Preferred Language
Articles
/
fBb2j4oBVTCNdQwCuJ_G
Deep Transfer Learning for Improved Detection of Keratoconus using Corneal Topographic Maps
...Show More Authors
Abstract <p>Clinical keratoconus (KCN) detection is a challenging and time-consuming task. In the diagnosis process, ophthalmologists must revise demographic and clinical ophthalmic examinations. The latter include slit-lamb, corneal topographic maps, and Pentacam indices (PI). We propose an Ensemble of Deep Transfer Learning (EDTL) based on corneal topographic maps. We consider four pretrained networks, SqueezeNet (SqN), AlexNet (AN), ShuffleNet (SfN), and MobileNet-v2 (MN), and fine-tune them on a dataset of KCN and normal cases, each including four topographic maps. We also consider a PI classifier. Then, our EDTL method combines the output probabilities of each of the five classifiers to obtain a decision based on the fusion of probabilities. Individually, the classifier based on PI achieved 93.1% accuracy, whereas the deep classifiers reached classification accuracies over 90% only in isolated cases. Overall, the average accuracy of the deep networks over the four corneal maps ranged from 86% (SfN) to 89.9% (AN). The classifier ensemble increased the accuracy of the deep classifiers based on corneal maps to values ranging (92.2% to 93.1%) for SqN and (93.1% to 94.8%) for AN. Including in the ensemble-specific combinations of corneal maps’ classifiers and PI increased the accuracy to 98.3%. Moreover, visualization of first learner filters in the networks and Grad-CAMs confirmed that the networks had learned relevant clinical features. This study shows the potential of creating ensembles of deep classifiers fine-tuned with a transfer learning strategy as it resulted in an improved accuracy while showing learnable filters and Grad-CAMs that agree with clinical knowledge. This is a step further towards the potential clinical deployment of an improved computer-assisted diagnosis system for KCN detection to help ophthalmologists to confirm the clinical decision and to perform fast and accurate KCN treatment.</p>
Scopus Clarivate Crossref
View Publication
Publication Date
Thu Jul 01 2021
Journal Name
Journal Of Physical Education
The effect of e-learning on learning the skills of short Service and front-dimensional blow for badminton players under the age of 15 years.
...Show More Authors

AO Dr. Ali Jihad, Journal of Physical Education, 2021

View Publication
Publication Date
Fri Jan 20 2023
Journal Name
Journal Of Electronic Materials
Influence of Dry and Wet Etching on AlInSb Contact Resistivity, Transfer Length, and Sheet Resistance Using Circular Transmission Model
...Show More Authors

View Publication
Scopus (4)
Crossref (4)
Scopus Clarivate Crossref
Publication Date
Wed Sep 01 2010
Journal Name
Al-khwarizmi Engineering Journal
Prediction of the Scale Removal Rate in Heat Exchanger Piping System Using the Analogies between Mass and Momentum Transfer
...Show More Authors

The possibility of predicting the mass transfer controlled CaCO3 scale removal   rate has been investigated.

Experiments were carried out using chelating agents as a cleaning solution at different time and Reynolds’s number. The results of CaCO3 scale removal or (mass transfer rate) (as it is the controlling process) are compared with proposed model of prandtl’s and Taylor particularly based on the concept of analogy among momentum and mass transfer.

Correlation for the variation of Sherwood number ( or mass transfer rate ) with Reynolds’s number have been obtained .

View Publication Preview PDF
Publication Date
Fri Apr 28 2023
Journal Name
Surgical Neurology International
Neurosurgery theater-based learning: Etiquette and preparation tips for medical students
...Show More Authors

View Publication Preview PDF
Scopus (1)
Crossref (1)
Scopus Crossref
Publication Date
Sun Feb 10 2019
Journal Name
Journal Of The College Of Education For Women
Brain Dominance Learning Styles for Secondary School Students Distinguished and Ordinary
...Show More Authors

The current research aims at detecting Brain Dominance Learning Styles distinguished
and ordinary secondary school students (males and females).The researcher adopted Torrance
measure, known as ‘the style of your learning and thinking to measure Brain Dominance
Learning Styles’, the codified version of Joseph Qitami (1986); picture (a). The researcher
verified the standard properties of tool. The final application sample was 352 distinguished
and ordinary students; 176 distinguished male and female students and 176 ordinary male and
female students at the scientific fifth level of secondary school from schools in the province of
Baghdad, AL- KarKh Education Directorates in the First and Second . and who have been

... Show More
View Publication Preview PDF
Publication Date
Wed Oct 11 2023
Journal Name
Journal Of Educational And Psychological Researches
The Relationship between Formal Thinking & Learning Styles for Kindergarten Department Students
...Show More Authors

The current research aims to reveal the strength of education and the direction of the relationship between the formal thinking and learning methods of Kindergarten department students. To achieve this objective, the researcher developed a scale of formal thinking according to the theory of (Inhelder & Piaget 1958) consisting of (25) items in the form of declarative phrases derived from the analysis of formal thinking skills based on a professional situation that students are expected to interact with in a professional way. The research sample consisted of (100) female students selected randomly who were divided into four groups based on the academic stages, the results revealed that The level of formal thinking of the main sample is

... Show More
View Publication Preview PDF
Publication Date
Tue Dec 05 2023
Journal Name
Baghdad Science Journal
AlexNet-Based Feature Extraction for Cassava Classification: A Machine Learning Approach
...Show More Authors

Cassava, a significant crop in Africa, Asia, and South America, is a staple food for millions. However, classifying cassava species using conventional color, texture, and shape features is inefficient, as cassava leaves exhibit similarities across different types, including toxic and non-toxic varieties. This research aims to overcome the limitations of traditional classification methods by employing deep learning techniques with pre-trained AlexNet as the feature extractor to accurately classify four types of cassava: Gajah, Manggu, Kapok, and Beracun. The dataset was collected from local farms in Lamongan Indonesia. To collect images with agricultural research experts, the dataset consists of 1,400 images, and each type of cassava has

... Show More
View Publication Preview PDF
Scopus (2)
Crossref (3)
Scopus Crossref
Publication Date
Fri May 01 2020
Journal Name
Journal Of Engineering
Shrinkage and Strength Behavior of Highly Plastic Clay Improved by Brick Dust
...Show More Authors

Highly plastic soils exhibit unfavorited properties upon saturation, which produce different defects in engineering structures. Attempts were made by researchers to proffer solutions to these defects by experimenting in practical ways. This included various materials that could possibly improve the soil engineering properties and reduce environmental hazards. This paper investigates the strength behavior of highly plastic clay stabilized with brick dust. The brick dust contents were 10%, 20%, and 30% by dry weight of soil. A series of linear shrinkage and unconfined compression tests were carried out to study the effect of brick dust on the quantitative amount of shrinkage experienced by highly plastic clay and the undra

... Show More
View Publication Preview PDF
Crossref (6)
Crossref
Publication Date
Fri May 01 2020
Journal Name
International Journal Of Advanced Science And Technology
Improved Merging Multi Convolutional Neural Networks Framework of Image Indexing and Retrieval
...Show More Authors

Background/Objectives: The purpose of current research aims to a modified image representation framework for Content-Based Image Retrieval (CBIR) through gray scale input image, Zernike Moments (ZMs) properties, Local Binary Pattern (LBP), Y Color Space, Slantlet Transform (SLT), and Discrete Wavelet Transform (DWT). Methods/Statistical analysis: This study surveyed and analysed three standard datasets WANG V1.0, WANG V2.0, and Caltech 101. The features an image of objects in this sets that belong to 101 classes-with approximately 40-800 images for every category. The suggested infrastructure within the study seeks to present a description and operationalization of the CBIR system through automated attribute extraction system premised on CN

... Show More
Publication Date
Mon Oct 05 2020
Journal Name
International Journal Of Advanced Science And Technology
Improved Merging Multi Convolutional Neural Networks Framework of Image Indexing and Retrieval
...Show More Authors

Improved Merging Multi Convolutional Neural Networks Framework of Image Indexing and Retrieval