Preferred Language
Articles
/
OXjVX58BuRolNscL4eKI
DAB-UNET: Dual Attention Block UNET Segmentation for Diabetic Retinopathy Utilizing an Encoder-Decoder Residual
...Show More Authors

—Fundus images play an essential role in ophthalmic diagnostics for the detection of many eye illnesses. The experiment begins with a thorough image preprocessing. technique, which includes clipping the circular borders, scaling the image, enhancing the contrast, removing noise, and augmenting the data. The new combined block applies to extracting distinctive deep feature representations, which help to detect the first shape of the edges of each lesion. It is namely the Attention Block and the Conv-Deconv UNET model. The attention block is subsequently implemented in order to augment the robustness and quality of feature depictions derived from a pair of DR images. The Dual Attention Block for the backbone, which is supplemented with hierarchical Bottleneck attention is what we propose here, referred to as Dual Attention Block UNET (DAB-UNET). Bottleneck Attention Blocks and Dual Attention Blocks greatly improve a model’s ability to concentrate on essential features, boosting its performance in complex tasks such as image segmentation. When these attention mechanisms are built into architectures like DAB-UNET, they make the network faster and more accurate, letting it pick up on small, specific details. This is particularly beneficial in areas like medical imaging, where high precision is essential. In order to emphasize retinal anomalies that are significant for the fovea. macula and Diabetic Retinopathy (DR) semantic segmentation in the deteriorated retina, the network is made up of a unique bottleneck attention block. We trained Mask Region-based Convolutional Neural Network (RCNN) model that comprises of a backbone for eliminating Oculus Dexter (OD) regions. Moreover, the proposed block combines self attention with channel attention in order to highlight these abnormalities. Our results indicate that DAB-UNET is potentially very effective for identifying landmarks even when dealing with different types of retinal degenerative disorders.

Scopus Crossref
View Publication Preview PDF
Quick Preview PDF
Publication Date
Wed Dec 13 2017
Journal Name
Al-khwarizmi Engineering Journal
Large Eddy Simulation in Duct Flow
...Show More Authors

In this paper, the problem of developing turbulent flow in rectangular duct is investigated by obtaining numerical results of the velocity profiles in duct by using large eddy simulation model in two dimensions with different Reynolds numbers, filter equations and mesh sizes. Reynolds numbers range from (11,000) to (110,000) for velocities (1 m/sec) to (50 m/sec) with (56×56), (76×76) and (96×96) mesh sizes with different filter equations. The numerical results of the large eddy simulation model are compared with k-ε model and analytic velocity distribution and validated with experimental data of other researcher. The large eddy simulation model has a good agreement with experimental data for high Reynolds number with the first, seco

... Show More
View Publication Preview PDF
Publication Date
Wed Jan 01 2025
Journal Name
Kuwait Journal Of Science
Detection of the most frequent sources of dust storms in Iraq during 2020–2023 using space tools
...Show More Authors

Dust storms are typical in arid and semi-arid regions such as the Middle East; the frequency and severity of dust storms have grown dramatically in Iraq in recent years. This paper identifies the dust storm sources in Iraq using remotely sensed data from Meteosat-spinning enhanced visible and infrared imager (SEVIRI) bands. Extracted combined satellite images and simulated frontal dust storm trajectories, using the Hybrid Single Particle Lagrangian Integrated Trajectory (HYSPLIT) model, are used to identify the most influential sources in the Middle East and Iraq. Out of 132 dust storms in Iraq during 2020–2023, the most frequent occurred in the spring and summer. A dust source frequency percentage map (DSFPM) is generated using ArcGIS so

... Show More
View Publication Preview PDF
Scopus (6)
Crossref (7)
Scopus Clarivate Crossref
Publication Date
Sat Dec 30 2023
Journal Name
Iraqi Journal Of Chemical And Petroleum Engineering
Ibuprofen Degradation from Synthetic Wastewater Using Photo-Fenton Process
...Show More Authors

   The removal of Ibuprofen antibiotics (IBU) by photo-degradation UV/H2O2/Fe+2 system was investigated in a batch reactor under different initial concentrations of H2O2 (100-500) mg/L, Fe+2 (10-40) mg/L, pH (3-9) and initial concentrations of IBU (10-80) mg/L, and their relationship with the degradation efficiency were studied. The result demonstrated that the maximum elimination of IBU was 85.54% achieved at 300 mg/L of H2O2, 30 mg/L of Fe+2, pH=3, and irradiation time of 150 min, for 10 mg/L of IBU. The results have shown that the oxidation reagent H2O2 plays a very important role in IBU degradation.

View Publication Preview PDF
Crossref (9)
Crossref
Publication Date
Tue Jun 30 2020
Journal Name
Iraqi Journal Of Chemical And Petroleum Engineering
Studying the Rheological Properties of Non-Newtonian Fluids under the Effect of temperature Using Different Chemical Additives
...Show More Authors

   This research studies the rheological properties ( plastic viscosity, yield point and apparent viscosity) of Non-Newtonian fluids under the effect of temperature using different chemical additives, such as (xanthan gum (xc-polymer), carboxyl methyl cellulose ( High and low viscosity ) ,polyacrylamide, polyvinyl alcohol, starch, Quebracho and Chrome Lignosulfonate). The samples were prepared by mixing 22.5g of bentonite with 350 ml of water and adding the additives in four different concentrations (3, 6, 9, 13) g by using Hamilton Beach mixer. The rheological properties of prepared samples were measured by using Fan viscometer model 8-speeds. All the samples were subjected to Bingham plastic model. The temperature range studi

... Show More
View Publication Preview PDF
Crossref (1)
Crossref
Publication Date
Sun Dec 03 2017
Journal Name
Baghdad Science Journal
Network Self-Fault Management Based on Multi-Intelligent Agents and Windows Management Instrumentation (WMI)
...Show More Authors

This paper proposed a new method for network self-fault management (NSFM) based on two technologies: intelligent agent to automate fault management tasks, and Windows Management Instrumentations (WMI) to identify the fault faster when resources are independent (different type of devices). The proposed network self-fault management reduced the load of network traffic by reducing the request and response between the server and client, which achieves less downtime for each node in state of fault occurring in the client. The performance of the proposed system is measured by three measures: efficiency, availability, and reliability. A high efficiency average is obtained depending on the faults occurred in the system which reaches to

... Show More
View Publication Preview PDF
Scopus Crossref
Publication Date
Tue Mar 01 2016
Journal Name
International Journal Of Engineering Research And Advanced Technology (ijerat)
Speeding Up Back-Propagation Learning (SUBPL) Algorithm: A New Modified Back_Propagation Algorithm
...Show More Authors

The convergence speed is the most important feature of Back-Propagation (BP) algorithm. A lot of improvements were proposed to this algorithm since its presentation, in order to speed up the convergence phase. In this paper, a new modified BP algorithm called Speeding up Back-Propagation Learning (SUBPL) algorithm is proposed and compared to the standard BP. Different data sets were implemented and experimented to verify the improvement in SUBPL.

View Publication
Publication Date
Tue May 16 2023
Journal Name
Journal Of Engineering
Parallel Routing in Wireless Sensor Network
...Show More Authors

The limitations of wireless sensor nodes are power, computational capabilities, and memory. This paper suggests a method to reduce the power consumption by a sensor node. This work is based on the analogy of the routing problem to distribute an electrical field in a physical media with a given density of charges. From this analogy a set of partial differential equations (Poisson's equation) is obtained. A finite difference method is utilized to solve this set numerically. Then a parallel implementation is presented. The parallel implementation is based on domain decomposition, where the original calculation domain is decomposed into several blocks, each of which given to a processing element. All nodes then execute computations in parall

... Show More
View Publication Preview PDF
Crossref
Publication Date
Sat Oct 01 2022
Journal Name
Baghdad Science Journal
Human Face Recognition Based on Local Ternary Pattern and Singular Value Decomposition
...Show More Authors

There is various human biometrics used nowadays, one of the most important of these biometrics is the face. Many techniques have been suggested for face recognition, but they still face a variety of challenges for recognizing faces in images captured in the uncontrolled environment, and for real-life applications. Some of these challenges are pose variation, occlusion, facial expression, illumination, bad lighting, and image quality. New techniques are updating continuously. In this paper, the singular value decomposition is used to extract the features matrix for face recognition and classification. The input color image is converted into a grayscale image and then transformed into a local ternary pattern before splitting the image into

... Show More
View Publication Preview PDF
Scopus (6)
Crossref (1)
Scopus Clarivate Crossref
Publication Date
Thu Dec 01 2022
Journal Name
Baghdad Science Journal
Diagnosing COVID-19 Infection in Chest X-Ray Images Using Neural Network
...Show More Authors

With its rapid spread, the coronavirus infection shocked the world and had a huge effect on billions of peoples' lives. The problem is to find a safe method to diagnose the infections with fewer casualties. It has been shown that X-Ray images are an important method for the identification, quantification, and monitoring of diseases. Deep learning algorithms can be utilized to help analyze potentially huge numbers of X-Ray examinations. This research conducted a retrospective multi-test analysis system to detect suspicious COVID-19 performance, and use of chest X-Ray features to assess the progress of the illness in each patient, resulting in a "corona score." where the results were satisfactory compared to the benchmarked techniques.  T

... Show More
View Publication Preview PDF
Scopus (8)
Crossref (2)
Scopus Clarivate Crossref
Publication Date
Tue Oct 30 2018
Journal Name
Journal Of Engineering
Accuracy Assessment of Stonex X-300 Laser Scanner Cameras
...Show More Authors

Assessment the actual accuracy of laboratory devices prior to first use is very important to know the capabilities of such devices and employ them in multiple domains. As the manual of the device provides information and values in laboratory conditions for the accuracy of these devices, thus the actual evaluation process is necessary.

In this paper, the accuracy of laser scanner (stonex X-300) cameras were evaluated, so that those cameras attached to the device and lead supporting role in it. This is particularly because the device manual did not contain sufficient information about those cameras.

To know the accuracy when using these cameras in close range photogrammetry, laser scanning (stonex X-300) de

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