Model of security level classification for data in hybrid cloud computing

Shakir, Mohanaad and Asmidar, Abubakar and Yousoff, Younus and Waseem, Mohammed and Al-Emran, Mostafa (2016) Model of security level classification for data in hybrid cloud computing. Journal of Theoretical and Applied Information Technology, 94 (1). pp. 133-141. ISSN 1992-8645 (print); 817-3195 (online). (Published)

Pdf (Open access)
Model of security level classification for data in hybrid.pdf
Available under License Creative Commons Attribution Non-commercial No Derivatives.

Download (2MB) | Preview


Organizations mainly rely on data and the mechanism of dealing with that data on cloud computing. Data in an organization has multi security levels, which is classified depending on nature of the data, and the impact of data on the organization. The security procedures which used for protecting data usually be complicated, and it had a direct and indirect influence on the usability level. This study aims to establish a model which has an ability to classify data dynamically according to the security form low till high levels. The security level classified it into five levels based on the policies and classification method. The purpose of classification is to apply a complex security procedure on data which has a high security level larger than data which has a low security level. It also has a potential to segregation an illegal data from the legal to support usability in system. Finally, several experiments have been conducted to evaluate the proposed approaches. Several experiments have been performed to empirically evaluate two feature selection methods (Chi-square (χ2), information gain (IG)) and five classification methods (decision tree classifier, Support Vector Machine (SVM), Naïve Bayes (NB), and K-Nearest Neighbor (KNN) and meta-classifier combination) for Legal Documents Filtering The results show that all classifiers perform better with the information gain feature selection methods than their results with Chi-Square feature selection method. Results also show that Support Vector Machine (SVM) outperforms achieve the best results among all individual classifiers. However, the proposed meta-classifiers method achieves the best results among all classification approaches.

Item Type: Article
Additional Information: Indexed by Scopus
Uncontrolled Keywords: Information system security; Classification of data; Big data; Neural language processing
Subjects: Q Science > QA Mathematics > QA76 Computer software
Faculty/Division: Faculty of Computer System And Software Engineering
Institute of Postgraduate Studies
Depositing User: Mrs Norsaini Abdul Samat
Date Deposited: 07 Nov 2022 08:16
Last Modified: 07 Nov 2022 08:16
Download Statistic: View Download Statistics

Actions (login required)

View Item View Item