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.
Objective: To assess knowledge of pregnant women concerning prenatal care who attend primary health care
center in Baghdad city.
Methodology: A descriptive analytic study carried on (100) pregnant women who attend primary health care
centers in Baghdad city (50) of them from Al- Sheik Omer primary health care center \Resafa sector .and 50 from
Belat Al-Shuhadaa/ Al Karch sector, during the period from April to November 2011. The data were collected
through interview and use questionnaire format. Validity and Reliability of the questionnaire were determined
through panel of experts and pilot study, data were analysed through the application of descriptive statistical
analysis and inferential statistical analysis.
R
Objective: impact of the education program for nurses' knowledge toward children under mechanical
ventilation, and to find out the relationships between nurses' knowledge and their general information.
Methodology: Quasi experimental study was carried out at the respiratory care units of Baghdad
Pediatric Teaching Hospitals started from February15th, until September 26th, 2011, A purposive (nonprobability)
sample of (23) nurses working in the respiratory care units, were selected from Children
Welfare and Pediatric Central Teaching Hospitals. The data were gathered through using of the
constructed multiple choice questionnaire using to evaluate the nurses knowledge using checklist, The
questionnaire consists of two p
This study aimed to identify attitudes towards mental illness in pregnant female clients to clinics women in the province of Ramallah and Al Bireh, for this purpose applied to study procedures on a sample of (200) of pregnant mothers were selected a sample available, have reached results no statistically significant differences in the level of attitudes towards mental illness due to the variable age in mothers pregnant female clients to clinics for women. Ther were astatistically significant differences in the level of these trends depending on the variable-level scientific research for the benefit of pregnant class university students and older and then high school and so on all areas except the area of social interaction, The results a
... Show MoreBackground: One of the most common complications of dentures is its ability to fracture, so the aim of this study was to reinforce the high impact denture base with carbon nanotubes in different concentrations to improve the mechanical and physical properties of the denture base. Materials and methods: Three concentrations of carbon nanotubes was used 0.5%, 1%, 1.5% in a pilot study to see the best values regarding transverse strength, impact, hardness and roughness test, 1 wt% was the best concentration, so new samples for control group and 1wt% carbon nanotubes and the previous tests were of course repeated. Results: There was a significant increase in impact strength and transverse strength when we add carbon nanotubes in 1wt%, compared
... Show MoreIn this work silicon solar cell has been used with semicircular grooves to improve its efficiency by reducing reflection of rays and increasing optical path through the cell. Software program for optical design (zemax) has been used by ray tracing mode to evaluate prototype efficiency when using detector beneath the cell. The prototype has aspect ratio (A.R=0.2) which is the best efficiency at incident angle (ϴ=0ͦ) and the best acceptance angle (ϴ=50ͦ).
This research deals with study of the Petrology and mineralogy of the Rus and Jil Formations at Najif and Al-Muthanna Governorates, Southern Iraq. The Rus Formation consists mainly of evaporites and subordinate carbonates. The evaporites are characterized by nodular structure (compound wispy, wispy, structureless and mosaic structures) with some laminated structure at the studied sections. Compound wispy to wispy structure are the dominant structures. The Jil Formation consists almost entirely of carbonate. The carbonate rocks are dolomitic limestone and dolomite beds, massive, fossiliferous, cavernous sometime friable and bioturbated in its lower part. The Jil Formation contains evaporites as thin beds, sometimes nodular and contains se
... Show MoreThis research is a comparative jurisprudential study that focuses on Imam Al-Bayhaqi’s preferred opinions in his book Al-Khilafiyat (The Disagreements), the part of Al-Rida’a (Breastfeeding). It is considered one of the most important familial topics that is concerned with organizing the social relations in Islam, strengthens the family ties and that prevents the family disintegration due to the ignorance and lack in comprehending Sharia laws (Islam law) in all aspects. The study follows the inductive and descriptive method. It aims at examining the prohibition of marriage when breastfeeding takes place at the time of woman’s conversion to Islam or during her infidelity period. It further aims at verifying the prohibition
... Show MoreCongenital valvular pulmonary stenosis accounts for 5-10% of all congenital heart disease. Balloon pulmonary valvuloplasty is a safe and effective method in reduction of moderate to severe valvular pulmonary stenosis. This retrospective study done in Hawler surgical specialty cardiac center on pediatric patients who had pulmonary valve stenosis (with echocardiographic peak gradient 2:50mmHg) and treated by balloon pulmonary valvuloplasty. A total of 178 cases were involved, 93(52.25%) patient was male and 85 (47.75%) patients was female. 160 patient (89.89%) were treated with single balloon method 18 patient (10.11%) were managed by double balloon method technique. Follow up period of these patients range from 1 year to 10 years (mean of 5.
... Show More