Article · Azerbaijan Journal of High Performance Computing · December 25, 2019
INTRODUCING A NEW INTRUSION DETECTION METHOD IN THE SDN NETWORK TO INCREASE SECURITY USING DECISION TREE AND NEURAL NETWORK
Ebrahim Zaheri Abdevand, Shamsollah Ghanbari, Zhanat Rysbayevna Umarova, Zhalgasbek Iztayev
Abstract
Computer networks are difficult to use due to the large number of devices such as router, switch, hop, and many sophisticated security management protocols, but in networks defined with integrated management and configuration software, software-based networks are nowadays important.They are high-end and will become one of the most used and important communication tools in the IT world in the future.In these networks, like all other networks, data security and protection is crucial because a network that is not secure will not work, in this paper, we present a new method of intrusion detection in this network, which consists of two parts: training and testing.Looking to determine if the network is normal or not?By checking the output of these two categories, the current status of the network is determined.The proposed method uses decision tree and neural network.In each first class of tree, the classification of abnormal data is classified and in the second class, the norm data is in decision tree.The output of the decision tree is neural network input Shows that the proposed method performs well.
More by Zhanat Umarova
- A HYBRID MACHINE LEARNING APPROACH FOR REAL-TIME FORECASTING OF MINUTE-LEVEL SEISMIC SIGNAL AMPLITUDESVestnik of M Kozybayev North Kazakhstan University · 2026
- An explainable AI approach based on XGBoost for leadership index predictionBulletin of the National Engineering Academy of the Republic of Kazakhstan · 2026
- A PARTIALLY CONTROLLED EVALUATION PROTOCOL FOR TRAJECTORY FORECASTING MODELS: RETHINKING COMPARABILITY IN DEEP LEARNING BENCHMARKSВестник КазАТК · 2026
- AI-TPACK-LX: Reproducible Psychometric AnalysisZenodo · 2026