Abstract
With the increasing number of attacks on computer networks, an attack detection security system is needed that can classify attacks quickly, and can process data on a large scale. One method for processing data on a large scale is data mining. Data mining is a process that uses one or more Machine Learning techniques to analyze and extract knowledge automatically. In the case of research, there are many techniques in data mining that can be used, including classification techniques. Classification is the basic form of data analysis. Decision Tree is one of the well-known techniques in data mining and is one of the most popular methods in the decision-making process of a case where the criteria for entropy, information gain and profit ratio are obtained from the method. This study will discuss data classification using the Decision Tree algorithm, where the data contains logs on firewall and internet traffic control devices used at Firat University Turkey. The data contains 65532 data records with 12 attributes and 4 classes in the action attribute then the data is classified using the Decision Tree algorithm, then processed through RapidMiner version 9.9 and the highest recall results are 100% and the accuracy rate is 99.82% so that the classification model by using the Decision Tree algorithm is better when applied to the dataset.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have