Preferred Language
Articles
/
ijs-9244
Using One-Class SVM with Spam Classification
...Show More Authors

Support Vector Machine (SVM) is supervised machine learning technique which has become a popular technique for e-mail classifiers because its performance improves the accuracy of classification. The proposed method combines gain ratio (GR) which is feature selection method with one-class training SVM to increase the efficiency of the detection process and decrease the cost. The results show high accuracy up to 100% and less error rate with less number of feature to 5 features.

View Publication Preview PDF
Quick Preview PDF
Publication Date
Fri Jan 31 2025
Journal Name
Journal Of Baghdad College Of Dentistry
Photogrammetric analysis of facial soft tissue profile of Iraqi adults sample with Class II div.1 and Class III malocclusion: (A comparative study)
...Show More Authors

Background: The purposes of this study were to determine the photogrammetric soft tissue facial profile measurements for Iraqi adults sample with class II div.1 and class III malocclusion using standardized photographic techniques and to verify the existence of possible gender differences. Materials & methods: Seventy five Iraqi adult subjects, 50 class II div.1 malocclusion (24 males and 26 females), 25 class III malocclusion (14 males and 11 females), with an age range from 18-25 years. Each individual was subjected to clinical examination and digital standardized right side photographic records were taken in the natural head position. The photographs were analyzed using AutoCAD program 2007 to measure the distances and angles used in t

... Show More
View Publication Preview PDF
Publication Date
Mon Oct 10 2016
Journal Name
Iraqi Journal Of Science
Satellite image classification using KL-transformation and modified vector quantization
...Show More Authors

In this work, satellite images classification for Al Chabaish marshes and the area surrounding district in (Dhi Qar) province for years 1990,2000 and 2015 using two software programming (MATLAB 7.11 and ERDAS imagine 2014) is presented. Proposed supervised classification method (Modified Vector Quantization) using MATLAB software and supervised classification method (Maximum likelihood Classifier) using ERDAS imagine have been used, in order to get most accurate results and compare these methods. The changes that taken place in year 2000 comparing with 1990 and in year 2015 comparing with 2000 are calculated. The results from classification indicated that water and vegetation are decreased, while barren land, alluvial soil and shallow water

... Show More
Publication Date
Mon Aug 26 2019
Journal Name
Iraqi Journal Of Science
Improving Accuracy in Human Age Classification Using Ensemble Learning Techniques
...Show More Authors

     Age is a predominant parameter for arbitrating an individual, for security and access concerns of the data that exist in cyber space. Nowadays we find a rapid growth in unethical practices from youngsters as well as skilled cyber users. Facial image renders a variety of information that can be used, when processed to ascertain the age of individuals. In this paper, local facial features are considered to predict the age group, where local Binary Pattern (LBP) is extracted from four regions of facial images. The prominent areas where wrinkles are developed naturally in human as age increases are taken for feature extraction. Further these feature vectors are subjected to  ensemble techniques that increases th

... Show More
View Publication Preview PDF
Scopus (1)
Scopus Crossref
Publication Date
Thu May 05 2022
Journal Name
Periodicals Of Engineering And Natural Sciences (pen)
Classification SINGLE-LEAD ECG by using conventional neural network algorithm
...Show More Authors

View Publication
Scopus Crossref
Publication Date
Sat Oct 01 2016
Journal Name
2016 6th International Conference On Information Communication And Management (icicm)
Enhancing case-based reasoning retrieval using classification based on associations
...Show More Authors

View Publication
Scopus (4)
Crossref (2)
Scopus Crossref
Publication Date
Mon Dec 01 2014
Journal Name
Journal Of Economics And Administrative Sciences
Comparison between some of linear classification models with practical application
...Show More Authors

Linear discriminant analysis and logistic regression are the most widely used in multivariate statistical methods for analysis of data with categorical outcome variables .Both of them are appropriate for the development of linear  classification models .linear discriminant analysis has been that the data of explanatory variables must be distributed multivariate normal distribution. While logistic regression no assumptions on the distribution of the explanatory data. Hence ,It is assumed that logistic regression is the more flexible and more robust method in case of violations of these assumptions.

In this paper we have been focus for the comparison between three forms for classification data belongs

... Show More
View Publication Preview PDF
Crossref
Publication Date
Thu Mar 10 2022
Journal Name
Buildings
Behavior of One-Way Reinforced Concrete Slabs with Polystyrene Embedded Arched Blocks
...Show More Authors

This study presents experimental and numerical investigations on seven one-way, reinforced concrete (RC) slabs with a new technique of slab weight reduction using polystyrene-embedded arched blocks (PEABs). All slabs had the same dimensions, steel reinforcement, and concrete compressive strength. One of these slabs was a solid slab, which was taken as a control slab, while the other six slabs were cast with PEABs. The main variables were the ratio of the length of the PEABs to the length of the slab (lp/L) and the ratio of the height of the PEABs to the total slab depth (hP/H). The minimum decrease in the ultimate load capacity was about 6% with a minimum reduction in the slab weight of 15%. In contrast, the maximum decrease in the

... Show More
Scopus (4)
Crossref (1)
Scopus Clarivate Crossref
Publication Date
Sun Mar 03 2013
Journal Name
Baghdad Science Journal
The Association of Myasthenia Gravis with HLA class II Antigens in Iraqi Patients
...Show More Authors

The nature and intensity of the association of myasthenia gravis (MG) with distinct human leukocyte antigen (HLA) haplotypes differ between ethnic populations, so this study determined the association of HLA class II antigens with myasthenia gravis (MG) in Iraq.The study included Iraqi patients diagnosed with MG and two control groups the first of 54 insulin dependent diabetes mellitus patients and the second of 237 subjects as a normal control group. The test used was microlymphocytotoxicity test.The work was done in the Teaching Laboratories/Medical City/Baghdad.Results: positive associations were observed (etiological risk factors) as follows: 1. HLA-DR locus showed one positively associated allele when compared to healthy control and th

... Show More
View Publication Preview PDF
Crossref
Publication Date
Sun Sep 29 2019
Journal Name
Iraqi Journal Of Science
Some Geometric Properties of Generalized Class of Meromorphic Functionsassocisted with Higher Ruscheweyh Derivatives
...Show More Authors

     The applications of Ruscheweyh derivative are studied and discussed of class of meromorphic multivalent application. We get some interesting geometric properties, such as coefficient bound, Convex linear combination, growth and distortion bounds, radii of starlikenss ,  convexity and neighborhood property.

View Publication Preview PDF
Scopus (6)
Scopus Crossref
Publication Date
Mon Oct 01 2018
Journal Name
Iraqi Journal Of Physics
Classification of brain tumors using the multilayer perceptron artificial neural network
...Show More Authors

Information from 54 Magnetic Resonance Imaging (MRI) brain tumor images (27 benign and 27 malignant) were collected and subjected to multilayer perceptron artificial neural network available on the well know software of IBM SPSS 17 (Statistical Package for the Social Sciences). After many attempts, automatic architecture was decided to be adopted in this research work. Thirteen shape and statistical characteristics of images were considered. The neural network revealed an 89.1 % of correct classification for the training sample and 100 % of correct classification for the test sample. The normalized importance of the considered characteristics showed that kurtosis accounted for 100 % which means that this variable has a substantial effect

... Show More
View Publication Preview PDF
Crossref (3)
Crossref