The convolutional neural networks (CNN) are among the most utilized neural networks in various applications, including deep learning. In recent years, the continuing extension of CNN into increasingly complicated domains has made its training process more difficult. Thus, researchers adopted optimized hybrid algorithms to address this problem. In this work, a novel chaotic black hole algorithm-based approach was created for the training of CNN to optimize its performance via avoidance of entrapment in the local minima. The logistic chaotic map was used to initialize the population instead of using the uniform distribution. The proposed training algorithm was developed based on a specific benchmark problem for optical character recognition applications; the proposed method was evaluated for performance in terms of computational accuracy, convergence analysis, and cost.
The effect of doping by methyl red and methyl blue on the absorption spectra and the optical energy gap of poly (methyl methacrylat) PMMA film have been studied. The optical transmission (T%) in the wavelength range 190-900 nm for films deposited by using solvent casting method were measured. The Absorptance data reveals that the doping affected the absorption edge as a red and blue shift in its values. The films show indirect allowed interband transitions that influenced by the doping. Optical constants; refractive index, extinction coefficient and real and imaginary part of dielectric constant were calculated and correlated with doping.
CdS and CdS:Sn thin films were successfully deposited on glass
substrates by spray pyrolysis method. The films were grown at
substrate temperatures 300 C°. The effects of Sn concentration on the
structural and optical properties were studied.
The XRD profiles showed that the films are polycrystalline with
hexagonal structure grown preferentially along the (002) axis. The
optical studies exhibit direct allowed transition. Energy band gap
vary from 3.2 to 2.7 eV.
In this paper the effect of thermal annealing on the structural and optical properties of Antimony Selenide (Sb2Se3) is investigated. Sb2Se3 powder is evaporated on clean amorphous glass substrates at room temperature under high vacuum pressure (4.5×10-6 mbar) to form thin films. The structural investigation was done with the aid of X-ray diffraction (XRD) and atomic force microscopy (AFM). The amorphous to polycrystalline transformation of these thin films was shown by X-ray diffraction analysis after thermal annealing. These films' morphology is explained. (UV-Vis ) spectra in ranges from 300 to 1100 nm was used to examine the optical properties of the films .The absorption coefficient and optical energy gap of the investigated films are
... Show MoreNanostructure of chromium oxide (Cr2O3-NPs) with rhombohedral structure were successfully prepared by spray pyrolysis technique using Aqueous solution of Chromium (III) chloride CrCl3 as solution. The films were deposited on glass substrates heated to 450°C using X-ray diffraction (XRD) shows the nature of polycrystalline samples. The calculated lattice constant value for the grown Cr2O3 nanostructures is a = b = 4.959 Å & c = 13.594 Å and the average crystallize size (46.3-55.6) nm calculated from diffraction peaks, Spectral analysis revealed FTIR peak characteristic vibrations of Cr-O Extended and Two sharp peaks present at 630 and 578 cm-1 attributed to Cr-O “stretching
... Show MoreRare earth elements (Cerium, Lanthanum and Neodymium) doped CdS thin films are prepared using the chemical Spray Pyrolysis Method with temperature 200 oC. The X-ray diffraction (XRD) analysis refers that pure CdS and CdS:Ce, CdS:La and CdS:Nd thin films showed the hexagonal crystalline phase. The crystallite size determined by the Debye-Scherrer equation and the range was (35.8– 23.76 nm), and it was confirmed by field emission scanning electron microscopy (FE-SEM). The pure and doped CdS shows a direct band gap (2.57 to 2.72 eV), which was obtained by transmittance. The room-temperature photoluminescence of pure and doped CdS shows large peak at 431 nm, and two small peaks at (530 and 610 nm). The Current – voltage measurement in da
... Show MoreAbstract: Reflection optical fibre Humidity sensor is presented in this work, which is based on no core fibre prepared by splicing a segment of no core fibre (NCF) at different lengths 1-6 cm with fixed diameter 125 µm and a single mode fibre (SMF). The range of humidity inside the chamber is controlled from 30% to 90% RH at temperature ~ 30 °С. The experimental result shows that the resonant wavelength dip shift decreases linearly with an increment of RH% and the sensitivity of the sensor increased linearly with an increasing in the length of NCF. However, a high sensitivity 716.07pm/RH% is obtained at length 5cm with good stability and reputability. Furthermore, the sensor is shif
... Show MoreZnTe possesses the proper optoelectronic properties as a candidate for device development. The structure and optical properties of ZnTe semiconductor thin films of 500 nm were studied using thermal evaporation technique. The influence of annealing temperatures on ZnTe thin films in the range ( R.T - 473 K). XRD and surface morphological analyses are used to examine the films. The ZnTe films are comparatively polycrystalline and cubic in phase, according to the XRD analysis. with a lattice constant of 0.61 nm upon an (111) orientation. The intensities of all the peaks rapidly increase though they show the same tendencies; it shows the crystallinity of the films becomes higher crystal size diameters (from 8.41 to 12.18nm) both increas
... Show MoreIn recent years, Bitcoin has become the most widely used blockchain platform in business and finance. The goal of this work is to find a viable prediction model that incorporates and perhaps improves on a combination of available models. Among the techniques utilized in this paper are exponential smoothing, ARIMA, artificial neural networks (ANNs) models, and prediction combination models. The study's most obvious discovery is that artificial intelligence models improve the results of compound prediction models. The second key discovery was that a strong combination forecasting model that responds to the multiple fluctuations that occur in the bitcoin time series and Error improvement should be used. Based on the results, the prediction acc
... Show MoreInterval methods for verified integration of initial value problems (IVPs) for ODEs have been used for more than 40 years. For many classes of IVPs, these methods have the ability to compute guaranteed error bounds for the flow of an ODE, where traditional methods provide only approximations to a solution. Overestimation, however, is a potential drawback of verified methods. For some problems, the computed error bounds become overly pessimistic, or integration even breaks down. The dependency problem and the wrapping effect are particular sources of overestimations in interval computations. Berz (see [1]) and his co-workers have developed Taylor model methods, which extend interval arithmetic with symbolic computations. The latter is an ef
... Show More