Published in:   Vol. 11 Issue 1 Date of Publication:   June 2022

Page(s):   5-8 ISSN:   2278-2397

DOI:   10.20894/IJCNES.103.011.001.006 Publisher:   Integrated Intelligent Research (IIR)

• Abstract
• Authors
• Keywords
• Citation
• References

Machine Learning is Agile when it comes to the models performing tasks with greater accuracy without being Programmed explicitly. Network security is becoming more important in today s world of interconnected systems, and it is attracting a lot of fresh research and study. Intrusion Detection Systems (IDS) are crucial for network security. Machine learning algorithms can be used to detect and prevent network assaults to improve network security. The framework is tested using the recently released KDD99 dataset, and it consists of three primary modules: and they are feature extraction, data pre- processing, feature selection and classification of dataset. There are a variety of classifiers that can be used to detect vulnerability or theft. Some are based on trees, such as decision tree. A Decision Tree is very similar to tree-like structure which is made up of nodes which act as a test nodes, vertices show the test s results, and leaf nodes acts as a class label. Among The four decision tree algorithm available, ID3 algorithm is chosen. Iterative Dichotomiser 3 (ID3) is an algorithm that divides features into two or more groups recurcively at each stage. ID3 uses a top-down greedy technique to build a decision tree, resulting in precise results.