Preferred Language
Articles
/
bRfWXJMBVTCNdQwC29Le
Comparative study of logistic regression and artificial neural networks on predicting breast cancer cytology

<p>Currently, breast cancer is one of the most common cancers and a main reason of women death worldwide particularly in<strong> </strong>developing countries such as Iraq. our work aims to predict the type of tumor whether benign or malignant through models that were built using logistic regression and neural networks and we hope it will help doctors in detecting the type of breast tumor. Four models were set using binary logistic regression and two different types of artificial neural networks namely multilayer perceptron MLP and radial basis function RBF. Evaluation of validated and trained models was done using several performance metrics like accuracy, sensitivity, specificity, and AUC (area under receiver operating characteristic ROC).   Dataset was downloaded from UCI ml repository; it is composed of 9 attributes and 699 samples. The findings are clearly showing that the RBF NN classifier is the best in prediction of the type of breast tumors since it had recorded the highest performance in terms of correct classification rate (accuracy), sensitivity, specificity, and AUC (area under Receiver Operating Characteristic ROC) among all other models.</p>

Scopus Crossref
View Publication
Publication Date
Mon Nov 01 2021
Journal Name
Indonesian Journal Of Electrical Engineering And Computer Science
Proposed emerged and enhanced routing protocols for wireless networks

The problem motivation of this work deals with how to control the network overhead and reduce the network latency that may cause many unwanted loops resulting from using standard routing. This work proposes three different wireless routing protocols which they are originally using some advantages for famous wireless ad-hoc routing protocols such as dynamic source routing (DSR), optimized link state routing (OLSR), destination sequenced distance vector (DSDV) and zone routing protocol (ZRP). The first proposed routing protocol is presented an enhanced destination sequenced distance vector (E-DSDV) routing protocol, while the second proposed routing protocol is designed based on using the advantages of DSDV and ZRP and we named it as

... Show More
Scopus (1)
Crossref (1)
Scopus Crossref
Publication Date
Wed Dec 14 2016
Journal Name
Journal Of Baghdad College Of Dentistry
Comparative Evaluation of the Effect of Different Universal Adhesives and Bonding Techniques on the Marginal Gap of Class I Composite Restoration (A SEM Study)

Background: With the increase in composite material use in posterior teeth, the concerns about the polymerization shrinkage has increased with the concerns about the formation of marginal gaps in the oral cavity environment. New generation of adhesives called universal adhesive have been introduced to the market in order to reduce the technique sensitive bonding procedures to give the advantage of using the bonding system in any etching protocol without compromising the bonding strength. The aim of the study was to study marginal adaptation of two universal adhesives (Single bondâ„¢ Universal and Prime and Bond elect) using 3 etching techniques under thermal cycling aging. Materials and Methods: Forty-eight sound maxillary first premola

... Show More
Crossref (1)
Crossref
View Publication Preview PDF
Publication Date
Sat Dec 01 2018
Journal Name
Journal Of Economics And Administrative Sciences
Comparison between the Methods of Ridge Regression and Liu Type to Estimate the Parameters of the Negative Binomial Regression Model Under Multicollinearity Problem by Using Simulation

The problem of Multicollinearity is one of the most common problems, which deal to a large extent with the internal correlation between explanatory variables. This problem is especially Appear in economics and applied research, The problem of Multicollinearity has a negative effect on the regression model, such as oversized variance degree and estimation of parameters that are unstable when we use the Least Square Method ( OLS), Therefore, other methods were used to estimate the parameters of the negative binomial model, including the estimated Ridge Regression Method and the Liu type estimator, The negative binomial regression model is a nonline

... Show More
Crossref
View Publication Preview PDF
Publication Date
Sun Jan 01 2023
Journal Name
International Journal Of Data And Network Science
The effects of big data, artificial intelligence, and business intelligence on e-learning and business performance: Evidence from Jordanian telecommunication firms

This study sought to investigate the impacts of big data, artificial intelligence (AI), and business intelligence (BI) on Firms' e-learning and business performance at Jordanian telecommunications industry. After the samples were checked, a total of 269 were collected. All of the information gathered throughout the investigation was analyzed using the PLS software. The results show a network of interconnections can improve both e-learning and corporate effectiveness. This research concluded that the integration of big data, AI, and BI has a positive impact on e-learning infrastructure development and organizational efficiency. The findings indicate that big data has a positive and direct impact on business performance, including Big

... Show More
Scopus (22)
Crossref (20)
Scopus Crossref
View Publication
Publication Date
Sat Dec 31 2022
Journal Name
Periodicals Of Engineering And Natural Sciences (pen)
Estimation of nonparametric regression function using shrinkage wavelet and different mother functions

Scopus Crossref
View Publication
Publication Date
Wed Mar 10 2021
Journal Name
Baghdad Science Journal
Generating a Strong Key for a Stream Cipher Systems Based on Permutation Networks

The choice of binary Pseudonoise (PN) sequences with specific properties, having long period high complexity, randomness, minimum cross and auto- correlation which are essential for some communication systems. In this research a nonlinear PN generator is introduced . It consists of a combination of basic components like Linear Feedback Shift Register (LFSR), ?-element which is a type of RxR crossbar switches. The period and complexity of a sequence which are generated by the proposed generator are computed and the randomness properties of these sequences are measured by well-known randomness tests.

Crossref
View Publication Preview PDF
Publication Date
Fri Jul 01 2022
Journal Name
Eurasian Chemical Communications
Assessment of hypoxemia status by measuring serum level of hypoxia inducible factor 1 alpha in relation to tumor suppression protein p53, estradiol and tumor proliferation markers of breast cancer in Thi-Qar province/Iraq

Scopus (9)
Scopus Clarivate
Publication Date
Sat Aug 20 2022
Journal Name
Journal Of Legal Sciences
The authority concerned with administrative licenses : A comparative study

The administrative authority (the administration) exercises its activity or work through two forms of business. This administrative act in which the intention of the administrative authority (the administration) is to have a specific legal effect. The risk, and whether the administration is restricted or discretionary in exercising its authority in the licensing area, it must not deviate from the legitimacy framework.

Accordingly, and to be informed of this, we divide our study into three sections, in the first of which we deal with the definition of administrative licenses, and in the second of it we explain the competent authority for administrative licenses in comparative law, and in the third we highlight the authority concer

... Show More
Crossref
View Publication Preview PDF
Publication Date
Sat Aug 06 2022
Journal Name
Ijci. International Journal Of Computers And Information
Techniques for DDoS Attack in SDN: A Comparative Study

Abstract Software-Defined Networking (commonly referred to as SDN) is a newer paradigm that develops the concept of a software-driven network by separating data and control planes. It can handle the traditional network problems. However, this excellent architecture is subjected to various security threats. One of these issues is the distributed denial of service (DDoS) attack, which is difficult to contain in this kind of software-based network. Several security solutions have been proposed recently to secure SDN against DDoS attacks. This paper aims to analyze and discuss machine learning-based systems for SDN security networks from DDoS attack. The results have indicated that the algorithms for machine learning can be used to detect DDoS

... Show More
Crossref (1)
Crossref
View Publication
Publication Date
Sun Jun 01 2014
Journal Name
University Of Baghdad
New Analytical Methods for Drugs Analysis A Comparative Study

Four different spectrophotometric methods are used in this study for the determination of Sulfamethoxazole and sulfanilamide drugs in pharmaceutical compounds, synthetic samples, and in their pure forms. The work comprises four chapters which are shown in the following: Chapter One: Includes a brief for Ultraviolet-Visible (UV-VIS) Absorption spectroscopy, antibacterial drugs and sulfonamides with some methods for their determination. The chapter lists two methods for optimization; univariate method and multivariate method. The later includes different types, two of these were mentioned; simplex method and design of experiment method. Chapter Two: Includes reaction of the two studied drugs with sodium nitrite and hydrochloric acid for diazo

... Show More
Preview PDF