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.
This paper provides an identification key to the species of Orthetrum Newman, 1833 (Odonata, Libellulidae), including six species that were collected from different localities in Iraq.
The species of O. anceps (Schneider, 1845) is registered as a new record in Iraq; the most important characters which are used in diagnostic key are included
The city of Derna has distinctive architectural and architectural features, like other Arab and Islamic cities in the Arab West and North Africa. Its markets and shops have taken many different forms and structural forms within the urban fabric of the central commercial zone. The meeting between the various commercial and handicraft jobs and consumers within a spatial area starting with the old markets of the dark market and the agency of the harvest and vegetable market and the mosque of the old and the square of the mosque and the Red Square and the square Kharazin. It then grew linearly towards commercial hubs that were associated with the city's expansion axes. Old markets represent the architectural and planning heritage associated
... Show MoreEat this research study features Technical Ceramics Islamic and Chinese The study of four chapters , such as the first chapter the general framework for research and containing the problem that put the following question: Mamdy effect features art on porcelain Islamic and Chinese ) , and whether there are dimensions of the aesthetic , intellectual and ideological in porcelain Islamic and Chinese with lies the importance of research in the promise of a qualitative study and add a scientific theme features art in porcelain Islamic and China , and the objectives of this study One was in the detection of features technical Ceramics Islamic and Chinese study examined the length of time the ninth century AD , and the tenth century AD , and in
... Show MoreThe sensitivity of SnO2 nanoparticles/reduced graphene oxide hybrid to NO2 gas is discussed in the present work using density functional theory (DFT). The SnO2 nanoparticles shapes are taken as pyramids, as proved by experiments. The reduced graphene oxide (rGO) edges have oxygen or oxygen-containing functional groups. However, the upper and lower surfaces of rGO are clean, as expected from the oxide reduction procedure. Results show that SnO2 particles are connected at the edges of rGO, making a p-n heterojunction with a reduced agglomeration of SnO2 particles and high gas sensitivity. The DFT results are in
Successfully, theoretical equations were established to study the effect of solvent polarities on the electron current density, fill factor and efficiencies of Tris (8-hydroxy) quinoline aluminum (Alq3)/ ZnO solar cells. Three different solvents studied in this theoretical works, namely 1-propanol, ethanol and acetonitrile. The quantum model of transition energy in donor–acceptor system was used to derive a current formula. After that, it has been used to calculate the fill factor and the efficiency of the solar cell. The calculations indicated that the efficiency of the solar cell is influenced by the polarity of solvents. The best performance was for the solar cell based on acetonitrile as a solvent with electron current density of (5.0
... Show MoreDeep learning (DL) plays a significant role in several tasks, especially classification and prediction. Classification tasks can be efficiently achieved via convolutional neural networks (CNN) with a huge dataset, while recurrent neural networks (RNN) can perform prediction tasks due to their ability to remember time series data. In this paper, three models have been proposed to certify the evaluation track for classification and prediction tasks associated with four datasets (two for each task). These models are CNN and RNN, which include two models (Long Short Term Memory (LSTM)) and GRU (Gated Recurrent Unit). Each model is employed to work consequently over the two mentioned tasks to draw a road map of deep learning mod
... Show MoreA study of Zooplankton community has been carried out at four selected sites on Dukan Lake. Samples of water and zooplankton were collected monthly for the period from July 2015 to February 2016. Some physical and chemical properties of water were studied and the results showed that the air temperature were ranged from 0 to 36.16 °C, water temperature ranged from 2.83 to 34.66 °C, hydrogen ion concentration of studied sites were found to lie in alkaline side, it was ranged between 6.87 to 8.57, electrical conductivity ranged from 190.79 to 850.08 µs.cm¹, turbidity ranged from 0.9-7.7 NTU, and dissolved oxygen from 3.3 to 6.8 mg.l-¹ while BOD5 were ranged from 0.53 to 34.66 mg.l-¹. Concerning to the zooplankton, 37 species were ident
... Show More