Preferred Language
Articles
/
9OaanZ4BmraWrQ4dIWM9
Comparison of Deep Neural Network Models (LSTM, Bi-LSTM, GRU and Bi-GRU) for Gold Price Prediction
...Show More Authors

This research studies the comparison of deep neural network models and performance evaluation to predict the gold prices of time series, where the gold prices contain high fluctuations and non-linear patterns that are difficult to capture using traditional models, which makes predicting them a significant challenge. Therefore, the focus was on using deep learning models represented by (LSTM), (Bi-LSTM), (GRU) and (Bi-GRU). The results showed the superiority of the (Bi-GRU) model according to comparison criteria (MSE), (RMSE), (MAE), and (R∧2) compared to other models because it was able to understand the time patterns better by processing the data in both directions and provided superior performance, which indicates its effectiveness, efficiency and reliability in predicting time series.

Scopus Crossref
View Publication
Publication Date
Fri Jun 01 2018
Journal Name
Journal Of Engineering
Determination of Best Location for Elevated Tank in Branched Network
...Show More Authors

The research focuses on determination of best location of high elevated tank using the required head of pump as a measure for this purpose. Five types of network were used to find the effect of the variation in the discharge and the node elevation on the best location. The most weakness point was determined for each network. Preliminary tank locations were chosen for test along the primary pipe with same interval distance. For each location, the water elevation in tank and pump head was calculated at each hour depending on the pump head that required to achieve the minimum pressure at the most weakness point. Then, the sum of pump heads through the day was determined. The results proved that there is a most economical lo

... Show More
View Publication Preview PDF
Crossref (1)
Crossref
Publication Date
Wed Dec 01 2010
Journal Name
Al-khwarizmi Engineering Journal
Prediction of Equilibrium Mixing Index and Optimum Mixing Time for Three solid materials in Fluidized Column
...Show More Authors

     Equilibrium and rate of mixing of free flowing solid materials are found using gas fluidized bed. The solid materials were sand (size 0.7 mm), sugar (size0.7 mm) and 15% cast iron used as a tracer. The fluidizing gas was air with velocity ranged from 0.45-0.65 m/s while the mixing time was up to 10 minutes. The mixing index for each experiment was calculated by averaging the results of 10 samples taken from different radial and axial positions in fluidized QVF column 150 mm ID and 900 mm height.

     The experimental results were used in solving a mathematical model of mixing rate and mixing index at an equilibrium proposed by Rose. The results show that mixing index increases with inc

... Show More
View Publication Preview PDF
Publication Date
Wed Jun 28 2017
Journal Name
Iraqi Journal Of Science
Antibacterial Activity of Synergistic Effect of Colicin and Gold Nanoparticles Against Pseudomonas Aerugensa
...Show More Authors

View Publication
Crossref
Publication Date
Thu Oct 08 2026
Journal Name
International Journal Of Robotics And Control Systems
Integrating Multimodal Emotion Recognition with Deep Q-Learning for Adaptive Social Robot Interaction
...Show More Authors

View Publication
Scopus (34)
Scopus
Publication Date
Wed Jun 16 2021
Journal Name
Cognitive Computation
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 b</p> ... Show More
View Publication
Scopus (54)
Crossref (41)
Scopus Clarivate Crossref
Publication Date
Wed May 10 2023
Journal Name
Diagnostics
A Deep Feature Fusion of Improved Suspected Keratoconus Detection with Deep Learning
...Show More Authors

Detection of early clinical keratoconus (KCN) is a challenging task, even for expert clinicians. In this study, we propose a deep learning (DL) model to address this challenge. We first used Xception and InceptionResNetV2 DL architectures to extract features from three different corneal maps collected from 1371 eyes examined in an eye clinic in Egypt. We then fused features using Xception and InceptionResNetV2 to detect subclinical forms of KCN more accurately and robustly. We obtained an area under the receiver operating characteristic curves (AUC) of 0.99 and an accuracy range of 97–100% to distinguish normal eyes from eyes with subclinical and established KCN. We further validated the model based on an independent dataset with

... Show More
View Publication
Scopus (41)
Crossref (38)
Scopus Clarivate Crossref
Publication Date
Wed Jul 01 2020
Journal Name
International Journal Of Drug Delivery Technology
Gold nanoparticle: Synthesis, functionalization, enhancement, drug delivery and therapy: A review
...Show More Authors

Scopus (26)
Scopus
Publication Date
Sun Feb 03 2019
Journal Name
Iraqi Journal Of Physics
Effect of laser energy and pulses on size and concentration of gold nanoparticles in DDDW by LALP method
...Show More Authors

The size and the concentration of the gold nanoparticles (GNPs)
synthesized in double distilled deionized water (DDDW) have been
found to be affected by the laser energy and the number of pulses.
The absorption spectra of the nanoparticles DDDW, and the
surface plasmon resonance (SPR) peaks were measured, and found to
be located between (509 and 524)nm using the UV- Vis
spectrophotometer. SPR calculations, images of transmission
electron microscope, and dynamic light scattering (DLS) method
were used to determine the size of GNPs, which found to be ranged
between (3.5 and 27) nm. The concentrations of GNPs in colloidal
solutions found to be ranged between (37 and 142) ppm, and
measured by atomic absorptio

... Show More
View Publication Preview PDF
Crossref (2)
Crossref
Publication Date
Mon Oct 02 2023
Journal Name
Journal Of Engineering
Microgrid Integration Based on Deep Learning NARMA-L2 Controller for Maximum Power Point Tracking
...Show More Authors

This paper presents a hybrid energy resources (HER) system consisting of solar PV, storage, and utility grid. It is a challenge in real time to extract maximum power point (MPP) from the PV solar under variations of the irradiance strength.  This work addresses challenges in identifying global MPP, dynamic algorithm behavior, tracking speed, adaptability to changing conditions, and accuracy. Shallow Neural Networks using the deep learning NARMA-L2 controller have been proposed. It is modeled to predict the reference voltage under different irradiance. The dynamic PV solar and nonlinearity have been trained to track the maximum power drawn from the PV solar systems in real time.

Moreover, the proposed controller i

... Show More
View Publication Preview PDF
Scopus (1)
Scopus Crossref
Publication Date
Thu Nov 02 2023
Journal Name
Journal Of Engineering
Prediction Unconfined Compressive Strength for Different Lithology Using Various Wireline Type and Core Data for Southern Iraqi Field
...Show More Authors

Unconfined Compressive Strength is considered the most important parameter of rock strength properties affecting the rock failure criteria.  Various research have developed rock strength for specific lithology to estimate high-accuracy value without a core.  Previous analyses did not account for the formation's numerous lithologies and interbedded layers. The main aim of the present study is to select the suitable correlation to predict the UCS for hole depth of formation without separating the lithology. Furthermore, the second aim is to detect an adequate input parameter among set wireline to determine the UCS by using data of three wells along ten formations (Tanuma, Khasib, Mishrif, Rumaila, Ahmady, Maudud, Nahr Um

... Show More
View Publication Preview PDF
Scopus (5)
Crossref (2)
Scopus Crossref