This project is completed as part of a thesis submitted to Deakin University.
I have utilized DS2OS and NSLKDD+ data for analysis of five different classification methods to detect anomalies in network traffic dataset. I have re-implemented method proposed by Hasan et al. (2019) to detect anomalies in IoT sensor network data and NSLKDD dataset. The anomalies in the datasets are cyber attacks. Multinomial classification was predicted in this implementation.
Machine learning techniques used: Logistic Regression, Support vector machine, Decision tree, Random forest classifier, Artificial Neural Network
If you use this work, please refer following authors as well:
Hasan, M, Islam, MM, Zarif, MII & Hashem, MMA 2019, 'Attack and anomaly detection in IoT sensors in IoT sites using machine learning approaches', Internet of Things, vol. 7.