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.
A new ligand (H4L) and its complexes with (CoII, NiII, CuII and PdII). This ligand was prepared in two steps, in the first step a solution of terephthaldehyde in methanol reacted under refluxe with 1,2-phenylenediamine to give precursore compound which reacted in the second step with 2,4- dihydroxybenzaldehyde to give the ligand. The complexes were synthesized by direct reaction of the corresponding metal chloride with the ligand. The ligand and complexes were characterized by spectroscopic methods [FT-IR, UV-vis, 1HNMR, HPLC and atomic absorption], chloride contant in addition to conductivity measurement. The stability constant K and Gibbs free energy ∆G were calculated for [[Ni2(H2L)Cl2], [Cu2(H2L)Cl2] complexes using spectrophoto
... Show MoreNon-steroidal anti-inflammatory drugs (NSAIDs) contain free –COOH which thought to be responsible for the GI irritation associated with all traditional NSAIDs. The esterification of this group is one of an approach to ultimate aim for reduce the gastric irritation; so in this study we synthesized and preliminarily evaluated new ester compounds as new analogues with expected selectivity toward COX-2 enzyme. Synthetic procedures have been successfully developed for the generation of the target compounds (III a and b). The synthetic approach involved multi-steps procedures which include: Synthesis of 4-hydroxy benzene sulphonamide ( I b ), synthesis of Naproxen and Ibuprofen acyl chloride and then reacting them with 4-hydroxy benzene sulphon
... Show MoreThe New Schiff base ligand 4,4'-[(1,1'-Biphenyl)-4,4'-diyl,bis-(azo)-bis-[2-Salicylidene thiosemicarbazide](HL)(BASTSC)and its complexes with Co(II), Ni(II), and Cu(II) were prepared and characterized by elemental analysis, electronic, FTIR, magnetic susceptibility measurements. The analytical and spectral data showed, the stiochiometry of the complexes to be 1:1 (metal: ligand). FTIR spectral data showed that the ligand behaves as dibasic hexadentate molecule with (N, S, O) donor sequence towards metal ions. The octahedral geometry for Co(II), Ni(II), and Cu(II) complexes and non electrolyte behavior was suggested according to the analysis data.
Coupling reaction of 4-aminoantipyrene with 8-hydroxyqunoline gave the new bidentate azo ligand 5-(4-antipyrene azo)-8-hydroxyqunoline. Treatment of this ligand with the following metals ions (MnII, CoII, NiII, CuII and ZnII) in aqueous ethanol with a 1:2 M:L ratio yielded a series of neutral complexes of the general formula [M(L)2Cl2]. The prepared complexes were characterized using flame atomic absorption, FT.IR, UV-Vis spectroscopic as well as magnetic susceptibility and conductivity measurements. Chloride ion content were also evaluated by (Mohr Method). From above data, the proposed molecular structure for these complexes as octahedral geometry.
Numerous integral and local electron density’s topological parameters of significant metal-metal and metal-ligand bonding interactions in a trinuclear tetrahydrido cluster [(Cp* Ir) (Cp Ru)2 (μ3-H) (μ-H)3]1 (Cp = η5 -C5Me5), (Cp* = η5 -C5Me4Et) were calculated and interpreted by using the quantum theory of atoms in molecules (QTAIM). The properties of bond critical points such as the delocalization indices δ (A, B), the electron density ρ(r), the local kinetic energy density G(r), the Laplacian of the electron density ∇2ρ(r), the local energy density
... Show Moren this study, data or X-ray images Fixable Image Transport System (FITS) of objects were analyzed, where energy was collected from the body by several sensors; each sensor receives energy within a specific range, and when energy was collected from all sensors, the image was formed carrying information about that body. The images can be transferred and stored easily. The images were analyzed using the DS9 program to obtain a spectrum for each object,an energy corresponding to the photons collected per second. This study analyzed images for two types of objects (globular and open clusters). The results showed that the five open star clusters contain roughly t
... Show More