Business intelligence framework using ant colony optimization for feature selection in higher education institution
Recently, business intelligence (BI) has become an important tool for effective decision-making. BI is a mathematical framework to gain information and knowledge through the process of extracting, transforming, managing, and analyzing data. The demand for accurate knowledge in higher education secto...
Saved in:
Main Author: | |
---|---|
Format: | Thesis |
Language: | English |
Published: |
2017
|
Subjects: | |
Online Access: | http://eprints.utm.my/id/eprint/86987/1/ShaminiRajaKumaranMFC2017.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
id |
my-utm-ep.86987 |
---|---|
record_format |
uketd_dc |
spelling |
my-utm-ep.869872020-10-31T12:16:32Z Business intelligence framework using ant colony optimization for feature selection in higher education institution 2017 Raja Kumaran, Shamini QA75 Electronic computers. Computer science Recently, business intelligence (BI) has become an important tool for effective decision-making. BI is a mathematical framework to gain information and knowledge through the process of extracting, transforming, managing, and analyzing data. The demand for accurate knowledge in higher education sector needs a correct technique to extract the exact information for decision-making. However, current BI frameworks and systems lack the ability to transform data into information, and these caused users not to able to fully utilize the BI outcome. This research developed a BI framework for the higher education that is able to explore, analyse and visualize the relevant data into information for use by the top management. This framework identifies the best set of attributes and evaluates the performance of the model with the help of 27 input features. In this case study, the framework used Ant Colony Optimization (ACO) technique mainly to identify the best set of attributes, and the performance was validated using Support Vector Machine (SVM). The framework consists of four layers which are data source, data integration, analytic, and access. Each layer contributes to decision making in terms of processing data, selection of significant features and data visualization. In this study, 46,658 input data were processed for identification of Graduate on Time (GOT) decision in the context of higher education referred as Masters and Doctor of Philosophy (PhD) postgraduates who completed their study within a specified period. The performance evaluation of the data achieved accuracies of 86.44% for PhD and 96.2% for Master’s. Based on the findings, the results showed that the BI dashboard as an output from the framework is capable of providing a good decision-making tool for education management. 2017 Thesis http://eprints.utm.my/id/eprint/86987/ http://eprints.utm.my/id/eprint/86987/1/ShaminiRajaKumaranMFC2017.pdf application/pdf en public http://dms.library.utm.my:8080/vital/access/manager/Repository/vital:132629 masters Universiti Teknologi Malaysia, Faculty of Computing Faculty of Computing |
institution |
Universiti Teknologi Malaysia |
collection |
UTM Institutional Repository |
language |
English |
topic |
QA75 Electronic computers Computer science |
spellingShingle |
QA75 Electronic computers Computer science Raja Kumaran, Shamini Business intelligence framework using ant colony optimization for feature selection in higher education institution |
description |
Recently, business intelligence (BI) has become an important tool for effective decision-making. BI is a mathematical framework to gain information and knowledge through the process of extracting, transforming, managing, and analyzing data. The demand for accurate knowledge in higher education sector needs a correct technique to extract the exact information for decision-making. However, current BI frameworks and systems lack the ability to transform data into information, and these caused users not to able to fully utilize the BI outcome. This research developed a BI framework for the higher education that is able to explore, analyse and visualize the relevant data into information for use by the top management. This framework identifies the best set of attributes and evaluates the performance of the model with the help of 27 input features. In this case study, the framework used Ant Colony Optimization (ACO) technique mainly to identify the best set of attributes, and the performance was validated using Support Vector Machine (SVM). The framework consists of four layers which are data source, data integration, analytic, and access. Each layer contributes to decision making in terms of processing data, selection of significant features and data visualization. In this study, 46,658 input data were processed for identification of Graduate on Time (GOT) decision in the context of higher education referred as Masters and Doctor of Philosophy (PhD) postgraduates who completed their study within a specified period. The performance evaluation of the data achieved accuracies of 86.44% for PhD and 96.2% for Master’s. Based on the findings, the results showed that the BI dashboard as an output from the framework is capable of providing a good decision-making tool for education management. |
format |
Thesis |
qualification_level |
Master's degree |
author |
Raja Kumaran, Shamini |
author_facet |
Raja Kumaran, Shamini |
author_sort |
Raja Kumaran, Shamini |
title |
Business intelligence framework using ant colony optimization for feature selection in higher education institution |
title_short |
Business intelligence framework using ant colony optimization for feature selection in higher education institution |
title_full |
Business intelligence framework using ant colony optimization for feature selection in higher education institution |
title_fullStr |
Business intelligence framework using ant colony optimization for feature selection in higher education institution |
title_full_unstemmed |
Business intelligence framework using ant colony optimization for feature selection in higher education institution |
title_sort |
business intelligence framework using ant colony optimization for feature selection in higher education institution |
granting_institution |
Universiti Teknologi Malaysia, Faculty of Computing |
granting_department |
Faculty of Computing |
publishDate |
2017 |
url |
http://eprints.utm.my/id/eprint/86987/1/ShaminiRajaKumaranMFC2017.pdf |
_version_ |
1747818518603104256 |