Explainable Hybrid Machine Learning for Autonomous Optimization of Network QOS in Cyber Security
DOI:
https://doi.org/10.59992/IJCI.2026.v5n4p5Keywords:
Network Performance Analysis, Network Traffic Predication, Performance Optimization, Throughput Optimization, Real-Time Monitoring, Feature Selection, Predictive Modelling, Network Delay Analysis, Intelligent Network Management, Weka ToolAbstract
Cyber Security is a smart defence strategy that uses advanced artificial intelligence as a shield. Artificial Intelligence (AI) and Machine Learning (ML) enhance cyber security by enabling faster and more accurate threat detection, automated responses and adaptive defence system that learn from data. Network security on the other hand, involves protecting, monitoring and controlling the network infrastructure and the data transmitted across it.
In this study predictive analysis was performed to classify network threats based on key performance metrics such as band width, latency response time and jitter. The network data set consisted of 1000 instances and 5 attributes to evaluate the classification performance; several data mining algorithms namely Naive Bayes, IBK, SMO, Logistic, and Random Tree were implemented using the WEKA data mining tool.
The experimental results indicate that the Random Tree classified achieved the best performance compared to the other algorithms. The accuracy obtained by the five algorithms was as follows (Random Tree 99.8%) IBK (95.9%) Naive Bayes (94.8%) Logistic Regression (87.9%) and SMO (87.7%). These findings demonstrate that the Random Tree model provides superior predictive capability for network threat detection. The confusion matrix analysis indicates that the proposed model has a strong capability to correctly identify attack traffic. With minimal misclassification. The model also demonstrates reliable performance in distinguishing between warning and normal network states. These results confirm it effectiveness in detecting real time performance degradation and identifying potential network threats. The evaluation process includes measuring model accuracy to determine the effectiveness of the classification results. The findings indicate that machine learning based approaches significantly improve network monitoring performance and enhance cyber security decision making processes. These results demonstrate the importance of predictive models in identifying network anomalies and supporting proactive threat mitigation strategies.
References
[1] Nguyen T.T.T & Armitage, G (2008 A survey of techniques for internet traffic classification using machine learning IEEE communications surveys &Tutorials,10(4),56-76
[2] Call ado, A, Kamienski, C, Szabo, G, Keiner, J, Fern Andes, S, & Sadok, D (2009) A survey on internet traffic identification IEEE Communications surveys &Tutorials,11(3),37-52
[3] Moore, A. W & Papagi Annaki, K (2005). Toward the accurate Identification of network applications passive and active Measurement conference (PAM).
[4] Witten I.H, Frank, E & Hall, M.A(2011) data mining: practical Machine learning tools and techniques. Morgan Kaufman.
[5] Said, A, Hmed, M& Mohammed E (2020) challenges in Building SDN dataset for machine learning A comprehensive survey. Journal of information security and Application ,50, 102-513 HTTp://DOI.Org/10.1016/I.Jisa 2020 102513
[6] Kumar, P, Kumar, R, &Singh A (2020) statistical Approaches for Dodos Detection in SDN International Journal of computer Networks and communication,12(2),1-16. HTTPS://DOI.Org/10.5121/’’IJcnc.2020.12201
[7] Lakshmanan R. ETAI (2018) Militating DOS Attacks in SDN International Journal of cybersecurity, (29) (1),33-50.
[8] Ram Kumar, S, K Umar, S, &Thomas, G. (2020). An Entropy Based Approach for Detecting Dodos Attacks in SDN Environments-computers &security, 92,101-118 HTTP://DOI.Org/10.1016/J Cose 2020-101826
[9] Iman Sharafaldin, Arash Habibi Lashkari, and Ali A. Ghorbani. Toward generating anew intrusion detection dataset and trusion traffic characterization. International conference on information science and security vol I, pp.108-116, funchal, Madeira Portugal, Jan.2018
[10] Amirhossein Gharib, Iman sharafaldin, Arash HabibiLashkari, and Ali a Ghorbani. An evaluation framework for intrusion detection dataset. IEEE international conference on information science and security.PP.1-6, pattaya, Thail and, Dec.2016
[11] Almseidin Mohammad, Maen Alzubi, Szilveszter Kovacs, and Mouhammad Alka _sassbeh. Evaluation of machine learning algorithms for intrusion detection system IEEE international symposium on intelligent systems and informatics.PP.277-282, Subotica, Serbia, sep.2017
[12] Prachi Chaudhary. Usage of machine learning for intrusion detection in a network international Journal of computer network and applications. Vol .3, no.6, PP.139-147, Now.Dec.2016
[13] Sommer, R, & Paxson, V (2010) outside the closed world on using machine learning for network intrusion detection IEEE symposium on security and privacy.
[14] Buczak, A.L., &Guven, E (2016) A. survey of datamining and machine learning methods for cybersecurity intrusion detection IEEE communication surveys &Tutorials 18(2) ,1153-1176
[15] Ahmad, 1, Basheri, M, 19bal, M. J, &Rahim, A. (2018) performance comparison of support vector machine, random forest, and extreme learning machine for intrusion detection IEEE Access ,6,33789-33795
[16] Lippmann, R.P.et al (2000) Evaluating intrusion detection systems. The 1998 DARPA of line intrusion detection Evaluation DARPA information survivability conference and Exposition Mustafa, N, &slay, J. (2015) UNSW –NB15: A comprehensive dataset for network intrusion detection systems. Military communication and information systems conference (MIKIS)
[17] Kim, G, Lee, S & Kim, S (2016) A novel hybrid intrusion detection methods integrating anomaly detection with misuse detection. Expert systems with applications ,41(4) ,1690-1700. Andrews. Tanenbaum &David J Wetherall computer networks ,5thed, Pearson, 2011.international telecommunication (ITU), “Quality of service (QOS) standards” ITU-T Recommendations IEEE Research publications on network traffic analysis and anomaly detection.
[18] AI-Yassen, W. L, Othman, Z, A & AI-Yassen, W. L (2017). An intelligent intrusion detection system based on support vector machine and information selection by filter approach the scientific world journal.
[19] Vinayakumar, R, so man, K. P, & poornachandran, P (2019) applying deep learning models for network traffic classification. Computers & Electrical Engineering.
[20] Raff, E, Barker, J. sylvesteer, J, Brandom, R, L, catan zaro, B, & Nicholas, C (2018) Malware detection by eating a whole exe. workshops at the thirty second AAAI conference on Artificial intelligence.
[21] A. Elsharif Karrar,” The use of case-based Reasoning in acknowledge –based (learning) software development organization,” international journal of Innovative Research in science, Engineering and Technology (An Iso, Vol.3297, no.5,2007, doi:10.15680 /IJIRSET.2016.0505331.
[22] I. Chakraborty and A.K. Chakraborty,” super-ensemble classifier for improving predications in imbalanced dataset,” commun state case stud data Anal Appl, PP.1-19, Nov2020, doi :10.1080 /23737484.2020.1740065
[23] “A Review on Data Mining Techniques for Treatment of cancer in Ayurveda Therapy.” [Online]. Available: WWW.IJcset.net
[24] A.E. Karrar, “The Effect of using Data Pre –Processing by Imputation in Handling Missing Values” Indonesian journal of Electrical Engineering and Informatics (IJEEI), Vol .10, no, 2, Apr.2022, doi :10. 525491ijeei.v 10i 2.3730
[25] S. Faroo9 Mohi-U-din, M. Tari9 and A. Tari9, Deep dive in to health: Harnessing AI and deep learning for brain and heart care” International Journal of Advanced Engineering Technologies and Innovations, Vol. I, no.4, PP.248-267, 2024.Available from: HTTPS://ijaei.com/index.php/journal / article /view /272
[26] M. Tari9, Y. Hayat, A. Hussain, A. Tari9, and S. Rasooi,” principles and perspectives in medical diagnostic systems employing artificial intelligence (AI) algorithms,” international Research Journal of Economics and Management studies, vol. 3, no. 1, 2024. Available form: HTTPS://WWW.journal.mediapublikasi.id/index.php/bullet/article/view/4094
[27] S.K. Lodhi, A. Y. Gill and H.K. Hussain,” Green innovations: Artificial intelligence and sustainable materials in production, “BULLET: journal Multidiscipline ILmu Vol.3, no .4, pp.492-507, 2024.Available from: HTTPs://Journal.mediapublikasi.id/index.php/bullet/article view 4474
