Preferred Language
Articles
/
qxf9Po8BVTCNdQwC4GW7
Toward Constructing a Balanced Intrusion Detection Dataset
...Show More Authors

Several Intrusion Detection Systems (IDS) have been proposed in the current decade. Most datasets which associate with intrusion detection dataset suffer from an imbalance class problem. This problem limits the performance of classifier for minority classes. This paper has presented a novel class imbalance processing technology for large scale multiclass dataset, referred to as BMCD. Our algorithm is based on adapting the Synthetic Minority Over-Sampling Technique (SMOTE) with multiclass dataset to improve the detection rate of minority classes while ensuring efficiency. In this work we have been combined five individual CICIDS2017 dataset to create one multiclass dataset which contains several types of attacks. To prove the efficiency of our algorithm, several machine learning algorithms have been applied on combined dataset with and without using BMCD algorithm. The experimental results have concluded that BMCD provides an effective solution to imbalanced intrusion detection and outperforms the state-of-the-art intrusion detection methods.

Crossref
View Publication
Publication Date
Wed Jul 10 2024
Journal Name
The Open Neuroimaging Journal
The Efficacy of Bedside Chest Ultrasound in the Detection of Traumatic Pneumothorax
...Show More Authors
Background

Chest X-rays have long been used to diagnose pneumothorax. In trauma patients, chest ultrasonography combined with chest CT may be a safer, faster, and more accurate approach. This could lead to better and quicker management of traumatic pneumothorax, as well as enhanced patient safety and clinical results.

Aim

The purpose of this study was to assess the efficacy and utility of bedside US chest in identifying traumatic pneumothorax and also its capacity to estimate the extent of the lesion in comparison to the gold standard modality chest computed tomography.

... Show More
View Publication
Scopus (5)
Crossref (6)
Scopus Crossref
Publication Date
Thu Apr 20 2023
Journal Name
Fire
An Efficient Wildfire Detection System for AI-Embedded Applications Using Satellite Imagery
...Show More Authors

Wildfire risk has globally increased during the past few years due to several factors. An efficient and fast response to wildfires is extremely important to reduce the damaging effect on humans and wildlife. This work introduces a methodology for designing an efficient machine learning system to detect wildfires using satellite imagery. A convolutional neural network (CNN) model is optimized to reduce the required computational resources. Due to the limitations of images containing fire and seasonal variations, an image augmentation process is used to develop adequate training samples for the change in the forest’s visual features and the seasonal wind direction at the study area during the fire season. The selected CNN model (Mob

... Show More
View Publication
Scopus (23)
Crossref (23)
Scopus Clarivate Crossref
Publication Date
Tue Jan 08 2019
Journal Name
Iraqi Journal Of Physics
Detection and interpretation of clouds types using visible and infrared satellite images
...Show More Authors

One of the most Interesting natural phenomena is clouds that have a very strong effect on the climate, weather and the earth's energy balance. Also clouds consider the key regulator for the average temperature of the plant. In this research monitoring and studying the cloud cover to know the clouds types and whether they are rainy or not rainy using visible and infrared satellite images. In order to interpret and know the types of the clouds visually without using any techniques, by comparing between the brightness and the shape of clouds in the same area for both the visible and infrared satellite images, where the differences in the contrasts of visible image are the albedo differences, while in the infrared images is the temperature d

... Show More
View Publication Preview PDF
Crossref
Publication Date
Mon Dec 02 2019
Journal Name
Technologies And Materials For Renewable Energy, Environment And Sustainability
Effect of thickness variation CdO/PSi thin films on detection of radiation
...Show More Authors

CdO films were deposited on substrates from glass, Silicon and Porous silicon by thermal chemical spray pyrolysis technique with different thicknesses (130 and 438.46) nm. Measurements of X-ray diffraction of CdO thin film proved that the structure of the Polycrystalline is cubic lattice, and its crystallite size is located within nano scale range where the perfect orientation is (200). The results show that the surface’s roughness and the root mean square increased with increasing the thickness of prepared films. The UV-Visible measurements show that the CdO films with different thicknesses possess an allowed direct transition with band gap (4) eV. AFM measurement revealed that the silicon porosity located in nano range. Cadmium oxide f

... Show More
Scopus (2)
Scopus
Publication Date
Sun Jan 01 2017
Journal Name
Spe
SPE-188966-MS: Drilling problems detection in Basrah oil fields using smartphones
...Show More Authors

Scopus (1)
Scopus
Publication Date
Wed Jan 01 2020
Journal Name
International Journal Of Computational Intelligence Systems
Evolutionary Feature Optimization for Plant Leaf Disease Detection by Deep Neural Networks
...Show More Authors

View Publication
Scopus (55)
Crossref (52)
Scopus Clarivate Crossref
Publication Date
Fri Jan 01 2021
Journal Name
Ieee Access
Fast Shot Boundary Detection Based on Separable Moments and Support Vector Machine
...Show More Authors

View Publication
Scopus (27)
Crossref (26)
Scopus Clarivate Crossref
Publication Date
Sun Mar 26 2017
Journal Name
Iraqi Journal Of Pharmaceutical Sciences ( P-issn 1683 - 3597 E-issn 2521 - 3512)
Detection and isolation of flavonoids from Calendula officinalis (F.Asteraceae) cultivated in Iraq
...Show More Authors

Calendula officinalis L. (Asteraceae) known as marigold is known to have several pharmacological activities and used for the treatment of several diseases as measles, jaundice, constipation and several inflammations. Marigold flowers contain several chemical constituents mainly flavonoids, triterpenoids and essential oil. In this study marigold flowers cultivated in Iraq had been investigated for its flavonoids content. The study revealed the presence of quercetin and kaempferol glycosides and the absence of myricetin glycosides. The flowers were extracted with ethanol 70% fractionated with different solvent and the flavonoids were isolated by preparative HPLC. The isolated flavonoids were identified by measuring melting points, UV, IR,

... Show More
View Publication Preview PDF
Crossref (1)
Crossref
Publication Date
Sat Apr 01 2023
Journal Name
Iop Conference Series: Earth And Environmental Science
Detection of Mineral and Microbial Contaminants in some Types of Imported Meat
...Show More Authors
Abstract<p>The main target of the current study is to investigate the microbial content and mineral contaminants of the imported meat available in the city of Baghdad and to ensure that it is free from harmful bacteria, safe and it compliances with the Iraqi standard specifications. Some trace mineral elements such as (Iron, Copper, Lead, and Cadmium) were also estimated, where 10 brands of these meats were collected. Bacteriological tests were carried out which included (total bacterial count, <italic>Staphylococcus</italic> bacteria, <italic>Salmonella</italic> bacteria). The results showed highest number of total bacterial count 13×10<sup>5</sup> CFU/g in F8 bra</p> ... Show More
View Publication
Scopus (2)
Scopus Crossref
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 (43)
Crossref (34)
Scopus Clarivate Crossref