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
Thu Apr 20 2017
Journal Name
International Journal Of Science And Research (ijsr)
Learning Styles according to the Model of Felder & Silverman and its Relationship with Mathematical Self-perceived Efficacy to Students of the College of Education for Pure Sciences-Ibn Al-Haitham
...Show More Authors

This research aims toknow the learning styles according to the model of Felder and Silverman and its relationship to effectively self- perceived mathematicalamong students of the Faculty of Education Pure Sciences - Ibn al-Haytham. By answering the following questions: 1. What are the preferred methods of learning among students in the mathematics department according to the model Felder and Silverman? 2. What is the mathematicalself-perceived levelof the students at the Department of Mathematics effectiveness level? 3. What is the relationship between learning styles according to the Felder model and Silverman and the effectiveness of mathematical self-perceived of the students of the Department of Mathematics? The research sample consiste

... Show More
Publication Date
Sun Apr 30 2023
Journal Name
Al-kindy College Medical Journal
Clinicopathological Features and ICD-10 Categorization of Oro-maxillofacial Surgical Biopsies from Sulaimani
...Show More Authors

Background: Few updated retrospective histopathological-based studies in Iraq evaluate a comprehensive spectrum of oro-maxillofacial lesions. Also, there was a need for a systematic way of categorizing the diseases and reporting results in codes according to the WHO classification that helps occupational health professionals in the clinical-epidemiological approach.

Objectives: to establish an electronic archiving database according to the ICD-10 that encompasses oro-maxillofacial lesions in Sulaimani city for the last 12 years, then to study the prevalence trend and correlation with clinicopathological parameters.

Subjects and Methods:  A descri

... Show More
View Publication Preview PDF
Scopus Crossref
Publication Date
Sun Jan 01 2017
Journal Name
International Journal Of Science And Nature
Morphological features of the small intestine in the adult indigenous Gazelle (Gazella Subgutturosa)
...Show More Authors

View Publication
Publication Date
Thu Oct 01 2015
Journal Name
Al-academy
Artistic features of women form in (Auguste-Dominique Ingres) works: نـدى عايـد يوسـف
...Show More Authors

Between decline and appearing dichotomy, art history comes to announce birth of an era that glories past and find new names that are emerged from yearning to past and represented by neo-classical, By refusing the previous approaches and create topics that touché culture and derived from it through s revitalizing ideal beauty standards. One of neo-classical artists, who tried to simulate the classical works, is (Jean-Auguste-Dominique Ingres), who put framework for semantic aesthetic of the art form by revitalizing past glories and deeply searching myths and cultures through finding special artistic features that emphasizes artist own stylistics and identity. This research studies artistic features of women form in (Jean-Auguste-D

... Show More
View Publication Preview PDF
Crossref
Publication Date
Sun Jan 22 2023
Journal Name
Mesopotamian Journal Of Big Data
Parallel Machine Learning Algorithms
...Show More Authors

 To expedite the learning process, a group of algorithms known as parallel machine learning algorithmscan be executed simultaneously on several computers or processors. As data grows in both size andcomplexity, and as businesses seek efficient ways to mine that data for insights, algorithms like thesewill become increasingly crucial. Data parallelism, model parallelism, and hybrid techniques are justsome of the methods described in this article for speeding up machine learning algorithms. We alsocover the benefits and threats associated with parallel machine learning, such as data splitting,communication, and scalability. We compare how well various methods perform on a variety ofmachine learning tasks and datasets, and we talk abo

... Show More
View Publication
Scopus (23)
Crossref (16)
Scopus Crossref
Publication Date
Sun Jan 25 2026
Journal Name
Journal Of Baghdad College Of Dentistry
A Micro Computed Tomography Assessment of New Carrier-Based Root Canal Fillings
...Show More Authors

Background: The main aim of the present study is to qualify and quantify voids formation of root canals obturated with GuttaCore (GC) and experimental Hydroxyapatite polyethylene (HA/PE) as new carrier-based root canal fillings by using micro computed tomography scan. Materials and methods: In the present study, eight straight single-rooted human permanent premolar teeth are selected and disinfected, then stored in distilled water. The teeth decoronated leaving a root length of 12mm each. The root canals instrumented by using crown down technique and the apical diameter of the root canal prepared to a size # 30/0.04 for achieving standardized measurements. A 5mL of 17% EDTA used to remove the smear layer followed by 5mL of 2.5% NaOCl and r

... Show More
View Publication Preview PDF
Publication Date
Thu Dec 01 2022
Journal Name
Wiadomości Lekarskie
EVALUATION OF TWO CRYOPROTECTANTS USED IN A NEW HUMAN SPERM CRYOPRESERVATION TECHNIQUE
...Show More Authors

The aim: To examine the efficiency of different concentrations of Dimethyl sulfoxide (DMSO) and glycerol as a cytoprotectants in protection of human sperms during cryopres¬ervation in this technique. Materials and methods: Thirty oligozoospermic semen samples were used in this study. Samples diagnosed according to WHO 2010 criteria. Sheep’s ovarian follicles obtained from local slaughterhouse and prepared by slicing the ovaries and evacuating the follicular fluid and oocyte. Each semen sample divided into six equal parts, and diluted 1:1 with cryosolution contains 5%, 10%, 15% DMSO or glycerol and injected within the emptied follicles. After freezing and thawing, the semen mixture aspired outside the follicles and sperm concentr

... Show More
View Publication
Scopus Crossref
Publication Date
Thu Jan 31 2019
Journal Name
Journal Of The College Of Education For Women
A New Vision in the Locality and the Factors of Forming Meander
...Show More Authors

The research addressed an analytical field investigation of the locality of meander, the factors responsible of the locality of the meander at certain points of the stream other than others, and the role sequence of these factors in the formation process.
The research revealed that the location of forming the meander was associated closely with the scale structural composition of the bank materials from which the first stage of forming the curved stream, for the inhomogeneous or non-identical opposite banks in their scale structural composition saw an activity of differential corrosion, while the homogeneous and identical opposite banks in their scale structural composition saw an identical corrosion activity in its intensity at both

... Show More
View Publication Preview PDF
Publication Date
Wed Feb 01 2023
Journal Name
Baghdad Science Journal
Synthesis, Characterization, and Thermal Analysis of a New Acidicazo Ligand's Metal Complexes
...Show More Authors

The researchers wanted to make a new azo imidazole as a follow-up to their previous work. The ligand 4-[(2-Amino-4-phenylazo)-methyl]-cyclohexane carboxylic acid as a derivative of trans-4-(aminomethyl) cyclohexane carboxylic acid diazonium salt, and synthesis a series of its chelate complexes with metalions, characterized these compounds using a variety technique, including elemental analysis, FTIR, LC-Mass, 1H-NMRand UV-Vis spectral process as well TGA, conductivity and magnetic quantifications. Analytical data showed that the Co (II) complex out to 1:1 metal-ligand ratio with square planner and tetrahedral geometry, respectively while 1:2 metal-ligand ratio in the Cu(II), Cr(III), Mn(II), Zn(II), Ru(III)and Rh(III)complexes

... Show More
View Publication Preview PDF
Scopus (33)
Crossref (10)
Scopus Clarivate Crossref
Publication Date
Sun Jul 01 2001
Journal Name
Bulletin Of The Iraq Natural History Museum (p-issn: 1017-8678 , E-issn: 2311-9799)
A new species of Wohlfahrtia Brauer and Bergenstam (Dipetera: Sarcophagidae) from Iraq
...Show More Authors

Wohlfahrtia longicorpuris sp. nov., from Iraq described, illustrated and distinguished from related species. The adults were reared from larvae collected from ulcer of a human face. Wohlfahrtia Brauer and Bergenstam is one of most important genus,which contains 19 species (Pape, 1998), some of these produce myiasis in mammals (Verves,1985).Taxonomic revision of this genus has been carried out by the following authors: Rohdendrof (1956), Zumpt (1965) and Pape (1996).

 

View Publication Preview PDF