorized copying and distribution. As a solution to the problem, digital watermark technology is now attracting attention as new method of protection against said unauthorized copying and distribution. The aim of the digital audio watermarking is to take prespecified data that carries certain information and hide it within the audio stream such that it is not audible to the human ear (i.e., transparent) but at the same time renders the file more resistant to removal (i.e., robust). In this paper, we propose a new method for embedding digital watermarks into audio signals in low frequency components, which method mitigates these and other related shortcomings. The proposed method uses the wavelet transform constructed by lifting-based wavelet transform (LBWT) in order to provide a fast implementation between watermark embedding and extraction parts. In the first stage of the proposed method, the original audio host signal is converted to a wavelet domain using LBWT. The signal is thus decomposed into low and high frequency components. Approximation coefficients correspond to low frequency components of the signal. Next, the watermark generated by pseudorandom numbers is embedded into wavelet approximation coefficients of the segmented host audio signal depending on the binary value of the binary image. The reason for embedding the watermark in the low frequency components is that these components' energy is greater than that of high frequency components in such a way that the watermark is inaudible; therefore, it should not alter the audible content and should not be easy to remove. The proposed method uses a binary image to decide whether or not the watermark generated by pseudorandom numbers is embedded in the audio host signal. To evaluate the performance of the proposed audio watermarking method, subjective and objective quality tests including bit error rate (BER) and signal-to-noise ratio (SNR) are conducted. The tests' results show that the proposed method yields a high recovery rate after attacks by commonly used audio data manipulations such as low-pass filtering, requantization, resampling and MP3 compression.