research centers


Search results: Found 63

Listing 11 - 20 of 63 << page
of 7
>>
Sort by

Article
Combining the Attribute Oriented Induction and Graph Visualization to Enhancement Association Rules Interpretation

Authors: Safaa O. Al-Mamory د. صفاء عبيس المعموري --- Zahraa Najim Abdullah زهراء نجم عبدالله
Journal: Iraqi Journal for Computers and Informatics ijci المجلة العراقية للحاسبات والمعلوماتية ISSN: 2313190X 25204912 Year: 2016 Volume: 42 Issue: 1 Pages: 10-22
Publisher: University Of Informatics Technology And Communications جامعة تكنولوجيا المعلومات و الاتصالات

Loading...
Loading...
Abstract

The important methods of data mining is large andfrom these methods is mining of association rule. The miningof association rule gives huge number of the rules. These hugerules make analyst consuming more time when searchingthrough the large rules for finding the interesting rules. One ofthe solutions for this problem is combing between one of theAssociation rules visualization method and generalizationmethod. Association rules visualization method is graph-basedmethod. Generalization method is Attribute OrientedInduction algorithm (AOI). AOI after combing calls ModifiedAOI because it removes and changes in the steps of thetraditional AOI. The graph technique after combing also callsgrouped graph method because it displays the aggregated thatresults rules from AOI. The results of this paper are ratio ofcompression that gives clarity of visualization. These resultsprovide the ability for test and drill down in the rules orunderstand and roll up.


Article
Application of Clustering as a Data Mining Tool in Bp systolic diastolic

Authors: Dr. Zeki S. Tywofik --- Ali T. YASEEN
Journal: Journal of College of Education مجلة كلية التربية ISSN: 18120380 Year: 2016 Issue: 3 Pages: 321-326
Publisher: Al-Mustansyriah University الجامعة المستنصرية

Loading...
Loading...
Abstract

This work demonstrates the application of clustering , a data mining tool, in the health care system. Hemoglobin A1c is the most parameters for the monitoring of metabolic control of patients with diabetes mellitus[1]. The aim of this study is to determine the reference rang of glycosylated hemoglobin (Hb A1c%) in an Iraqi population (males and females ) effect and predict Bp systolic diastolic( Blood pressure systolic diastolic) by using demonstrates the application of clustering, as data mining tool, in the health care system. Data mining has the capability for clustering, prediction, estimation, and pattern recognition by using health databases.Blood samples were collected from 100 healthy subjects ( 50 females and 50 males ) are ranged between (20-75) years old as dataset. The reference value of HbA1c% was (5.34 + 0.67)% in female and (5.67 + 0.73)% in males. The present clustering and found a strong relation between HbA1c% and systolic diastolic blood pressure in males whereas the relation in females no significant


Article
Employee Performance Assessment Using Modified Decision Tree

Authors: Hassan A. Jeiad --- Zinah J. M. Ameen --- Alza A. Mahmood
Journal: Engineering and Technology Journal مجلة الهندسة والتكنولوجيا ISSN: 16816900 24120758 Year: 2018 Volume: 36 Issue: 7 Part (A) Engineering Pages: 806-811
Publisher: University of Technology الجامعة التكنولوجية

Loading...
Loading...
Abstract

Decision tree algorithms are famous method in inductive learning and successfully applied for model classification and prediction. Performance evaluation in organization is one of the most important issues that are reliable due to the transition from industrial to knowledge age. This paper proposes the use of modified ID3 (Interactive Dichotomiser 3) decision tree algorithm combining with Taneja entropy instead of the original ID3 algorithm that depends on Shannon entropy which is widely used in the information theory. In fact, the original ID3 was suffer from complexity in the form of complex tree with large number of hops and nodes. The information gain was used as a splitting criteria of the modified ID3. The proposed modified ID3 algorithm has been tested on a dataset for a different university employees with several attributes that directly affect their annual performance assessment. The most optimized tree is constructed by taking one attribute that have the largest information gain from the dataset as a root of tree and repeating the process until the tree is completed. The results showed that the proposed modified ID3 decision tree algorithm that based on Taneja entropy gives less complexity due to small tree with three nodes and two to one hope to reach the right decision.


Article
Effect of Aging Time on Deformation Behavior of Lead-Free and Lead Base Solders Alloys

Author: Alaa H. Ali
Journal: Engineering and Technology Journal مجلة الهندسة والتكنولوجيا ISSN: 16816900 24120758 Year: 2018 Volume: 36 Issue: 8 Part (A) Engineering Pages: 853-866
Publisher: University of Technology الجامعة التكنولوجية

Loading...
Loading...
Abstract

The effect of aging time on the deformation behavior of lead-free and lead- based sub-mm solder alloys were investigated. Experimental results showed that the aging time (less than 4 hours) did not have any effect on the anisotropy behavior of Tin solder balls during compression processes but that is clear in other intervals time specially when the aging time increased, and the microstructure images show different grain growth in high temperature longer time and the Tin anisotropic behavior in lead-free solder alloys


Article
Prediction Model for Financial Distress Using Proposed Data Mining Approach By

Authors: Raghad Mohammed Hadi --- Shatha H. Jafer Al-khalisy --- Najlaa Abd Hamza
Journal: Journal of Al-Qadisiyah for Computer Science and Mathematics مجلة القادسية لعلوم الحاسوب والرياضيات ISSN: 20740204 / 25213504 Year: 2019 Volume: 11 Issue: 2 Pages: Comp Page 37-44
Publisher: Al-Qadisiyah University جامعة القادسية

Loading...
Loading...
Abstract

The problem of financial distress researches are the lack of awareness of banks about the risks of financial failure and its impact on the continuity of its activity in the future, as the traditional methods used to predict financial failure through financial analysis based on financial ratios in a single result gives misleading results cannot be relied upon to judge the continuity of the activity of banks, With an increase in the number of failed banks and their inability to continue. Which requires the discovery of modern techniques that serve as an early warning of the possibility of failure and lack of continuity. The research aims to apply data mining technology to predict the financial failure of banks, and how it can provide information that helps to judge the extent to which banks continue to operate. This effort suggested founded back propagation artificial neural network to build predict system. The proposed module evaluated with banks from Free Iraq Stock Exchange dataset the investigational outcomes displays capable method to identify failure banks with great discovery rate and small wrong terror rate.


Article
Data Clustering Using Fuzzy Approach

Authors: Raghad M. Hadi --- Soukaena H. Hashem --- Abeer T. Maolood
Journal: Journal of Education for Pure Science مجلة التربية للعلوم الصرفة ISSN: 20736592 Year: 2017 Volume: 7 Issue: 3 Pages: 120-136
Publisher: Thi-Qar University جامعة ذي قار

Loading...
Loading...
Abstract

AbstractIn largeComputers;the huge volume of files actually generate disorder to analyze it. So, itdesiresto design a clustering techniques which reduce the costs of analysts. Document clustering isan essentialprocess in text mining, which retrieve the information with an acceptable accuracy,which can be achieved by fuzzy clustering.Reuters 21578 dataset is used for experimental purpose, the proposed system was tested by usingReuters 21578 datasets according to the time required to cluster data. The proposed system improvesdata clustering algorithms by construct required fuzzy clusters. The proposed system showed a goodresult compared with clustering techniques in comparing with other clustering techniques in timeefficiency.


Article
Approach for Spatial Database Mining

Authors: Prof. Dr. Ala’a H. AL-Hamami --- Assest Prof. Dr. Soukaena Hassan --- Dr. Mazin Sameer Al-Hakeem
Journal: Journal of Baghdad College of Economic sciences University مجلة كلية بغداد للعلوم الاقتصادية الجامعة ISSN: 2072778X Year: 2012 Issue: 31 Pages: 407-420
Publisher: Baghdad College of Economic Sciences كلية بغداد للعلوم الاقتصادية

Loading...
Loading...
Abstract

Most of the previous spatial mining works are depend on strategy of organizing the huge spatial data in a suitable data structure and usually the data organized as R-Tree. The data mining algorithms then applied on each level of R-Tree. This method causes time consuming and takes huge storage area and leads to inadequate results. The proposed approach suggests the following strategy for efficient spatial mining. It collects all the spatial data and organizes it (according to normalization and generalization) to a flat data base. After that the following steps will be executed: build the proposed spatial database, apply mining algorithms on the proposed Structure of the spatial data to extract the association rules, clusters and classes. Finally analyzes the resulted patterns from the mining algorithms.


Article
Mining Tutors’ Interesting Areas to Develop Researched Papers Using A Proposed Educational Data Mining System
تنقیب اھتمامات التدریسیین لكتابة بحث باستخدام نظام مقترح يف تنقیب البیانات التعلیمي

Author: Reem Jafar Ismail
Journal: Engineering and Technology Journal مجلة الهندسة والتكنولوجيا ISSN: 16816900 24120758 Year: 2012 Volume: 30 Issue: 10 Pages: 1732-1748
Publisher: University of Technology الجامعة التكنولوجية

Loading...
Loading...
Abstract

Educational Data Mining (EDM) is the process of converting raw data fromeducational systems to useful information that can be used by educational softwaredevelopers, students, teachers, parents, and other educational researchers. One ofthe difficulties in the educational institutes that face the tutor is how to write apaper. This work aims to help the tutor to write a researched paper on specificsubject by finding another tutor who is also interested in the same subject. This is done by exploring the tutor database by usingthe proposed educational data mining system, the tutor database is arranged inmultidimensional form will include: tutor’s teaching subjects, tutor’s interestingareas, tutor’s published researches, tutor’s Msc. and Ph.D research subjects. Theproposed system implements SMC and Cosine similarity measures with newproposed representation of tutor’s database. A clustering K-Means techniques andassociated rule generation is implemented by using WEKA data mining tool. Theresults obtained from that work are very useful for tutor and they give a richanalysis for developing researched papers for different tutors.

یقصد بتنقیب البیانات التعلیمي ھ و عملی ة تحوی ل ك م البیان ات ف ي انظم ة التعل یم ال ى معلوم اتمفیدة یمكن استخدامھا من قبل مبرمجي البرامجیات التعلیمیة او الطلاب او التدریسیین او الوال دیناو اي شخص تعلیمي باحث. احدى الصعوبات التي تواجھ التدریس ي ف ي المؤسس ات التعلیمی ة ھ وایجاد موضوع لكتابة بحث م ن اج ل الترقی ة العلمی ة ف ي مج ال الت دریس ل ذا ف ان البح ث المقت رحیھدف الى مساعدة التدریسي لكتابة بحث في موضوع ما عن طریق ایجاد تدریسي اخ ر ل ھ اھتم امفي نفس الموضوع وسیتم ذلك من خلال التنقیب ف ي قاع دة البیان ات التابع ة ال ى التدریس یین والت يتحتوي عل ى معلوم ات تش مل: موض وعات ال درس الت ي ت م تدریس ھا م ن قب ل التدریس ي ،مج الاتالاھتمام ات البحثی ة للتدریس ي ،البح وث الت ي ت م نش رھا م ن قب ل التدریس ي وك ذلك موض وعاتالماجستیر والدكتوراه التابعة لھ. ان البحث المقترح استخدم صیغة جدیدة لتمثیل البیانات في قاع دةK-Means البیان ات وك ذلك اس تخدم مقیاس ین للتش ابھ. لق د ت م ترتی ب بیان ات التدریس یین ض من لنت ائج .WEKA data mining باس تخدام Associated rule generation و Clusteringالمستخلصة من ھذا البحث مفیدة جدا للتدریسیین وتعطي تحلیل مستفیض من اجل تط ویر البح وثالعلمیة للتدریسیین.


Article
Secured Data Mining Algorithm in E-commerce Environment (SDM algorithm)

Authors: Dr. Nada M. Al-Hakkak --- Nawal A. Ibrahim Al-Jarah
Journal: Journal of Baghdad College of Economic sciences University مجلة كلية بغداد للعلوم الاقتصادية الجامعة ISSN: 2072778X Year: 2014 Volume: 2014 Issue: 5 Pages: 423-433
Publisher: Baghdad College of Economic Sciences كلية بغداد للعلوم الاقتصادية

Loading...
Loading...
Abstract

E-commerce is a new technical method use technology to speed up the commercial work, and find multiple ways for buy and sell goods and services; those ports or ways are endless and does not have any restriction related to geography or time.Data Mining (DM) is considered as one of Business Intelligent (BI) tools that used for data abstraction, from huge amount of data stored in Data Warehouse (DW). DM gets use from Artificial Intelligent (AI) to make machine learning.This paper proposed Secured Data Mining (SDM) algorithm for a secured abstraction learning among events related to E-commerce environment.

تعتبر الاعمال الالكترونية E-commerce اسلوبا تقنيا حديثا يستخدم التكتولوجيا لتسريع المعاملات التجارية وايجاد منافذ بيع وشراء لاتعرف حدودا مكانية او زمانية. لاتنقيب عن البيانات Data Mining (DM) يعتبر احد ادوات Business Intelligent (BI) ويستخدم لاستخلاص بيانات هائلة مخزونة في الــ Data Warehouse (DW) ، الــ DM يستفيد من الــ Artificial Intelligent (AI) لجعل الكمبيوتر بتعلم Machine Learning .هذا البحث يقترح استخدام خوارزمية Secured Data Mining (SDM) وهي التنقيب الامن للبيانات في بيئة الاعمال الالكترونية.


Article
Privacy Preserving for Data Mining Applications

Authors: Soukaena Hassan Hashem --- Ala’a H. AL-Hamami
Journal: Engineering and Technology Journal مجلة الهندسة والتكنولوجيا ISSN: 16816900 24120758 Year: 2008 Volume: 26 Issue: 5 Pages: 552-564
Publisher: University of Technology الجامعة التكنولوجية

Loading...
Loading...
Abstract

The results of data Mining (DM) such as association rules, classes, clusters,etc, will be readily available for working team. So the mining will penetrate theprivacy of sensitive data and makes the stolen of the knowledge resulted muchmore easily. The main objective of the proposed system is preserving the privacyof data mining, that will done by developing algorithms for modifying, encryptingand distributing the original data in the database to be mined. So we ensure theprivacy of data (original data in database that will be mined) and the privacy ofknowledge (the association rules extracted from mined database) even after themining process has taken place. The problem that arises when confidentialinformation can be derived from released data by unauthorized users can be solved.Keyword:

نتائج خوارزميات تعدين البيانات مثل القواعد المترابطة والعنقدة والتصنيفات كلها تكون متوفرةومعلنة لفريق العمل الذي قام باستخراج هذه النتائج. وبهذا فأن عملية التعدين تسبب سهولةاختراق المعلومات الحساسة وتسهل عملية سرقة المعارف الناتجة منها. ان الهدف الرئيسي منهذا البحث هو حماية خصوصية البيانات المراد تعدينها من خلال بناء خوارزميات تحويروتشفير وتوزيع البيانات الاصلية الموجودة ضمن قاعدة البيانات المراد تعدينها. وبهذا نضمنخصوصية البيانات ( البيانات الاصلية في القاعدة المراد تعدينها ) وخصوصية المعارفالمستحصلة ( خصوصية القواعد المترابطة الناتجة من قاعدة البيانات المعدنة ) بعد انتهاء عمليةالتعدين. المشكلة تتنامى عندما تخترق موثوقية المعلومات من قبل الاشخاص غير المخولينبسبب كون المعلومات متوفرة ومعلنة بشكل صريح.

Listing 11 - 20 of 63 << page
of 7
>>
Sort by
Narrow your search

Resource type

article (63)


Language

English (47)

Arabic (4)

Arabic and English (4)


Year
From To Submit

2019 (4)

2018 (11)

2017 (10)

2016 (10)

2015 (1)

More...