Preferred Language
Articles
/
LxfsW5IBVTCNdQwCqq1N
A New Proposed Hybrid Learning Approach with Features for Extraction of Image Classification
...Show More Authors

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.

Scopus Clarivate Crossref
View Publication
Publication Date
Sun Feb 25 2024
Journal Name
Baghdad Science Journal
Prioritized Text Detergent: Comparing Two Judgment Scales of Analytic Hierarchy Process on Prioritizing Pre-Processing Techniques on Social Media Sentiment Analysis
...Show More Authors

Most companies use social media data for business. Sentiment analysis automatically gathers analyses and summarizes this type of data. Managing unstructured social media data is difficult. Noisy data is a challenge to sentiment analysis. Since over 50% of the sentiment analysis process is data pre-processing, processing big social media data is challenging too. If pre-processing is carried out correctly, data accuracy may improve. Also, sentiment analysis workflow is highly dependent. Because no pre-processing technique works well in all situations or with all data sources, choosing the most important ones is crucial. Prioritization is an excellent technique for choosing the most important ones. As one of many Multi-Criteria Decision Mak

... Show More
View Publication Preview PDF
Scopus (1)
Scopus Crossref
Publication Date
Wed Jul 17 2019
Journal Name
Iraqi Journal Of Science
Induced callus from seedlings of Peganum harmala L. and studying harmine compound concentration in vitro and in vivo by GC analysis
...Show More Authors

Plant tissue culture considers a benefit biotechnological technique for scientific research especially the production of undifferentiation callus cells and regeneration through suspension or static media. The seedlings of Peganum harmala was used as a source to produce callus mass in vitro in static media through different tissue culture media supplemented by varying combinations of plant growth regulators (PGR). The result illustrates that 2 mg/l of Kinitine with 0.5 mg/l of 2, 4-D was efficient to stimulate callus induction with percent 100% in stem and root of P. harmala and this combination gave a high fresh weight, 1954 mg in root and 1170
mg in stem and high dry weight in root and stem was 74.6

... Show More
View Publication Preview PDF
Scopus (5)
Crossref (2)
Scopus Crossref
Publication Date
Sun Jan 01 2017
Journal Name
Food And Nutrition Sciences
Optimization of Culture Conditions to Produce Phytase from <i>Aspergillus tubingensis SKA</i>
...Show More Authors

The effects of nutrients and physical conditions on phytase production were investigated with a recently isolated strain of Aspergillus tubingensis SKA under solid state fermentation on wheat bran. The nutrient factors investigated included carbon source, nitrogen source, phosphate source and concentration, metal ions (salts) and the physical parameters investigated included inoculum size, pH, temperature and fermentation duration. Our investigations revealed that optimal productivity of phytase was achieved using wheat bran supplemented with: 1.5% glucose. 0.5% (NH4)2SO4, 0.1% sodium phytate. Additionally, optimal physical conditions were 1 × 105 spore/g substrate, initial pH of 5.0, temperature of fermentation 30˚C and fermentation dura

... Show More
View Publication Preview PDF
Crossref (6)
Crossref
Publication Date
Tue Aug 31 2021
Journal Name
Iraqi Journal Of Science
The Utilization of Remote Sensing Imagery and Inverse Distance Weighted Scheme to Simulate the White Oil Effects on Soil Geotechnical Properties
...Show More Authors

     This research aims to utilize a complementarity of field excavations and laboratory works with spatial analyses techniques for a highly accurate modeling of soil geotechniques properties (i.e. having lower root mean square error value for the spatial interpolation). This was conducted, for a specified area of interest, firstly by adopting spatially sufficient and  well distributed samples (cores). Then, in the second step, a simulation is performed for the variations in properties when soil is contaminated with commonly used industrial material, which is white oil in our case. Cohesive (disturbed and undisturbed) soil samples were obtained from three various locations inside Baghdad University campus in AL-J

... Show More
View Publication Preview PDF
Scopus Crossref
Publication Date
Thu Jan 30 2025
Journal Name
Journal Of Baghdad College Of Dentistry
The validity of salivary microRNAs (hsa-miR-200a, hsa-miR-125a and hsa- miR-93) as oral squamous cell carcinoma biomarker
...Show More Authors

Background: Oral squamous cell carcinoma represents the vast majority of oral cancer it is a common malignant tumor with an increasing incidence. Around the world, the 5 year mortality rate of oral cancer is about 50%. Thus novel biomarkers for early detection oral squamous cell carcinoma are needed. The level of three salivary microRNAs namely hsa-miR-200a, hsa-miR-125a and hsa- miR-93 were measured in saliva of patients with oral squamous cell carcinoma and compared their levels in saliva of healthy control subjects to determine their potential as oral cancer biomarker. Materials and methods: The level of these three microRNAs was measured by using revers transcription, preamplification and quantitative PCR. Results: Only miR-200a presen

... Show More
View Publication Preview PDF
Publication Date
Mon Jun 30 2014
Journal Name
Al-kindy College Medical Journal
Unstable Angina /Non ST Elevation Myocardial Infarction: Frequency of Conventional Risk Factors; TIMI Risk Score, and Their Impact On Angiographic Data
...Show More Authors

Background: Appreciation of the crucial role of risk factors in the development of coronary artery disease (CAD) is one of the most significant advances in the understanding of this important disease. Extensive epidemiological research has established cigarette smoking, diabetes, hyperlipidemia, and hypertension as independent risk factors for CADObjective: To determine the prevalence of the 4 conventional risk factors(cigarette smoking, diabetes, hyperlipidemia, and hypertension) among patients with CAD and to determine the correlation of Thrombolysis in Myocardial Infarction (TIMI) risk score with the extent of coronary artery disease (CAD) in patients with unstable angina /non ST elevation myocardial infarction (UA/NSTEMI).Methods: We

... Show More
View Publication Preview PDF
Publication Date
Fri Jan 13 2023
Journal Name
Atmosphere
Impact of North African Sand and Dust Storms on the Middle East Using Iraq as an Example: Causes, Sources, and Mitigation
...Show More Authors

This study aims to determine the reasons for the increase in the frequency of sand and dust storms in the Middle East and to identify their sources and mitigate them. A set of climatic data from 60 years (1960–2022) was analyzed. Sand storms in Iraq are a silty sand mature arkose composed of 72.7% sand, 25.1% silt, and 2.19% clay; the clay fraction in dust storms constitutes 70%, with a small amount of silt (20.6%) and sand (9.4%). Dust and sand storms (%) are composed of quartz (49.2, 67.1), feldspar (4.9, 20.9), calcite (38, 5), gypsum (4.8, 0.4), dolomite (0.8, 1.0), and heavy minerals (3.2, 6.6). Increasing temperatures in Iraq, by an average of 2 °C for sixty years, have contributed to an increase in the number of dust storm

... Show More
View Publication Preview PDF
Crossref (19)
Crossref
Publication Date
Sat Sep 30 2023
Journal Name
Iraqi Journal Of Science
Clinical Characteristics of the SARS-CoV-2 Alpha, Delta, Delta plus and Omicron Variants versus the Wild Type in Iraqi Patients
...Show More Authors

     Coronavirus disease 2019 (COVID-19) is caused by severe acute respiratory syndrome called coronavirus 2 (SARS-CoV-2). Due to its concerning rate of transmission and intensity, coronavirus was classified as a pandemic on March 11, 2020. With the continuous evolution of the viral genome and mutations that may alter infectivity, disease severity or interactions with host immunity, SARS-CoV-2 has evolved into many variants: Alpha (B.1.1.7 lineage), Delta (B.1.617.2 lineage), Delta plus (B.1.617.2.1), Omicron (B.1.1.529 lineage) and other variants. Thus, this study aimed to find and provide database for local clinical characteristics of different variants of SARS-COV-2 and severity of infection with viral load compared with the wild

... Show More
View Publication
Scopus (1)
Crossref (1)
Scopus Crossref
Publication Date
Mon Aug 01 2022
Journal Name
Azerbaijan Medical Journal
Molecular Co- Localization of Human Papilloma Virus 6 / 11 in Combined Resected Tissues from Nononcologic Palatine and Pharyngeal Tonsillar Hypertrophies
...Show More Authors

More than 450 distinct types of human papilloma virus recognized via recent molecular techniques. The low and high oncogenic risk-HPV genotypes have an association with a variety of benign and malignant tumors in the oropharyngeal and nasopharyngeal localizations. This study aimed to determine the rate of DNA detection of HPV genotype 6/11 in non-oncologic nasopharyngeal and palatine tonsillar tissues from pediatric patients subjected to adeno-tonsillectomies. A total number of 64 tissue specimens enrolled; 44 non-oncologic nasopharyngeal and palatine hypertrophied tissue specimens from 22 pediatric patients sustained combined adeno-tonsillectomies and compared to 20 nasal trimmed tissues with unremarkable pathological changes (in

... Show More
Publication Date
Mon Jan 01 2024
Journal Name
Russian Electronic Journal Of Radiology
COHORT COMPARATIVE STUDY OF COVID-19 VACCINATED AND NON-VACCINATED PATIENTS DEPENDING ON CT CHEST FINDINGS BETWEEN IRAQI AND JORDANIAN POPULATION
...Show More Authors

View Publication Preview PDF
Scopus Crossref