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
Sat Jan 01 2022
Journal Name
Technologies And Materials For Renewable Energy, Environment And Sustainability: Tmrees21gr
Theoretical investigation of charge transfer at N3 sensitized molecule dye contact with TiO2 and ZnO semiconductor
...Show More Authors

We present a simple model of charge transfer current through sensitizer N3 molecule contact to TiO2 and ZnO semiconductors to calculate the charge transfer current. The model underlying depends on the fundamental parameters of the charge transfer reaction and it is based on the quantum transition theory approach. A transition energy, driving energy and potential barrier have been taken into account charge transfer current at N3 / TiO2 and N3 / ZnO devices with wide polarity solvents Acetic acid, 2-Methoxyethanol, 1-Butanol, Methyl alcohol, chloroform, N,N-Dimethylacetamide and Ethyl alcohol via the quantum donor-acceptor system.The effects of the transition energy and potential barrier are computed and discussion on charge transfer current.

... Show More
View Publication Preview PDF
Scopus Crossref
Publication Date
Tue Aug 31 2021
Journal Name
Iraqi Journal Of Science
Heat Transfer Analysis and Magnetohydrodynamics Effect on Peristaltic Transport of Ree–Eyring Fluid in Rotating Frame
...Show More Authors

This paper discusses Ree–Eyring fluid’s peristaltic transport in a rotating frame and examines the impacts of Magnetohydrodynamics (MHD). The results deal with  systematically (analytically) applying each of the governing equations of Ree–Eyring fluid, the axial and secondary velocities, flow rate due to auxiliary stream, and bolus. The effects of some distinctive variables, such as Hartman number, heat source/sink, and amplitude ratio, are taken under consideration and illustrated through graphs.

View Publication Preview PDF
Scopus (6)
Scopus Crossref
Publication Date
Fri Nov 24 2023
Journal Name
Iraqi Journal Of Science
Effect of Magnetichydrodynamic on unsteady flow and heat transfer upon stretching sheet with non – uniform heat
...Show More Authors

In this paper we study the effect of magnetichydrodynamic upon the boundary
layer flow and heat transfer on a permeable unsteady stretching sheet with non –
uniform heat source / sink. It found that the momentum and energy equations are
controlled by many different dimensionless parameters such as prandtle number
pr , unsteadiness parameter A , constant pressure So , coefficient of the space
dependent  A , the temperature dependent  B , and the MHD parameter M . The
analytic solutions are obtained by using suitable similarity transformations and
homotopy analysis method (HAM).
Furthermore, we analysis the effects of all dimensionless number, there are
mentioned above, upon the velocity distribution and

... Show More
View Publication
Publication Date
Thu Feb 28 2019
Journal Name
Journal Of Accounting And Financial Studies ( Jafs )
Evaluation of the Construction, Build, Operate and Transfer (B.O.T): Applied Research in Southern Cement State Company
...Show More Authors

   Form of investment in infrastructure important factor to drive economic growth in any country, with the dwindling ability of governments to provide the necessary funds for such investments, emerged as a rising trend for private sector involvement in public projects and infrastructure, and one of these trends is the build-operate-transfer system (BOT), which commonly used in various developed and developing countries as one of the tools used in the implementation of these investments, as the private sector under this system design, finance, build and operate the project, and are re-administration of the state after a certain period under a contractual agreement between the parties of the contract. As this system provides majo

... Show More
View Publication Preview PDF
Crossref
Publication Date
Wed Feb 15 2023
Journal Name
International Journal Of Emerging Technologies In Learning (ijet)
Instructional Design According to the Repulsive Learning Model and its Impact on the Achievement of Chemistry and Lateral Thinking for Third-Grade Intermediate Students
...Show More Authors

Identify the effect of an educational design according to the repulsive (allosteric) learning model on the achievement of chemistry and lateral thinking. The sample consisted of (59) students from third-grade intermediate students. They were randomly distributed into two groups (experimental and control), and the equivalence was done in (chronological age, previous achievement in chemistry, intelligence, lateral thinking). The (30) students from experimental group were taught according to the instructional design, other 29 students from the (control) group were taught according to the usual method. Two tests done, one of them is an achievement test consisted of (30) items of the type of multiple choice, the other was a lateral think

... Show More
View Publication
Scopus (1)
Scopus Crossref
Publication Date
Sat Feb 08 2025
Journal Name
Iraqi Journal Of Science
Intrusion Detection Approach Based on DNA Signature
...Show More Authors

View Publication
Publication Date
Thu Jul 01 2021
Journal Name
Iraqi Journal Of Science
Vehicles Detection System at Different Weather Conditions
...Show More Authors

The importance of efficient vehicle detection (VD) is increased with the expansion of road networks and the number of vehicles in the Intelligent Transportation Systems (ITS). This paper proposes a system for detecting vehicles at different weather conditions such as sunny, rainy, cloudy and foggy days. The first step to the proposed system implementation is to determine whether the video’s weather condition is normal or abnormal. The Random Forest (RF) weather condition classification was performed in the video while the features were extracted for the first two frames by using the Gray Level Co-occurrence Matrix (GLCM). In this system, the background subtraction was applied by the mixture of Gaussian 2 (MOG 2) then applying a number

... Show More
View Publication Preview PDF
Scopus (7)
Crossref (4)
Scopus Crossref
Publication Date
Tue Aug 23 2022
Journal Name
Int. J. Nonlinear Anal. Appl.
Face mask detection based on algorithm YOLOv5s
...Show More Authors

Determining the face of wearing a mask from not wearing a mask from visual data such as video and still, images have been a fascinating research topic in recent decades due to the spread of the Corona pandemic, which has changed the features of the entire world and forced people to wear a mask as a way to prevent the pandemic that has calmed the entire world, and it has played an important role. Intelligent development based on artificial intelligence and computers has a very important role in the issue of safety from the pandemic, as the Topic of face recognition and identifying people who wear the mask or not in the introduction and deep education was the most prominent in this topic. Using deep learning techniques and the YOLO (”You on

... Show More
Publication Date
Wed Sep 22 2021
Journal Name
Samarra Journal Of Pure And Applied Science
Toward Constructing a Balanced Intrusion Detection Dataset
...Show More Authors

Several Intrusion Detection Systems (IDS) have been proposed in the current decade. Most datasets which associate with intrusion detection dataset suffer from an imbalance class problem. This problem limits the performance of classifier for minority classes. This paper has presented a novel class imbalance processing technology for large scale multiclass dataset, referred to as BMCD. Our algorithm is based on adapting the Synthetic Minority Over-Sampling Technique (SMOTE) with multiclass dataset to improve the detection rate of minority classes while ensuring efficiency. In this work we have been combined five individual CICIDS2017 dataset to create one multiclass dataset which contains several types of attacks. To prove the eff

... Show More
View Publication
Crossref (6)
Crossref
Publication Date
Fri Dec 08 2023
Journal Name
Iraqi Journal Of Science
Intrusion Detection Approach Based on DNA Signature
...Show More Authors

Intrusion-detection systems (IDSs) aim at detecting attacks against computer systems and networks or, in general, against information systems. Most of the diseases in human body are discovered through Deoxyribonucleic Acid (DNA) investigations. In this paper, the DNA sequence is utilized for intrusion detection by proposing an approach to detect attacks in network. The proposed approach is a misuse intrusion detection that consists of three stages. First, a DNA sequence for a network traffic taken from Knowledge Discovery and Data mining (KDD Cup 99) is generated. Then, Teiresias algorithm, which is used to detect sequences in human DNA and assist researchers in decoding the human genome, is used to discover the Shortest Tandem Repeat (S

... Show More
View Publication Preview PDF