• Mar 31, 2020 News!Vol.9, No.1 has been published with online version.   [Click]
  • Dec 25, 2019 News!Vol.8, No.4 has been published with online version.   [Click]
  • Jul 16, 2019 News!The papers published in Vol.8, No.1-No.2 have all received dois from Crossref.
General Information
    • ISSN: 2010-3751 (Print)
    • Frequency: Quarterly
    • DOI: 10.18178/IJFCC
    • Editor-in-Chief: Prof. Mohamed Othman
    • Executive Editor: Ms. Cherry L. Chan
    • Abstracting/ Indexing: Crossref, Electronic Journals LibraryEI (INSPEC, IET), Google Scholar, EBSCO, etc.
    • E-mail:  ijfcc@ejournal.net 
Editor-in-chief
Prof. Mohamed Othman
Department of Communication Technology and Network Universiti Putra Malaysia, Malaysia
It is my honor to be the editor-in-chief of IJFCC. The journal publishes good papers in the field of future computer and communication. Hopefully, IJFCC will become a recognized journal among the readers in the filed of future computer and communication.
IJFCC 2019 Vol.8(4): 134-141 ISSN: 2010-3751
DOI: 10.18178/ijfcc.2019.8.4.555

Evaluation of a Bayesian Machine Learning –Based and Regression Analysis -Based Performance Prediction Model for Computer Networks

Akinyemi Bodunde.O., Aladesanmi Temitope.A., Oyebade Adedoyin.I., Aderounmu Ganiyu.A, and Kamagaté Beman.H.
Abstract—This study accessed the operation of the purported Bayesian Network machine learning-based prediction model for network performances in the face of security risks. This was with a view to predetermine the effect of network security risk factors on the network Confidentiality, Integrity, and Availability. The performance of the proposed BN prediction model was benchmarked with the existing Regression Analysis (RA) prediction model using Prediction Accuracy, Reliability, and Availability as the evaluation measures of the model performance. The simulation result proved that the prediction accuracy of the Bayesian Network model is higher in all the measures, the reliability is high, but the availability rate is relatively lower. The results showed that the proposed model is able to obtain better effectiveness in optimizing the network performances by gathering information about the inherent network risks to deliver the higher prediction accuracy, higher reliability, and relative availability. This implied that the BN scheme is a robust computational scheme that improves the capabilities properties of the prediction model despite its computational complexity as compared to the RA model. It was concluded that the proposed prediction model measures the security risk quantitatively and predicts network performances using objectives metrics and eventually improves the overall network performance efficiencies.

Index Terms—Bayesian network, computer networks, prediction model, regression analysis, machine learning.

Akinyemi Bodunde.O., Oyebade Adedoyin.I., and Aderounmu Ganiyu.A. are with Department of Computer Science and Engineering, Obafemi Awolowo University, Ile-Ife Nigeria (e-mail: bakinyemi@oauife.edu.ng, sacnet2010@yahoo.com, gaderoun@oauife.edu.ng).
Aladesanmi Temitope.A. is with INTECU, Obafemi Awolowo University, Ile-Ife Nigeria (e-mail: taladesanmi@oauife.edu.ng).
Kamagaté Beman.H. is with Laboratoire LARIT- Cocody Danga Abidjan, Cote D’ivoire (e-mail: beman2017@gmail.com).

[PDF]

Cite: Akinyemi Bodunde.O., Aladesanmi Temitope.A., Oyebade Adedoyin.I., Aderounmu Ganiyu.A, and Kamagaté Beman.H., "Evaluation of a Bayesian Machine Learning –Based and Regression Analysis -Based Performance Prediction Model for Computer Networks," International Journal of Future Computer and Communication vol. 8, no. 3, pp. 134-141, 2019.

Copyright © 2008-2020. International Journal of Future Computer and Communication. All rights reserved.
E-mail: ijfcc@ejournal.net