Image classification is the process of finding common features in images from various classes and applying them to categorize and label them. The main problem of the image classification process is the abundance of images, the high complexity of the data, and the shortage of labeled data, presenting the key obstacles in image classification. The cornerstone of image classification is evaluating the convolutional features retrieved from deep learning models and training them with machine learning classifiers. This study proposes a new approach of “hybrid learning” by combining deep learning with machine learning for image classification based on convolutional feature extraction using the VGG-16 deep learning model and seven classifiers. A hybrid supervised learning system that takes advantage of rich intermediate features extracted from deep learning compared to traditional feature extraction to boost classification accuracy and parameters is suggested. They provide the same set of characteristics to discover and verify which classifier yields the best classification with our new proposed approach of “hybrid learning.” To achieve this, the performance of classifiers was assessed depending on a genuine dataset that was taken by our camera system. The simulation results show that the support vector machine (SVM) has a mean square error of 0.011, a total accuracy ratio of 98.80%, and an F1 score of 0.99. Moreover, the results show that the LR classifier has a mean square error of 0.035 and a total ratio of 96.42%, and an F1 score of 0.96 comes in the second place. The ANN classifier has a mean square error of 0.047 and a total ratio of 95.23%, and an F1 score of 0.94 comes in the third place. Furthermore, RF, WKNN, DT, and NB with a mean square error and an F1 score advance to the next stage with accuracy ratios of 91.66%, 90.47%, 79.76%, and 75%, respectively. As a result, the main contribution is the enhancement of the classification performance parameters with images of varying brightness and clarity using the proposed hybrid learning approach.
The ground charge density distributions (CDD), elastic charge form factors and proton, charge, neutron, and matter root mean square (rms) radii for stable 40Ca and 48Ca have been calculated using single-particle radial wave functions of Woods-Saxon (WS) and harmonic-oscillator (HO) potentials. Different central potential depths are used for each subshell which is adjusted so as to reproduce the experimental single-nucleon binding energies. An excellent agreement between the calculated rms charge radii and experimental data are found for both nuclei using WS and HO potentials. The calculated proton rms radii for 40Ca are found to be in good agreement with experiment data using both WS and HO potentials while the results for 48Ca showed an ov
... Show MoreThe bound radial wave functions of Cosh potential which are the solutions to the radial part of Schrodinger equation are solved numerically and used to compute the size radii; i.e., the root-mean square proton, neutron, charge and matter radii, ground density distributions and elastic electron scattering charge form factors for nitrogen isotopes 14,16,18,20,22N. The parameters of such potential for the isotopes under study have been opted so as to regenerate the experimental last single nucleon binding energies on Fermi's level and available experimental size radii as well.
The measurement of vitamin B1 in pure and pharmaceutical formulations was proposed by using a straightforward and sensitive spectrophotometric approach. Sulfacetamide (SFA) is diazotized, then coupled with vitamin B1 in alkaline media to produce a colored azo dye complex with a stability constant of 5.597 × 105 L/mol. The product is stable, with a maximum absorption wavelength of 489.5 nm, molar absorptivity of 10108 L/mol∙cm, Sandell's sensitivity of 0.0334 μg/cm2, detection limit of 0.0135 μg/mL, and Beer's law being observed over the concentration range of 0.2–20.0 μg/mL. The stability constant and stoichiometry of the produced azo dye were calculated using the continuous variation (Job's) and mole ratio methods. The suggested ap
... Show MoreThe ejector refrigeration system is a desirable choice to reduce energy consumption. A Computational Fluid Dynamics CFD simulation using the ANSYS package was performed to investigate the flow inside the ejector and determine the performance of a small-scale steam ejector. The experimental results showed that at the nozzle throat diameter of 2.6 mm and the evaporator temperature of 10oC, increasing boiler temperature from 110oC to 140oC decreases the entrainment ratio by 66.25%. At the boiler temperature of 120oC, increasing the evaporator temperature from 7.5 to 15 oC increases the entrainment ratio by 65.57%. While at the boiler temperature of 120oC and
... Show MoreTransforming the common normal distribution through the generated Kummer Beta model to the Kummer Beta Generalized Normal Distribution (KBGND) had been achieved. Then, estimating the distribution parameters and hazard function using the MLE method, and improving these estimations by employing the genetic algorithm. Simulation is used by assuming a number of models and different sample sizes. The main finding was that the common maximum likelihood (MLE) method is the best in estimating the parameters of the Kummer Beta Generalized Normal Distribution (KBGND) compared to the common maximum likelihood according to Mean Squares Error (MSE) and Mean squares Error Integral (IMSE) criteria in estimating the hazard function. While the pr
... Show MoreIn this work , the effect of chlorinated rubber (additive I), zeolite 3A with chlorinated rubber (additive II), zeolite 4A with chlorinated rubber (additiveIII), and zeolite 5A with chlorinated rubber (additive IV), on flammability for epoxy resin studied, in the weight ratios of (2, 4, 7,10 & 12%) by preparing films of (130x130x3) mm in diameters, three standard test methods used to measure the flame retardation which are ; ASTM : D-2863 , ASTM : D-635 & ASTM : D-3014. Results obtained from these tests indicated that all of them are effective and the additive IV has the highest efficiency as a flame retardant.
This work aimed to produce PVA and PVA/Ag nanofibers ultra-high sensitivity photodetector by electrospinning. The electrospinning process was used to successfully prepare PVA nanofibers and a PVA-Ag nanofiber composite. FE-SEM, XRD, UV, I-V characterizations are used to study the morphological, structural, optical, and electrical properties of the material. In contrast, the PVA-Ag nanofiber composite film displayed a cubic structure with favored orientation (200) that indicated the presence of Ag NPs in the PVA-Ag nanofibers film. While the optical energy gap for PVA was 3.96 eV, it was only 2.14 eV for PVA-Ag nanofibers composite film, making this composite sensitive to visible light, particularly green light at 550 nm with a 65% photosens
... Show MoreThis paper discussed the solution of an equivalent circuit of solar cell, where a single diode model is presented. The nonlinear equation of this model has suggested and analyzed an iterative algorithm, which work well for this equation with a suitable initial value for the iterative. The convergence of the proposed method is discussed. It is established that the algorithm has convergence of order six. The proposed algorithm is achieved with a various values of load resistance. Equation by means of equivalent circuit of a solar cell so all the determinations is achieved using Matlab in ambient temperature. The obtained results of this new method are given and the absolute errors is demonstrated.