Network Intrusion Detection using Hybrid Machine Learning
- Resource Type
- Conference
- Authors
- Chuang, Po-Jen; Li, Si-Han
- Source
- 2019 International Conference on Fuzzy Theory and Its Applications (iFUZZY) Fuzzy Theory and Its Applications (iFUZZY), 2019 International Conference on. :1-5 Nov, 2019
- Subject
- Computing and Processing
Engineering Profession
General Topics for Engineers
Power, Energy and Industry Applications
Robotics and Control Systems
Signal Processing and Analysis
Machine learning algorithms
Clustering algorithms
Classification algorithms
Training
Mathematical model
Intrusion detection
Predictive models
machine learning
network intrusion detection
trained classification models
performance and time evaluation
- Language
- ISSN
- 2377-5831
A hybrid machine learning algorithm used to combine two different machine learning algorithms, with the purpose of exploiting their advantages to mend the loopholes in each original design and so to achieve better performance over each individual algorithm. This paper presents a new hybrid machine learning algorithm which combines two existing algorithms - Naive Bayes and C4.5 - to improve both the trained classification model performance and training time in network intrusion detection. As experimental results show, in contrast to other hybrid machine learning algorithms, our proposed algorithm is able to shorten the needed training time and meanwhile yields desirable detection performance.