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
Wed Jan 01 2020
Journal Name
Advances In Intelligent Systems And Computing
Forecasting by Using the Optimal Time Series Method
...Show More Authors

View Publication
Scopus (20)
Crossref (10)
Scopus Crossref
Publication Date
Sun Jul 09 2023
Journal Name
Journal Of Engineering
Solar Powered Air-Conditioning Using Absorption Refrigeration Technique
...Show More Authors

The present work includes design, construction and operates of a prototype solar absorption refrigeration system, using methanol as a refrigerant to avoid any refrigerant that cause global warming and greenhouse effect. Flat plate collector was used because it’s easy, ninexpensive and efficient. Many test runs (more than 50) were carried out on the system from May to October, 2013; the main results were taken between the period of July 15, 2013 to August 15, 2013 to find the maximum C.O.P, cooling, temperature and pressure of the system. The system demonstrates a maximum generator temperature of 93.5 oC, on July 18, 2013 at 2:30 pm, and the average mean generator temperature Tgavr was 74.7 °C, for this period. The maximum pressure Pg

... Show More
View Publication Preview PDF
Crossref (3)
Crossref
Publication Date
Wed Jan 01 2020
Journal Name
International Journal Of Engineering Business Management
Using ANN in emergency reconstruction projects post disaster
...Show More Authors

The purpose of this study is to avoid delays and cost changes that occur in emergency reconstruction projects especially in post disaster circumstances. This study is aimed to identify the factors that affect the real construction period and the real cost of a project against the estimated period of construction and the estimated cost of the project. The case study is related to the construction projects in Iraq. Thirty projects in different areas of construction in Iraq were selected as a sample for this study. Project participants from the projects authorities provided data about the projects through a data collection distributed survey made by the authors. Mathematical data analysis was used to construct a model to predict change

... Show More
View Publication
Scopus (6)
Crossref (12)
Scopus Clarivate Crossref
Publication Date
Mon Jan 09 2023
Journal Name
2023 15th International Conference On Developments In Esystems Engineering (dese)
Abstract Pattern Image Generation using Generative Adversarial Networks
...Show More Authors

View Publication
Scopus (5)
Crossref (3)
Scopus Crossref
Publication Date
Tue Jan 01 2019
Journal Name
Biochem. Cell. Arch
BIOSYNTHESIS OF SILVER NANOPARTICLES USING MINTS LEAF EXTRACT AND EVALUATION OF THEIR ANTIMICROBIAL ACTIVITY
...Show More Authors

The aim of this study is to synthesize an easy, non-toxic and eco-friendly method. Silver nanoparticles which were synthesized by leaf extract of mint were characterized by UV-Visible Spectroscopy which appears UVVisible spectrum of demonstrated a peak 448 nm corresponding to surface Plasmon resonance of silver nanoparticles, Fourier Transform Infrared Spectroscopy (FTIR); functional groups involved in the silver nanoparticles synthesis were identified, the presence of silver nanoparticles was confirmed by X-ray diffraction (XRD) and Atomic Force Microscope (AFM) analysis clearly illustrated that the shape of silver nanoparticles was spherical and the size of the silver nanoparticles has been measured as 55- 85 nm. Evaluation of its antimic

... Show More
Scopus (3)
Scopus
Publication Date
Sat Jan 01 2022
Journal Name
Journal Of The Mechanical Behavior Of Materials
The effect of using polyolefin fiber on some properties of slurry-infiltrated fibrous concrete
...Show More Authors
Abstract<p>Slurry-infiltrated fibrous concrete (SIFCON) is a special type of concrete that has great strength, as well as high ductility. However, the unit weight is high, which exceeds the unit weight of fiber-reinforced concrete, because of the high fiber content. This research aims to verify the compressive and flexural strength, as well as the density of SIFCON when using two different fibers (steel and polyolefin). Sometimes mono type of fiber steel or polyolefin, sometimes by hybridizing two types of fiber steel + polyplefin. Volume fraction (6% for all species) was used. Hook-end steel fiber and polyolefin fiber are used. With hybridization, a total volume fraction of 6% was used, which </p> ... Show More
View Publication
Crossref (4)
Crossref
Publication Date
Tue Jan 01 2019
Journal Name
Indian Journal Of Public Health Research &amp; Development
Comparison of the Cyclic Fatigue of Protaper Next, 2Shape and Hyflex EDM Using Glyde
...Show More Authors

View Publication Preview PDF
Scopus Crossref
Publication Date
Wed Dec 25 2024
Journal Name
Jurnal Kimia Valensi
Green Synthesis, Characterization, and Applications of Aluminum Oxide Nanoparticles Using Aqueous Extract of Clove
...Show More Authors

In this work, γ-Al2O3NPs were successfully biosynthesized, mediated aluminum nitrate nona hydrate Al(NO3)3.9H2O, sodium hydroxide, and aqueous clove extract in alkali media. The γ-Al2O3NPs were characterized by different techniques like Fourier transform infrared spectroscopy (FT-IR), UV-Vis spectroscopy, X-ray diffraction (XRD), scanning electron microscopy (SEM), energy–dispersive x-ray spectroscopy, transmission electron microscope (TEM), Energy-dispersive X-ray spectroscopy (EDX), and atomic force microscopy (AFM). The final results indicated the γ-Al2O3NPs nanoparticle size, bonds nature, element phase, crystallinity, morphology, surface image, particle analysis – threshold detection, and the topography parameter. The id

... Show More
View Publication Preview PDF
Scopus (3)
Crossref (2)
Scopus Crossref
Publication Date
Tue Nov 09 2021
Journal Name
Journal Of Accounting And Financial Studies ( Jafs )
The role of using blockchain technology in improving the quality of digital financial reports
...Show More Authors

This study aims mainly to identify the role of the use of blockchain technology in improving the quality of digital financial reports, answering questions and testing the hypothesis of the study, the researchers relied on the descriptive analytical approach, and to obtain the necessary data a questionnaire was distributed after evaluation to the study community.

The results of the study have shown that the use of blockchain technology helps to provide a high degree of reliability in digital financial reports published to banks over the Internet, ensure the speed of completion and completion, and maintain the privacy and confidentiality of the information contained in the digital financial reports of banks

... Show More
View Publication Preview PDF
Publication Date
Fri Jun 01 2018
Journal Name
International Journal Of Civil Engineering And Technology (ijciet)
Performance assessment of biological treatment of sequencing batch reactor using artificial neural network technique.
...Show More Authors

Artificial Neural Network (ANN) model's application is widely increased for wastewater treatment plant (WWTP) variables prediction and forecasting which can enable the operators to take appropriate action and maintaining the norms. It is much easier modeling tool for dealing with complex nature WWTP modeling comparing with other traditional mathematical models. ANN technique significance has been considered at present study for the prediction of sequencing batch reactor (SBR) performance based on effluent's (BOD5/COD) ratio after collecting the required historical daily SBR data for two years operation (2015-2016) from Baghdad Mayoralty and Al-Rustamiya WWTP office, Iraq. The prediction was gotten by the application of a feed-forwa

... Show More