Preferred Language
Articles
/
ijs-8043
Hybrid CNN-SMOTE-BGMM Deep Learning Framework for Network Intrusion Detection using Unbalanced Dataset
...Show More Authors

This paper proposes a new methodology for improving network security by introducing an optimised hybrid intrusion detection system (IDS) framework solution as a middle layer between the end devices. It considers the difficulty of updating databases to uncover new threats that plague firewalls and detection systems, in addition to big data challenges. The proposed framework introduces a supervised network IDS based on a deep learning technique of convolutional neural networks (CNN) using the UNSW-NB15 dataset. It implements recursive feature elimination (RFE) with extreme gradient boosting (XGB) to reduce resource and time consumption. Additionally, it reduces bias towards the majority class of the dataset by combining the Synthetic Minority Oversampling Technique (SMOTE) with the Bayesian Gaussian Mixture Model (BGMM) to solve the data imbalance problem. The results demonstrate that this model greatly outperforms the existing approaches, attaining identification rates in the binary classification of up to 98.80% and the multiple group classification of up to 96.49%.

Scopus Crossref
View Publication Preview PDF
Quick Preview PDF
Publication Date
Thu May 04 2017
Journal Name
Ibn Al-haitham Journal For Pure And Applied Sciences
Minimizing total Completion Time and Maximum late Work Simultaneously
...Show More Authors

In this paper, the problem of scheduling jobs on one machine for a variety multicriteria
are considered to minimize total completion time and maximum late work. A set of n
independent jobs has to be scheduled on a single machine that is continuously available from
time zero onwards and that can handle no more than one job at a time. Job i,(i=1,…,n)
requires processing during a given positive uninterrupted time pi, and its due date d
i.
For the bicriteria problems, some algorithms are proposed to find efficient (Pareto)
solutions for simultaneous case. Also for the multicriteria problem we proposed general
algorithms which gives efficient solutions within the efficient range

View Publication Preview PDF
Publication Date
Mon Aug 01 2011
Journal Name
Journal Of Engineering
LDPC CODED MULTIUSER MC-CDMA PERFORMANCE OVERMULTIPATH RAYLEIGH FADING CHANNEL
...Show More Authors

This work presents the simulation of a Low density Parity Check (LDPC) coding scheme with
multiuserMulti-Carrier Code Division Multiple Access (MC-CDMA) system over Additive White
Gaussian Noise (AWGN) channel and multipath fading channels. The decoding technique used in
the simulation was iterative decoding since it gives maximum efficiency with ten iterations.
Modulation schemes that used are Phase Shift Keying (BPSK, QPSK and 16 PSK), along with the
Orthogonal Frequency Division Multiplexing (OFDM). A 12 pilot carrier were used in the estimator
to compensate channel effect. The channel model used is Long Term Evolution (LTE) channel with
Technical Specification TS 25.101v2.10 and 5 MHz bandwidth including the chan

... Show More
View Publication Preview PDF
Crossref
Publication Date
Sat Oct 01 2011
Journal Name
Journal Of Engineering
THE EFFECT OF CUTOFF WALL ANGLE ON SEEPAGE UNDER DAMS
...Show More Authors

Flow of water under concrete dams generates uplift pressure under the dam, which may cause the dam to function improperly, in addition to the exit gradient that may cause piping if exceeded a safe value. Cutoff walls usually used to minimize the effect of flow under dams. It is required to
1)minimize the flow quantity to conserve water in the reservoir, it is also required to
2)minimize the uplift pressure under the dam to maintain stability of the dam, and it is required to

3) minimize the exit gradient to prevent quick condition to occur at the toe of the dam where piping may occur and may cause erosion of the soil. Varying the angle of cutoff walls affects its influence on the factors aforementioned that are required to

... Show More
View Publication Preview PDF
Crossref (6)
Crossref
Publication Date
Thu Jan 02 2014
Journal Name
Journal Of The Faculty Of Medicine Baghdad
Surgery in Varicose Veins
...Show More Authors

Background: Varicose veins are common in Iraq. Increasing incidence is associated with available jobs of bodyguards, barbers and computer workers.

Objectives: To highlight the frequency, presentation, methods of accurate diagnosis and surgical procedures which are commonly used by Vascular Surgeons in Medical City Teaching Complex, Al-Shaheed Ghazi Al-Hariri Subspecialties hospital and to compare this study with other international studies.

Patients and methods:  This is a retrospective study of hundred patients with varicose veins, who were admitted and surgically treated at Al-Shaheed Ghazi Al-Hariri subspecialties hospital during one year period (1st of July 2010

... Show More
View Publication Preview PDF
Crossref
Publication Date
Mon Feb 04 2019
Journal Name
Iraqi Journal Of Physics
Structure dependence of gamma ray irradiation effects on polyurethane and epoxy resin studied by PAL technique
...Show More Authors

Positron annihilation lifetime (PAL) technique has been employed to
study the microstructural changes of polyurethane (PU), EUXIT 101
and epoxy risen (EP), EUXIT 60 by Gamma-ray irradiation with the
dose range (95.76 - 957.6) kGy. The size of the free volume hole and
their fraction in PU and EP were determined from ortho-positronium
lifetime component and its intensity in the measured lifetime spectra.
The results show that the irradiation causes significant changes in the
free volume hole size (Vh) and the fractional free volume (Fh), and
thereby the microstructure of PU and EP. The results indicate that
the γ-dose increases the crystallinity in the amorphous regions of PU
and increas

... Show More
View Publication Preview PDF
Crossref (1)
Crossref
Publication Date
Sun Oct 03 2010
Journal Name
Journal Of Educational And Psychological Researches
The Effect of Applying K-W-L Technique on Teaching ESP Students
...Show More Authors

         Over the last few decades, many instructors have been trying all kinds of teaching methods, but without benefit. Nevertheless, in the 1986, a new technique is appeared which called K-W-L technique, it  is specified for reading comprehension passages because reading  skill is not easy matter for students for specific purposes (ESP).therefore, the K-W-L technique is a good one for thinking and experiences. To fulfill the aims and verify the hypothesis which reads as follows" it is hypothesized that there are no significant differences between the achievements of students who are taught according to K-W-L technique and those who are taught according to the traditional method

... Show More
View Publication Preview PDF
Publication Date
Fri Nov 24 2023
Journal Name
Iraqi Journal Of Science
Bayesian Analysis of five Exponentiated Distributions under different Priors and loss functions
...Show More Authors

The paper is concerned with posterior analysis of five exponentiated (Weibull, Exponential, Inverted Weibull, Pareto, Gumbel) distrebutions. The expressions for Bayes estimators of the shape parameters have been derived under four different prior distributions assuming four different loss functions. The posterior predictive distributions have been obtained, and the comparison between estimators made by using the mean squared errors through generated different sample sizes by using simulation technique. In general, the performance of estimators under Chi-square prior using squared error loss function is the best.

View Publication Preview PDF
Publication Date
Fri Jun 30 2023
Journal Name
Iraqi Journal Of Science
Statistical Analysis of COVID-19 Data in Iraq
...Show More Authors

The analysis of COVID-19 data in Iraq is carried out. Data includes daily cases and deaths since the outbreak of the pandemic in Iraq on February 2020 until the 28th of June 2022. This is done by fitting some distributions to the data in order to find out the most appropriate distribution fit to both daily cases and deaths due to the COVID-19 pandemic. The statistical analysis includes estimation of the parameters, the goodness of fit tests and illustrative probability plots. It was found that the generalized extreme value and the generalized Pareto distributions may provide a good fit for the data for both daily cases and deaths. However, they were rejected by the goodness of fit test statistics due to the high variability of the data.<

... Show More
View Publication Preview PDF
Scopus (2)
Scopus Crossref
Publication Date
Tue Jan 25 2022
Journal Name
Iraqi Journal Of Science
Modeling of medium-Sized magnitudes of earthquakes
...Show More Authors

n this work, it have earthquakes data been analytized as a result of ground water injection attendant to dig wells and oil, which affects the pressure pores in the rock and is according to cause a medium-sized earthquake that have already occurred more than 20 times. according to the publication of the Department of Attenba, the dangers of earthquakes and movement flooring in Guy-Greenbrie-United area of one of United States of America cities, where these data represent a monitor magnitudes of earthquakes from September 2008 the September 2011, we conducted statistical analysis and create a model for earthquakes flooring that was chosen for four dis-tributions and results i the optima reveal the best distribution is the Burr X11 then Gen

... Show More
View Publication Preview PDF
Publication Date
Fri Sep 30 2022
Journal Name
Journal Of Economics And Administrative Sciences
Estimation of Reliability through the Wiener Degradation Process Based on the Genetic Algorithm to Estimating Parameters
...Show More Authors

      In this paper, the researcher suggested using the Genetic algorithm method to estimate the parameters of the Wiener degradation process,  where it is based on the Wiener process in order to estimate the reliability of high-efficiency products, due to the difficulty of estimating the reliability of them using traditional techniques that depend only on the failure times of products. Monte Carlo simulation has been applied for the purpose of proving the efficiency of the proposed method in estimating parameters; it was compared with the method of the maximum likelihood estimation. The results were that the Genetic algorithm method is the best based on the AMSE comparison criterion, then the reliab

... Show More
View Publication Preview PDF
Crossref