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 class

This paper proposes improving the structure of the neural controller based on the identification model for nonlinear systems. The goal of this work is to employ the structure of the Modified Elman Neural Network (MENN) model into the NARMA-L2 structure instead of Multi-Layer Perceptron (MLP) model in order to construct a new hybrid neural structure that can be used as an identifier model and a nonlinear controller for the SISO linear or nonlinear systems. Two learning algorithms are used to adjust the parameters weight of the hybrid neural structure with its serial-parallel configuration; the first one is supervised learning algorithm based Back Propagation Algorithm (BPA) and the second one is an intelligent algorithm n

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 class

In this work, new Schiff bases of quinazolinone derivatives (Q1-Q5) were synthesized from methyl anthranilate. The synthesis involved three steps. In the first step, methyl anthranilate was reacted with isothiocyanatobenzene, producing the thiourea derivative K1. The second step entailed reacting K1 with hydrazine hydrate, synthesizing 3-amino-2-(phenylamino) quinazolin-4(3H)-one (K2). The third step involved reaction of K2 with various aromatic aldehydes, yielding the Schiff bases derivatives Q1-Q5. The chemical structures of these compounds were identified by FT-IR,1H NMR and 13C NMR spectroscopy. The newly synthesized derivatives (Q1-Q5) were subjected to rigorous evaluation to assess their efficacy as corrosion inhibitors for ca

The bacterial isolates were obtained from Al-Kindi Hospital were diagnosed by the Vitek-2 system and re confirm by 16srRNA gene as S. aurous, the results were shown 20 isolates (66.7%) out of 30 isolates were positive to protease production. All bacterial isolates (100%) were sensitive to Gentamicin and Levofloxacin. but resistant (100%) to aztreonam. The best temperature for enzyme production from bacteria was 37 °C, and the best pH for enzyme production was 7. Partial purification of the bacterial enzyme (protease) was carried out using short steps included ammonium sulfate 65% saturation, ion exchange using DEAE- cellulose column and then applied on gel filtration chromatography using Sephadex G-200 column. The enzymatic activit

Natural fibers and particles reinforced composites are being broadly used due to their bio and specific properties such as low density and easy to machine and production with low cost. In this work, water absorption and mechanical properties such as tensile strength, flexural strength and impact strength of recycled jute fibers reinforced epoxy resin were enhanced by treating these fibers with alkaline solution. The recycled jute fibers were treated with different concentration of (NaOH) solution at (25 ⁰C) for a period of (24) hours. From the obtained results, it was found that all these properties are improved when fibers treated with (7.5wt% NaOH) related to untreated fibers. Conversely, the mentioned properties of composit

A series of new compounds including p-bromo methyl pheno acetate [2]. N-( aminocarbonyl)–p-bromo pheno acetamide [3] , N-( aminothioyl) -p-bromo phenoacetyl amide [4], N-[4-(p-di phenyl)-1,3-oxazol-2-yl]-p-bromopheno acetamide [5],N-[4-p-di phenyl]-1,3-thiazol-2-yl-p-bromo phenoacet amide [6], p-bromopheno acetic acid hydrazide [7] , 1-N-(p-bromo pheno acetyl)-1,2-dihydro-pyridazin-3,6- dione [8], 1-N-(p-bromo pheno acetyl)-1,2-dihydro-phthalazin-3,8- dione[ 9], 1-(p-bromo pheno acetyl)-3-methylpyrazol-5-one [10] and 1-(p-bromo phenol acetyl)- 3,5-dimethyl pyrazole [11] have been synthesized. The prepared compounds were characterized by m.p.,FT-IR and 1H-NMR spectroscopy. Also ,the biological activity was evaluated .