Preferred Language
Articles
/
ijs-6463
Paradigm Shift Towards Federated Learning for COVID-19 Detection: A Survey
...Show More Authors

     The novel coronavirus 2019 (COVID-19) is a respiratory syndrome with similar traits to common pneumonia. This major pandemic has affected nations both socially and economically, disturbing everyday life and urging the scientific community to develop solutions for the diagnosis and prevention of COVID-19. Reverse transcriptase-polymerase chain reaction (RT–PCR) is the conventional approach used for detecting COVID-19. Nevertheless, the initial stage of the infection is less predictable in PCR tests, making early prediction challenging. A robust and alternative diagnostic method based on digital computerised technologies to support conventional methods would greatly help society. Therefore, this paper reviews recent research based on using machine and federated learning techniques on publicly available datasets comprising Computed Tomography (CT) images, Chest X-ray (CXR) and ultrasound of COVID-19 patients. This paper also analyses the analytical efficiency such as accuracy, sensitivity, specificity and F1-score of models to determine the efficacy. Based on our study, we observed that Machine Learning (ML) was proposed widely in COVID-19 prediction and diagnosis methods. But this method has challenges due to less dataset availability and privacy concerns. However, federated learning-based COVID-19 detection overcame the challenge and provided better efficacy with low datasets and supported medical data privacy. Thus, based on the advantage observed, federated learning-based COVID-19 detection systems should be developed in the future.

Scopus Crossref
View Publication Preview PDF
Quick Preview PDF
Publication Date
Tue Dec 15 2020
Journal Name
Aip Conference Proceedings
The water bodies in the Southern East of Iraq before and after 2018
...Show More Authors

This study is concerned with the recent changes that occurred in the last three years (2017-2019) in the marshes region in southern Iraq as a result of the changes in the global climate, the study included all the water bodies in the five governorates that are located in the southern regions of Iraq (Wasit, Maysan, Dhi-Qar, Qadisiyah and Basrah), which represent the marshes lands in Iraq. Scenes of the Landsat 8 satellite are used to create a mosaic to cover the five governorates within a time window with the slightest difference between the date of the scene capture, not to exceed 8 days. The results of calculating the changes in water areas were obtained using the classifier support vector machine, where high accuracy ratios were recorded

... Show More
View Publication Preview PDF
Scopus (2)
Crossref (1)
Scopus Clarivate Crossref
Publication Date
Tue Feb 28 2023
Journal Name
Iraqi Journal Of Science
Comparison of Performance Metrics Level of Restricted Boltzmann Machine and Backpropagation Algorithms in Detecting Diabetes Mellitus Disease
...Show More Authors

Diabetes is a disease caused by high sugar levels. Currently, diabetes is one of the most common diseases in the number of people with diabetes worldwide. The increase in diabetes is caused by the delay in establishing the diagnosis of the disease. Therefore, an initial action is needed as a solution that requires the most appropriate and accurate data mining to manage diabetes mellitus. The algorithms used are artificial neural network algorithms, namely Restricted Boltzmann Machine and Backpropagation. This research aims to compare the two algorithms to find which algorithm can produce high accuracy, and determine which algorithm is more accurate in detecting diabetes mellitus. Several stages were involved in this research, including d

... Show More
View Publication Preview PDF
Scopus (1)
Scopus Crossref
Publication Date
Wed Apr 05 2023
Journal Name
Journal Of Engineering
The Behavior of Gypseous Soil under Vertical Vibration Loading
...Show More Authors

The dynamic response of foundation rest on collapsible soil in dry and soaked states is studied through wide experimental programmed. Gypseous soil from Tikrit governorate area was obtained and subjected to various physical and chemical analysis to determine its properties. Steel rectangular footing (400x200x20) mm is manufactured. The machine is fitted to the footing, then the model machine foundation is placed centrally over the prepared soil layer in steel container (1200x 1000x1000)mm with proper care to maintain the center of gravity of whole system lie in the same vertical line with container.Then, the footing is subjected to vertical harmonic loading using a rotating mass type mechanical oscillator to simulate different dynamic lo

... Show More
View Publication Preview PDF
Crossref (2)
Crossref
Publication Date
Fri Sep 16 2016
Journal Name
Journal Of Earthquake Engineering
Dynamic Response of Saturated Soil - Foundation System Acted upon by Vibration
...Show More Authors

In this study, the response and behavior of machine foundations resting on dry and saturated sand was investigated experimentally. In order to investigate the response of soil and footing to steady state dynamic loading, a physical model was manufactured to simulate steady state harmonic load at different operating frequencies. Total of 84 physical models were performed. The footing parameters are related to the size of the rectangular footing and depth of embedment. Two sizes of rectangular steel model footing were tested at the surface and at 50 mm depth below model surface. Meanwhile the investigated parameters of the soil condition include dry and saturated sand for two relative densities 30% and 80%. The response of the footing was ela

... Show More
View Publication
Crossref (25)
Crossref
Publication Date
Sat Jun 03 2023
Journal Name
Iraqi Journal Of Science
Face Recognition Using Stationary wavelet transform and Neural Network with Support Vector Machine
...Show More Authors

Face recognition is a type of biometric software application that can identify a specific
individual in a digital image by analyzing and comparing patterns. It is the process of
identifying an individual using their facial features and expressions.
In this paper we proposed a face recognition system using Stationary Wavelet Transform
(SWT) with Neural Network, the SWT are applied into five levels for feature facial
extraction with probabilistic Neural Network (PNN) , the system produced good results
and then we improved the system by using two manner in Neural Network (PNN) and
Support Vector Machine(SVM) so we find that the system performance is more better
after using SVM where the result shows the performance o

... Show More
View Publication Preview PDF
Publication Date
Tue Jan 02 2007
Journal Name
Journal Of The Faculty Of Medicine Baghdad
The Role Of Tumor Markers In The Diagnosis And Follow Up In Patients With Pancreatic Cancer
...Show More Authors

Background: To shade a light on certain tumor markers and their sensitivity and specificity in determination of pancreatic cancer.
Patients & Methods :- A total of 35 patients with pancreatic cancer were studied between June 2003 and April 2004 in Specialized Surgical - Baghdad Teaching Hospital . These patients were compared with other 25 non malignant G.I diseases patients as well as 35 healthy controls . The serum was estimated for CAI 9-9 , and CEA by ELFA (Enzyme Linked Fluorescent Assay) method and CPR by ELISA method.
Results :- Five patients with pancreatic cancer were excluded from this study because they were beyond surgery.The results show that there is significant differences between se

... Show More
View Publication Preview PDF
Crossref
Publication Date
Sun Oct 30 2022
Journal Name
Iraqi Journal Of Science
Power-Efficient Virtual Machine Placement in Cloud Datacenters using Heuristic Assisted Enhanced Discrete Particle Swarm Optimization
...Show More Authors

    The increase in cloud computing services and the large-scale construction of data centers led to excessive power consumption. Datacenters contain a large number of servers where the major power consumption takes place. An efficient virtual machine placement algorithm is substantial to attain energy consumption minimization and improve resource utilization through reducing the number of operating servers. In this paper, an enhanced discrete particle swarm optimization (EDPSO) is proposed. The enhancement of the discrete PSO algorithm is achieved through modifying the velocity update equation to bound the resultant particles and ensuring feasibility. Furthermore, EDPSO is assisted by two heuristic algorithms random first fit (RFF) a

... Show More
View Publication
Crossref
Publication Date
Sat Jan 02 2021
Journal Name
Journal Of The College Of Languages (jcl)
The problems of Google Translate: Los servicios de la traducción automática de Google y sus problemas
...Show More Authors

There are numbers of automatic translation services that internet users can choose to automatically translate a certain text, and Google translate is one of these automatic services that proposes over 51 Languages. The present paper sheds light on the nature of the translation process offered by Google, and analyze the most prominent problems faced when Google translate is used. Direct translation is common with Google Translate and often results in nonsensical literal translations, particularly with long compound sentences. This is due to the fact that Google translation system uses a method based on language pair frequency that does not take into account grammatical rules which, in turn, affects the quality of the translation. The

... Show More
View Publication Preview PDF
Crossref
Publication Date
Fri Dec 01 2017
Journal Name
Ocean Engineering
Stresses and pore water pressure induced by machine foundation on saturated sand
...Show More Authors

In this study, the response and behavior of machine foundations resting on dry and saturated sand was investigated experimentally. In order to investigate the response of soil and footing to steady state dynamic loading, a physical model was manufactured. The manufactured physical model could be used to simulate steady state harmonic load at different operating frequencies. Total of (84) physical models were performed. The parameters that were taken into considerations include loading frequency, size of footing and different soil conditions. The footing parameters were related to the size of the rectangular footing and depth of embedment. Two sizes of rectangular steel model footing were used (100 200 12.5 mm) and (200 400 5.0 mm).

... Show More
View Publication
Crossref (20)
Crossref
Publication Date
Mon Mar 11 2019
Journal Name
Al-khwarizmi Engineering Journal
An Investigation Study of Tool Geometry in Single Point Incremental Forming (SPIF) and their effect on Residual Stresses Using ANOVA Model
...Show More Authors

Incremental forming is a flexible sheet metal forming process which is performed by utilizing simple tools to locally deform a sheet of metal along a predefined tool path without using of dies. This work presents the single point incremental forming process for producing pyramid geometry and studies the effect of tool geometry, tool diameter, and spindle speed on the residual stresses. The residual stresses were measured by ORIONRKS 6000 test measuring instrument. This instrument was used with four angles of (0º,15º,30º, and 45º) and the average value of residual stresses was determined, the value of the residual stress in the original blanks was (10.626 MPa). The X-ray diffraction technology was used to measure the residual stresses

... Show More
View Publication Preview PDF
Crossref (1)
Crossref