IoT, Anomaly Detection, Machine Learning, K-Nearest Neighbors, Random Forest, Real-Time Detection
DOI:
https://doi.org/10.62951/ijies.v1i1.50Keywords:
IoT, Anomaly detection, Machine learning, K-Nearest Neighbors, Random Forest, Real-time detectionAbstract
The increase in connected IoT devices causes increased vulnerability to cyber attacks. This research develops a hybrid machine learning model to detect real-time anomalies in IoT networks. This model combines the K-Nearest Neighbors (KNN) and Random Forest (RF) algorithms to increase accuracy and efficiency. Evaluation was carried out using the UNSW-NB15 dataset to test model performance. The results show that this hybrid approach is able to detect anomalies with high accuracy and a low false positive rate.
References
Ahmed, M., Mahmood, A. N., & Hu, J. (2016). A survey of network anomaly detection techniques. Journal of Network and Computer Applications, 60, 19–31. https://doi.org/10.1016/j.jnca.2015.11.016
Alzubaidi, L., et al. (2021). A survey on hybrid machine learning techniques for anomaly detection in IoT networks. Journal of Information Security and Applications, 57, Article 102688. https://doi.org/10.1016/j.jisa.2020.102688
Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5–32. https://doi.org/10.1023/A:1010933404324
Cybersecurity Ventures. (2021). Cybercrime damages $10.5 trillion by 2025. Retrieved from https://cybersecurityventures.com
Hodge, V. J., & Austin, J. (2004). A survey of outlier detection methodologies. Artificial Intelligence Review, 22(2), 85–126. https://doi.org/10.1023/B:AIRE.0000045509.59114.01
Statista. (2021). Number of connected IoT devices worldwide from 2019 to 2030. Retrieved from https://www.statista.com/statistics/1183457/iot-number-of-connected-devices-worldwide/
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2024 International Journal of Information Engineering and Science
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
