Assembly Classifier Approach to Analyze Intrusion Detection Dataset in Networks by Using Data Mining Techniques
Journal: International Journal of Science and Research (IJSR) (Vol.4, No. 4)Publication Date: 2015-04-05
Authors : Ayad Mohammed Mahyoub Ghaleb; Samani A. Talab;
Page : 742-748
Keywords : Intrusion Detection; Intrusion Detection System IDS; Probe attacks; Dos Denial of Service attacks; R2L Remote to Local attack; U2R User to Root attack; Weka; NLS-KDD 99 data set;
Abstract
The Intrusion Detection system analyzes network traffic to detect the attacks. The attack detection methods used by these systems are of two types anomaly detection and misuse detection methods. Intrusion detection is a type of security management system for computer networks. An Intrusion detection system analyzes information within a computer network to identify possible security breaches, which include both anomaly and misuse. In this paper I studied the performance of number of data mining algorithms and chose best three algorithms for building multi classifier from decision tree classifier, nave Bayes classifier and Multilayer Perceptron classifier. I evaluated performance classifier by account accuracy and error rate.
Other Latest Articles
- Comparative Analysis of Some Encryption Algorithms and Secured Remote Protocol
- A Review of Carrier Based Modulation Techniques
- A Mathematical Skew-Logistic Model for G-Flip is An Effective Treatment for Chemotherapy Refractory Metastatic Pancreatic Cancer
- Use of Geoinformation Technology in Assessing Nexus between Ecosystem Changes and Wildlife Distribution: A Case Study of Mt. Marsabit Forest
- Enhanced MIMO Based Anti-Jamming Technique in Wireless Networks
Last modified: 2021-06-30 21:44:39