Preferred Language
Articles
/
ijs-250
Modified Artificial immune system as Feature Selection
...Show More Authors

Feature selection algorithms play a big role in machine learning applications. There are several feature selection strategies based on metaheuristic algorithms. In this paper a feature selection strategy based on Modified Artificial Immune System (MAIS) has been proposed. The proposed algorithm exploits the advantages of Artificial Immune System AIS to increase the performance and randomization of features. The experimental results based on NSL-KDD dataset, have showed increasing in performance of accuracy compared with other feature selection algorithms (best first search, correlation and information gain).

View Publication Preview PDF
Quick Preview PDF
Publication Date
Fri Feb 07 2025
Journal Name
Al–bahith Al–a'alami
Foreign Series in the Kurdish Satellite Channels and Their Role in the Development of Awareness among Young People in the Kurdistan Region (Korean Series as a Model) (A Field Study on a Sample of Students of the Institute of Fine Arts in the City of Sulay
...Show More Authors

The dubbing process for the Foreign Dramas by the Kurdish language became a serious phenomenon in the Kurdish satellite TV, especially in the past few years. It attracted a wide audience, especially young adolescents. And prepared by some breakthrough hostile to Kurdish culture and value coordinated by others remedy for the structural gaps and lapses have, as a result of climate which is brought into existence globalization and secretions variety dimensional, saturated value and cognitive effects bearing a strong identity of its elements. From here, the problem of this research is the ambiguity of their role in a series of developmental processes Kurdish awareness of young people and the extent of the impact that caused it.

This

... Show More
View Publication Preview PDF
Publication Date
Sat Jun 01 2019
Journal Name
Journal Of The College Of Languages (jcl)
An Analytical Study of Viewpoint in Parsi Pour's and Ar-Rikabi's Novels: The Dog and the Long Night and Alibaba's Sad Night as Examples: بررسی تحليلی زاویه¬ی دید در رمان¬های پارسی پور و الرکابی باتكيه بر رمان "سگ و زمستان بلند" و "ليل علی بابا الحزین"
...Show More Authors

It is noted in the title that the paper studies the viewpoint in the novel The Dog and the Long Night by the Iranian novelist Shahranoush Parsi Pour and in the novel Alibaba's Sad Night by the Iraqi novelist Abdulkhaliq Ar-Rikabi. Both are well known novelists, and about whose stories and novels many critical books, MA theses, and Ph.D. dissertations have been written. Also, some of their literary works have won prizes. Here, the researcher shed light on the concept of viewpoint, its types, and its importance in novels in general. This was done along with tackling the two viewpoints in both novels, where similarities and differences were identified. For this end, the researcher has adopted the analytic-descriptive appro

... Show More
View Publication Preview PDF
Crossref (1)
Crossref
Publication Date
Mon Sep 20 2021
Journal Name
Key Engineering Materials
Effect of Partial Substitution of Sr by Ba on the Structural Properties of Tl<sub>0.8</sub>Ni<sub>0.2</sub>Sr<sub>2-x</sub>Br<sub>x</sub>Ca<sub>2</sub>Cu<sub>3</sub>O<sub>9-δ</sub> System
...Show More Authors

In this manuscript, the effect of substituting strontium with barium on the structural properties of Tl0.8Ni0.2Sr2-xBrxCa2Cu3O9-δcompound with x= 0, 0.2, 0.4, have been studied. Samples were prepared using solid state reaction technique, suitable oxides alternatives of Pb2O3, CaO, BaO and CuO with 99.99% purity as raw materials and then mixed. They were prepared in the form of discs with a diameter of 1.5 cm and a thickness of (0.2-0.3) cm under pressures 7 tons / cm2, and the samples were sintered at a constant temperature o

... Show More
View Publication
Scopus (3)
Scopus Crossref
Publication Date
Sat Jul 31 2021
Journal Name
Iraqi Journal Of Science
A Decision Tree-Aware Genetic Algorithm for Botnet Detection
...Show More Authors

     In this paper, the botnet detection problem is defined as a feature selection problem and the genetic algorithm (GA) is used to search for the best significant combination of features from the entire search space of set of features. Furthermore, the Decision Tree (DT) classifier is used as an objective function to direct the ability of the proposed GA to locate the combination of features that can correctly classify the activities into normal traffics and botnet attacks. Two datasets  namely the UNSW-NB15 and the Canadian Institute for Cybersecurity Intrusion Detection System 2017 (CICIDS2017), are used as evaluation datasets. The results reveal that the proposed DT-aware GA can effectively find the relevant

... Show More
View Publication Preview PDF
Scopus (4)
Crossref (1)
Scopus Crossref
Publication Date
Wed Dec 30 2020
Journal Name
Iraqi Journal Of Science
Hybrid vs Ensemble Classification Models for Phishing Websites
...Show More Authors

Phishing is an internet crime achieved by imitating a legitimate website of a host in order to steal confidential information. Many researchers have developed phishing classification models that are limited in real-time and computational efficiency.  This paper presents an ensemble learning model composed of DTree and NBayes, by STACKING method, with DTree as base learner. The aim is to combine the advantages of simplicity and effectiveness of DTree with the lower complexity time of NBayes. The models were integrated and appraised independently for data training and the probabilities of each class were averaged by their accuracy on the trained data through testing process. The present results of the empirical study on phishing websi

... Show More
View Publication Preview PDF
Scopus (10)
Crossref (6)
Scopus Crossref
Publication Date
Tue Jun 23 2020
Journal Name
Baghdad Science Journal
Anomaly Detection Approach Based on Deep Neural Network and Dropout
...Show More Authors

   Regarding to the computer system security, the intrusion detection systems are fundamental components for discriminating attacks at the early stage. They monitor and analyze network traffics, looking for abnormal behaviors or attack signatures to detect intrusions in early time. However, many challenges arise while developing flexible and efficient network intrusion detection system (NIDS) for unforeseen attacks with high detection rate. In this paper, deep neural network (DNN) approach was proposed for anomaly detection NIDS. Dropout is the regularized technique used with DNN model to reduce the overfitting. The experimental results applied on NSL_KDD dataset. SoftMax output layer has been used with cross entropy loss funct

... Show More
View Publication Preview PDF
Scopus (23)
Crossref (9)
Scopus Clarivate Crossref
Publication Date
Tue Jan 01 2019
Journal Name
Advances In Materials Physics And Chemistry
The Role of Cooling Condition on the Superconducting Properties of Tl<sub>2-x</sub>Hg<sub>x</sub>Sr<sub>2</sub>Ca<sub>2</sub>Cu<sub>3</sub>O<sub>10+δ</sub> System
...Show More Authors

View Publication
Crossref
Publication Date
Tue Jan 04 2022
Journal Name
Iraqi Journal Of Science
Proposed Handwriting Arabic Words classification Based On Discrete Wavelet Transform and Support Vector Machine
...Show More Authors

A proposed feature extraction algorithm for handwriting Arabic words. The proposed method uses a 4 levels discrete wavelet transform (DWT) on binary image. sliding window on wavelet space and computes the stander derivation for each window. The extracted features were classified with multiple Support Vector Machine (SVM) classifiers. The proposed method simulated with a proposed data set from different writers. The experimental results of the simulation show 94.44% recognition rate.

View Publication Preview PDF
Publication Date
Sat Jun 01 2024
Journal Name
International Journal Of Advanced And Applied Sciences
High-accuracy models for iris recognition with merging features
...Show More Authors

Due to advancements in computer science and technology, impersonation has become more common. Today, biometrics technology is widely used in various aspects of people's lives. Iris recognition, known for its high accuracy and speed, is a significant and challenging field of study. As a result, iris recognition technology and biometric systems are utilized for security in numerous applications, including human-computer interaction and surveillance systems. It is crucial to develop advanced models to combat impersonation crimes. This study proposes sophisticated artificial intelligence models with high accuracy and speed to eliminate these crimes. The models use linear discriminant analysis (LDA) for feature extraction and mutual info

... Show More
View Publication
Scopus Clarivate Crossref
Publication Date
Fri Sep 30 2022
Journal Name
Iraqi Journal Of Science
Improving Measurement of Effectiveness of Blended Learning in Iraqi Education Using SVM
...Show More Authors

E-learning has recently become of great importance, especially after the emergence of the Corona pandemic, but e-learning has many disadvantages. In order to preserve education, some universities have resorted to using blended learning. Currently, the Ministry of Higher Education and Scientific Research in Iraq has adopted e-learning in universities and schools, especially in scientific disciplines that need laboratories and a spatial presence. In this work, we collected a dataset based on 27 features and presented a model utilizing a support vector machine with regression that was enhanced with the KNN method, which identifies factors that have a substantial influence on the model for the type of education, whether blended or traditiona

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