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.
Multilevel models are among the most important models widely used in the application and analysis of data that are characterized by the fact that observations take a hierarchical form, In our research we examined the multilevel logistic regression model (intercept random and slope random model) , here the importance of the research highlights that the usual regression models calculate the total variance of the model and its inability to read variance and variations between levels ,however in the case of multi-level regression models, the calculation of the total variance is inaccurate and therefore these models calculate the variations for each level of the model, Where the research aims to estimate the parameters of this m
... Show MoreMetal nanoparticles (NPs) of silver (Ag), copper (Cu), zinc oxide (ZnO), cadmium oxide (CdO) and tin (Sn) were synthesized by laser ablation of a solid target in de-ionized water (DI). X-ray diffraction patterns showed the formation of AgO, Ag, Cu, ZnO, CdO, and Sn NPs. Absorbance spectrum of the produced nanoparticles was measured by UV-Vis spectrophotometer which showed that Ag and CdO NPs shifted to the short wavelength (blue shift), indicating the formation of NPs with smaller sizes, whereas CuO showed the formation two peaks. ZnO and Sn NPs shifted to the long wavelength (red shift) which indicates the formation NPs with larger size. Zeta potential results proved that ZnO nanoparticles were more stable (-26.53mV) than the othe
... Show MoreAbstract
In this work, pure Polypyrrole (PPy) and Polypyrrole (PPy)/Graphene (GN) was synthesized by in-situ polymerization in different weight percentages (0.1, 0.3, 0.5, 1, 3 and 5 wt.% (g)) of GN nano particles using chemical oxidation method at room temperature. The FTIR, SEM and electrical properties were studies for the nano composites. The result show that when concentration of GN Nano particle increase, the electrical conductivity increased and the graphene sheets were merging to form a continuous area of the GN through the polypyrrole base material. The FTIR spectra shows that the characteristics absorption peaks of polypyrrole that is, 1546.80, 1463.87 and 3400.27 cm-1(stretching vibration in the pyrrol
... Show MoreThis paper examined accounting information systems (AIS) as a mediator between small and medium-sized enterprises (SMEs) strategies, including (finance source, administrative innovation, organizational culture, developing capabilities levels of SMEs, information source, development of business managers, and technological innovation) and organizational performance. In this quantitative study, 450 self-administered questionnaires were distributed to the managers and owners of SMEs using purposive sampling. Data were analyzed using the structural equation modeling (SEM) method via SmartPLS3 Software. The study offers empirical findings on the importance of AIS as a mediator, considers various factors, a
The dual nature of asphalt binder necessitates improvements to mitigate rutting and fatigue since it performs as an elastic material under the regime of rapid loading or cold temperatures and as a viscous fluid at elevated temperatures. The present investigation assesses the effectiveness of Nano Alumina (NA), Nano Silica (NS), and Nano Titanium Dioxide (NT) at weight percentages of 0, 2, 4, 6, and 8% in asphalt cement to enhance both asphalt binder and mixture performance. Binder evaluations include tests for consistency, thermal susceptibility, aging, and workability, while mixture assessments focus on Marshall properties, moisture susceptibility, resilient modulus, permanent deformation, and fatigue characteristics. NS notably im
... Show MoreFive isolates of Gram negative bacteria (Klebsiella pneumoniae, Psuedomonas auroginosa, proteus mirabilis and two strains of E.coli) were in quested for the ability of bearing silver nanoparticles by using LB medium, all the isolates of bacteria were buttered brown color just as soon as mixed the supernatant of bacterial culture with AgNO3 solution, that refered the biosynthesis of Silver nanoparticles (Ag NPs). UV–visible spectrophotometer and Fourier transform infrared (FTIR) spectroscopy were utilized for estimation of (Ag NPs). The five isolates of bacteria were tendered to produce spontaneous mutants by using different kinds of antibiotics, Ampicillin put to use for making mutant in E.coli and Proteus mirabillis, while Pseudom
... Show MoreThis study includes the preparation of the ferrite nanoparticles CuxCe0.3-XNi0.7Fe2O4 (where: x = 0, 0.05, 0.1, 0.15, 0.2, 0.25, 0.3) using the sol-gel (auto combustion) method, and citric acid was used as a fuel for combustion. The results of the tests conducted by X-ray diffraction (XRD), emitting-field scanning electron microscopy (FE-SEM), energy-dispersive X-ray analyzer (EDX), and Vibration Sample Magnetic Device (VSM) showed that the compound has a face-centered cubic structure, and the lattice constant is increased with increasing Cu ion. On the other hand, the compound has apparent porosity and spherical particles, and t
... Show MoreThe intellectual property of digital documents has been protected by using many methods of digital watermarking. Digital documents have been so much of advantages over print documents. Digital documents are less expensive and easy to store, transport, and searched compared to traditional print documents. But it has its owner limitation too. A simple image editor can be used to modify and make a forged document. Digital documents can be tampered easily. In order to utilize the whole benefits of digital document, these limitations have to overcome these limitations by embedding some text, logo sequence that identifies the owner of the document..
In this research LSB technique has been used
... Show Moresix specimens of the Hg0.5Pb0.5Ba2Ca2Cu3-y