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
Tue Jun 30 2015
Journal Name
Iraqi Journal Of Chemical And Petroleum Engineering
Using the Artificial Gas Lift to Increase the Productivity of Noor Oil Field / Mishrif Formation
...Show More Authors

Noor Oil Field is one of Iraqi oil fields located in Missan province / Amarah city. This field is not subjected to licensing rounds, but depends on the national effort of  Missan Oil Company. The first two wells in the field were drilled in seventies and were  not opened to production until 2009. The aim of this study is to study the possibility of using the method of gas lift to increase the productivity of this field . PROSPER software was used to design the continuous  gas lift by using maximum production rate in the design.

   The design was made after comparing  the measured pressure with the calculated pressure, this comparison  show  that the method of Beggs-Brill and Petroleum Exper

... Show More
View Publication Preview PDF
Publication Date
Wed Jul 01 2020
Journal Name
Iop Conference Series: Materials Science And Engineering
Calculating the Vertical Displacement using the Method of Least Squares Adjustment and 3D Objects Fitting
...Show More Authors
Abstract<p>In this research, the Iraqi flagpole at Baghdad University, which is the longest in Baghdad, with a height of 75m, was monitored. According to the importance of this structure, the calculation of the displacement (vertical deviation) in the structure was monitored using the Total Station device, where several observations were taken at different times for two years the monitoring started from November 2016 until May 2017, at a rate of four observations for one year. The observation was processed using the least square method, and the fitting of circles, and then the data was processed. The deviation was calculated using the Matlab program to calculate the values of corrections, where </p> ... Show More
View Publication
Scopus (1)
Crossref (1)
Scopus Crossref
Publication Date
Sat Sep 30 2023
Journal Name
Iraqi Journal Of Chemical And Petroleum Engineering
Removal of Lead Ions from Wastewater by using a Local Adsorbent from Charring Tea Wastes
...Show More Authors

   Adsorption of lead ions from wastewater by native agricultural waste, precisely tea waste. After the activation and carbonization of tea waste, there was a substantial improvement in surface area and other physical characteristics which include density, bulk density, and porosity. FTIR analysis indicates that the functional groups in tea waste adsorbent are aromatic and carboxylic. It can be concluded that the tea waste could be a good sorbent for the removal of Lead ions from wastewater. Different dosages of the adsorbents were used in the batch studies. A random series of experiments indicated a removal degree efficiency of lead reaching (95 %) at 5 ppm optimum concentration, with adsorbents R2 =97.75% for tea. Three mo

... Show More
View Publication Preview PDF
Crossref (1)
Crossref
Publication Date
Mon Dec 16 2024
Journal Name
Light & Engineering
The Design and Experimental Realization of a Laser-Based Heating System Using Recycled Laser Module
...Show More Authors

Laser is a powerful device that has a wide range of applications in fields ranging from materials science and manufacturing to medicine and fibre optic communications. One remarkable

View Publication
Publication Date
Sun Jan 01 2023
Journal Name
Ibero- American Journal Of Exercise And Sports Psychology
THE EFFECT OF SPECIAL EXERCISES USING TWO DESIGNED DEVICES IN DEVELOPING SOME DEFENSIVE HANDBALL SKILLS
...Show More Authors

Scopus (4)
Scopus
Publication Date
Wed Nov 05 2014
Journal Name
International Journal Of Applied Mathematical Research
Approximate solution of a model describing biological species living together using a new iterative method
...Show More Authors

View Publication
Crossref (2)
Crossref
Publication Date
Mon Dec 11 2017
Journal Name
Al-khwarizmi Engineering Journal
ptimization the Parameters of Magnetic Abrasive Process Using Taguchi Method to Improve the Surface Roughness
...Show More Authors

Abstract  

Magnetic abrasive finishing (MAF) process is one of non-traditional or advanced finishing methods which is suitable for different materials and produces high quality level of surface finish where it uses magnetic force as a machining pressure. A set of experimental tests was planned according to Taguchi orthogonal array (OA) L27 (36) with three levels and six input parameters. Experimental estimation and optimization of input parameters for MAF process for stainless steel type 316 plate work piece, six input parameters including amplitude of tooth pole, and number of cycle between teeth, current, cutting speed, working gap, and finishing time, were performed by design of experiment

... Show More
View Publication Preview PDF
Crossref (1)
Crossref
Publication Date
Sun Apr 29 2012
Journal Name
Journal Of Karbala University
Optimization Quantitative Determination of Cimetidine in Pharmaceutical Preparations via Bromothymol Blue Using Central Composite Design
...Show More Authors

Preview PDF
Publication Date
Fri Mar 01 2024
Journal Name
Water, Air, &amp; Soil Pollution
Decontamination of Cobalt-Polluted Soils Using an Enhanced Electro-kinetic Method, Employing Eco-friendly Conditions
...Show More Authors

View Publication
Scopus (1)
Crossref (1)
Scopus Clarivate Crossref
Publication Date
Tue May 01 2018
Journal Name
Sci.int.(lahore)
The Effect of Wavelet Coefficient Reduction on Image Compression Using DWT and Daubechies Wavelet Transform
...Show More Authors

FG Mohammed, HM Al-Dabbas, Science International, 2018 - Cited by 2

View Publication