Preferred Language
Articles
/
QBeJP48BVTCNdQwCDWaI
Multiresolution hierarchical support vector machine for classification of large datasets
...Show More Authors

Support vector machine (SVM) is a popular supervised learning algorithm based on margin maximization. It has a high training cost and does not scale well to a large number of data points. We propose a multiresolution algorithm MRH-SVM that trains SVM on a hierarchical data aggregation structure, which also serves as a common data input to other learning algorithms. The proposed algorithm learns SVM models using high-level data aggregates and only visits data aggregates at more detailed levels where support vectors reside. In addition to performance improvements, the algorithm has advantages such as the ability to handle data streams and datasets with imbalanced classes. Experimental results show significant performance improvements in comparison with existing SVM algorithms.

Scopus Clarivate Crossref
View Publication
Publication Date
Thu Oct 01 2020
Journal Name
Upstream Oil And Gas Technology
Integrated approach for non-Darcy flow in hydraulic fractures considering different fracture geometries and reservoir characteristics
...Show More Authors

Scopus (5)
Crossref (4)
Scopus Clarivate Crossref
Publication Date
Fri Aug 05 2016
Journal Name
Wireless Communications And Mobile Computing
A comparison study on node clustering techniques used in target tracking WSNs for efficient data aggregation
...Show More Authors

Wireless sensor applications are susceptible to energy constraints. Most of the energy is consumed in communication between wireless nodes. Clustering and data aggregation are the two widely used strategies for reducing energy usage and increasing the lifetime of wireless sensor networks. In target tracking applications, large amount of redundant data is produced regularly. Hence, deployment of effective data aggregation schemes is vital to eliminate data redundancy. This work aims to conduct a comparative study of various research approaches that employ clustering techniques for efficiently aggregating data in target tracking applications as selection of an appropriate clustering algorithm may reflect positive results in the data aggregati

... Show More
View Publication
Scopus (31)
Crossref (24)
Scopus Clarivate Crossref
Publication Date
Wed Mar 29 2023
Journal Name
Iraqi Journal Of Chemical And Petroleum Engineering
Cold Cracking Technology for Crude Oil Upgrading in Qaiyarah Heavy Oil Field; Technical and Economical Evaluation
...Show More Authors

Heavy oil is classified as unconventional oil resource because of its difficulty to recover in its natural state, difficulties in transport and difficulties in marketing it. Upgrading solution to the heavy oil has positive impact technically and economically specially when it will be a competitive with conventional oils from the marketing prospective. Developing Qaiyarah heavy oil field was neglected in the last five decades, the main reason was due to the low quality of the crude oil resulted in the high viscosity and density of the crude oil in the field which was and still a major challenge putting them on the major stream line of production in Iraq. The low quality of the crude properties led to lower oil prices in the global markets

... Show More
View Publication Preview PDF
Crossref (1)
Crossref
Publication Date
Mon Feb 06 2023
Journal Name
Journal Of Kufa-physics
No-Core optical fibers sensor for detecting hemoglobin concentration (HB) based on the Surface Plasmon resonance.
...Show More Authors

In this work, a fiber-optic biomedical sensor was manufactured to detect hemoglobin percentages in the blood. SPR-based coreless optical fibers were developed and implemented using single and multiple optical fibers. It was also used to calculate refractive indices and concentrations of hemoglobin in blood samples. An optical fiber, with a thickness of 40 nanometers, was deposited on gold metal for the sensing area to increase the sensitivity of the sensor. The optical fiber used in this work has a diameter of 125μm, no core, and is made up of a pure silica glass rod and an acrylate coating. The length of the fiber was 4cm removed buffer and the splicing process was done. It is found in practice that when the sensitive refractive i

... Show More
View Publication Preview PDF
Crossref (1)
Crossref
Publication Date
Sun Apr 13 2025
Journal Name
Scientific Reports
Optimized image segmentation using an improved reptile search algorithm with Gbest operator for multi-level thresholding
...Show More Authors
Abstract<p>Image segmentation using bi-level thresholds works well for straightforward scenarios; however, dealing with complex images that contain multiple objects or colors presents considerable computational difficulties. Multi-level thresholding is crucial for these situations, but it also introduces a challenging optimization problem. This paper presents an improved Reptile Search Algorithm (RSA) that includes a Gbest operator to enhance its performance. The proposed method determines optimal threshold values for both grayscale and color images, utilizing entropy-based objective functions derived from the Otsu and Kapur techniques. Experiments were carried out on 16 benchmark images, which inclu</p> ... Show More
View Publication
Scopus (3)
Crossref (4)
Scopus Clarivate Crossref
Publication Date
Mon Jun 19 2017
Journal Name
Arabian Journal For Science And Engineering
A New Method to Tune a Fractional-Order PID Controller for a Twin Rotor Aerodynamic System
...Show More Authors

View Publication
Scopus (35)
Crossref (32)
Scopus Clarivate Crossref
Publication Date
Tue Dec 05 2023
Journal Name
Baghdad Science Journal
AlexNet Convolutional Neural Network Architecture with Cosine and Hamming Similarity/Distance Measures for Fingerprint Biometric Matching
...Show More Authors

In information security, fingerprint verification is one of the most common recent approaches for verifying human identity through a distinctive pattern. The verification process works by comparing a pair of fingerprint templates and identifying the similarity/matching among them. Several research studies have utilized different techniques for the matching process such as fuzzy vault and image filtering approaches. Yet, these approaches are still suffering from the imprecise articulation of the biometrics’ interesting patterns. The emergence of deep learning architectures such as the Convolutional Neural Network (CNN) has been extensively used for image processing and object detection tasks and showed an outstanding performance compare

... Show More
View Publication Preview PDF
Scopus (5)
Crossref (3)
Scopus Crossref
Publication Date
Tue Nov 01 2022
Journal Name
Computers And Electronics In Agriculture
A novel heat-pulse probe for measuring soil thermal conductivity: Field test under different tillage practices
...Show More Authors

View Publication
Scopus (13)
Crossref (7)
Scopus Clarivate Crossref
Publication Date
Tue Nov 30 2021
Journal Name
Iraqi Geological Journal
Subsurface Investigation Using Electrical Resistivity Imaging for Proposed Industrial Site near Erbil-Kirkuk Borders, Northern Iraq
...Show More Authors

The friendly-environment geophysical methods are commonly used in various engineering and near-surface environmental investigations. Electrical Resistivity Imaging technique was used to investigate the subsurface rocks, sediments properties of a proposed industrial site to characterize the lateral and vertical lithological changes. via the electrical resistivity, to give an overview about the karst, weak and robust subsoil zones. Nineteen 2D ERI profiles using Wenner array with 2 m electrode spacing have been applied to investigate the specific industry area. One of these profiles has been conducted with one-meter electrode spacing. The surveyed profiles are divided into a number of blocks, each block consists of several parallel pr

... Show More
View Publication Preview PDF
Scopus (8)
Scopus Crossref
Publication Date
Mon Jun 19 2023
Journal Name
Journal Of Engineering
Active Carbon from Date Stones for Phenol Oxidation in Trickle Bed Reactor, Experimental and Kinetic Study
...Show More Authors

The catalytic wet air oxidation (CWAO) of phenol has been studied in a trickle bed reactor

using  active  carbon  prepared  from  date  stones  as  catalyst  by  ferric  and  zinc  chloride activation (FAC and ZAC). The activated carbons were characterized by measuring their surface area and adsorption capacity besides conventional properties, and then checked for CWAO using a trickle bed reactor operating at different conditions (i.e. pH, gas flow rate, LHSV, temperature and oxygen partial pressure). The results showed that the active carbon (FAC and ZAC), without any active metal supported, gives the highest phenol conversion. The reaction network proposed account

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