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.
Baghdad (the capital of the Abbasid Caliphate, and his legacy oldest civilizations in history, with glory ethyl). 1. benediction this city landmarks archaeological evidence of their own Kkabbab mosques and forms gates and (Aelchenachel) 2, which adorn the walls of buildings and Chaababeckha high and palm trees, all these vocabulary inspired artists embody Baghdad warmest dissolved in their artwork and all those who lived and grew up in Baghdad embodied in his memory for the nights Beauties and their lights and Hoa_khasha. Ceramic Arts art one who embodied the most important symbols that represent the beauty and credited with Baghdad. And many Iraqis potters inspired single Baghdadi in their work, notably ceramists late arrows Saudi which
... Show Morethe Research problem entitled: (compound shapes in the work of the artist Max Ernst and Ali Najjar) the nature of the concept of compound shapes and mechanisms of functioning in contemporary art done. The research consisted of(4) four parts: the first part is dealing with the methodological framework of the Search represented the research problem , which is manifested through this study to reveal the technical features of the composite shapes, that linked achievement both artists (Max Ernst) and (Ali Al Najjar). Which is crystallized into two objectives as follows: 1 - Detection of the technical features of the composite shapes in the work of Max Ernst and Ali Al-Najjar.2 - Detection of similarities and differences in the recruitment of
... Show MoreThe current study aimed to determine the morphometric and meristic characteristics of the North African catfish Clarias gariepinus (Burchell, 1822). Six specimens of C. gariepinus were collected from the Tigris River, in central Iraq. This study is considered the confirmation first record of this species in Iraq, and the second documentation of this exotic fish. The present species is characterized by a very long dorsal fin, a rounded caudal fin and four pairs of barbels.
Studies on the flexural behavior of post-tensioned beams subjected to strand damage and strengthened with near-surface mounted (NSM) technique using carbon fiber-reinforced polymer (CFRP) are limited and fail to examine the effect of CFRP laminates on strand strain and strengthening efficiency systematically. Furthermore, a design approach for UPC structures in existing design guidelines for FRP strengthening techniques is lacking. Hence, the behavior of post-tensioned beams strengthened with NSM-CFRP laminates after partial strand damage is investigated in this study. The testing program consists of seven post-tensioned beams strengthened by NSM-CFRP laminates with three partial strand damage ratios (14.3% symmetrical damage, 14.3%
... Show MoreThe fingerprinting DNA method which depends on the unique pattern in this study was employed to detect the hydatid cyst of Echinococcus granulosus and to determine the genetic variation among their strains in different intermediate hosts (cows and sheep). The unique pattern represents the number of amplified bands and their molecular weights with specialized sequences to one sample which different from the other samples. Five hydatitd cysts samples from cows and sheep were collected, genetic analysis for isolated DNA was done using PCR technique and Random Amplified Polymorphic DNA reaction(RAPD) depending on (4) random primers, and the results showed:
... Show MoreThis study examined the relationship between the reporting lag (the timeliness of corporate financial reporting) and several independent variables: (1) Audit reporting lag,(2)Company Size,(3) Profitability of the company,(4)Company Age,(5) Sector Type.(6)Audit’s Opinion,(7) Market Type,(8) Gearing,(9) Concentration of ownership,(10) Audit Firm Size(11)Profit or Loss Company(12) Companies Listed lag on the PEX. In order to achieve the objectives of the study and testing its hypotheses, the data Obtained through actual data of a financial reports, and based on me
... Show MoreThis research aims to explore the impact of strategic intelligence by his dimensions (Foresight , system thinking, vision, motivation and partnership) on decision making styles which represented by ( rational, intuitive, dependent, Spontaneous and Avoidant style) for a sample of the administrative leaders in the center of Reconstruction &Housing Ministry and Some its formations which are companies of (Sa'ad, Al Mansour, al Farouq, Assyria, al-Mu'tasim, al- Rasheed, and Public Authority for Housing). So to achieve the research objectives and to test hypotheses, it has been relying
... Show Morethe reality of small and medium enterprises analysis reflects weaknesses plaguing these enterprises and strengths that are characterized by, and thus the formulation of appropriate solutions to the obstacles faced by these enterprises to enhance its contribution to the achievement of economic and social development. Iraqi small and medium enterprises suffer from several obstacles stand in front of development and support their competitiveness, the finance one of the main obstacles which impede growth and development of these enterprises, noting the banking system in Iraq reluctance to lend to small and medium-sized enterprises, as a result of the high cost of lending these enterprises compared to large projects, as well as
... Show MoreAbstract
This research aims to evaluate the application of the inspectors general of global indicators offices according to the axles (leadership, strategy and planning, employees, partners and resources, process management) and through the assumption main research which states that (there is an application for global indicators to evaluate performance in the offices of the ministries under study) which are subdivided into five sub-hypotheses according to the classification and division of the five axes of the checklist.
The researchers have taken refuge in the process of assessing the performance of the check list which included global i
... Show MoreA fast moving infrared excess source (G2) which is widely interpreted as a core-less gas and dust cloud approaches Sagittarius A* (Sgr A*) on a presumably elliptical orbit. VLT