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 Aug 01 2024
Journal Name
Advances In Science And Technology Research Journal
Power Predicting for Power Take-Off Shaft of a Disc Maize Silage Harvester Using Machine Learning
...Show More Authors

View Publication
Scopus (3)
Crossref (1)
Scopus Clarivate Crossref
Publication Date
Thu Dec 01 2022
Journal Name
Iaes International Journal Of Artificial Intelligence
Reduced hardware requirements of deep neural network for breast cancer diagnosis
...Show More Authors

Identifying breast cancer utilizing artificial intelligence technologies is valuable and has a great influence on the early detection of diseases. It also can save humanity by giving them a better chance to be treated in the earlier stages of cancer. During the last decade, deep neural networks (DNN) and machine learning (ML) systems have been widely used by almost every segment in medical centers due to their accurate identification and recognition of diseases, especially when trained using many datasets/samples. in this paper, a proposed two hidden layers DNN with a reduction in the number of additions and multiplications in each neuron. The number of bits and binary points of inputs and weights can be changed using the mask configuration

... Show More
View Publication Preview PDF
Scopus (5)
Crossref (1)
Scopus Crossref
Publication Date
Mon Apr 17 2017
Journal Name
Wireless Personal Communications
ITPMAP: An Improved Three-Pass Mutual Authentication Protocol for Secure RFID Systems
...Show More Authors

View Publication
Scopus (9)
Crossref (5)
Scopus Clarivate Crossref
Publication Date
Sun Sep 01 2013
Journal Name
2013 Ieee International Conference On Circuits And Systems (iccas)
Improved undetected error probability model for JTEC and JTEC-SQED coding schemes
...Show More Authors

The undetected error probability is an important measure to assess the communication reliability provided by any error coding scheme. Two error coding schemes namely, Joint crosstalk avoidance and Triple Error Correction (JTEC) and JTEC with Simultaneous Quadruple Error Detection (JTEC-SQED), provide both crosstalk reduction and multi-bit error correction/detection features. The available undetected error probability model yields an upper bound value which does not give accurate estimation on the reliability provided. This paper presents an improved mathematical model to estimate the undetected error probability of these two joint coding schemes. According to the decoding algorithm the errors are classified into patterns and their decoding

... Show More
View Publication
Scopus (1)
Crossref (1)
Scopus Crossref
Publication Date
Sun May 22 2022
Journal Name
International Journal Of Early Childhood Special Education
The impact of using learning acceleration model on the achievement of mathematics for third intermediate grade students
...Show More Authors

The current study aims at identifying the impact of using learning acceleration model on the achievement of mathematics for third intermediategrade students. Forachieving this, the researchers chose the School (Al-Kholood Secondary School for Girls) affiliated to the General Directorate of Babylon Education / Hashemite Education Department for the academic year (2021/2021), The sample reached to (70) female students from the third intermediate grade, with (35) female students for each of the two research groups. The two researchers prepared an achievement test consisting of (25) objective items of multiple choice type, The psychometric properties of the test were confirmed, and after the completion of the experiment, the achievement test wa

... Show More
Publication Date
Sun Sep 03 2023
Journal Name
Wireless Personal Communications
Application of Healthcare Management Technologies for COVID-19 Pandemic Using Internet of Things and Machine Learning Algorithms
...Show More Authors

View Publication
Scopus (4)
Crossref (3)
Scopus Clarivate Crossref
Publication Date
Tue Apr 30 2024
Journal Name
Iraqi Journal Of Science
Crescent Moon Visibility: A New Criterion using Deep learned Artificial Neural-Network
...Show More Authors

     Many authors investigated the problem of the early visibility of the new crescent moon after the conjunction and proposed many criteria addressing this issue in the literature. This article presented a proposed criterion for early crescent moon sighting based on a deep-learned pattern recognizer artificial neural network (ANN) performance. Moon sight datasets were collected from various sources and used to learn the ANN. The new criterion relied on the crescent width and the arc of vision from the edge of the crescent bright limb. The result of that criterion was a control value indicating the moon's visibility condition, which separated the datasets into four regions: invisible, telescope only, probably visible, and certai

... Show More
Preview PDF
Scopus Crossref
Publication Date
Mon Mar 01 2021
Journal Name
Iop Conference Series: Materials Science And Engineering
Investigating the effect of cartographic properties on updating cadastral maps
...Show More Authors
Abstract<p>Cadastral maps are the main documents of ownership and plots of land, as it contribute to preserving the property rights of individuals and institutions. It indicates the size and shape of each parcel and reveals geographic relationships that affect property value. The Iraqi cadastral maps are in old coordinate system AL-nahrwan 1934 and lambert conformal conic projection. Therefore these maps are old and unfit for use. The main objective of this paper is to investigate the effect of cartographic properties on updating cadastral maps. This depends on studying the effect of conversion the projection and the datum of the cadastral maps of the study area from (datum: nahrwan34, projection: lambert confo</p> ... Show More
View Publication
Crossref
Publication Date
Fri Apr 01 2016
Journal Name
Journal Of Engineering
Numerical Study of Heat Transfer Enhancement in Heat Exchanger Using AL2O3 Nanofluids
...Show More Authors

In this study, the flow and heat transfer characteristics of Al2O3-water nanofluids for a range of the Reynolds number of 3000, 4500, 6000 and 7500 with a range of volume concentration of 1%, 2%, 3% and 4% are studied numerically. The test rig consists of cold liquid loop, hot liquid loop and the test section which is counter flow double pipe heat exchanger with 1m length. The inner tube is made of smooth copper with diameter of 15mm. The outer tube is made of smooth copper with diameter of 50mm. The hot liquid flows through the outer tube and the cold liquid (or nanofluid) flow through the inner tube. The boundary condition of this study is thermally insulated the outer wall with uniform velocity a

... Show More
View Publication Preview PDF
Publication Date
Mon Jan 01 2018
Journal Name
Proceedings Of The 10th International Joint Conference On Computational Intelligence
Deep Classifier Structures with Autoencoder for Higher-level Feature Extraction
...Show More Authors

View Publication
Crossref (2)
Scopus Crossref