Main Article Content

Abstract

Technology plays a crucial role in agriculture, and with the Internet of Things (IoT), it has evolved into smart agriculture. The use of this technology for smart farming is increasing worldwide as it provides reliable information about farms, leading to enhanced productivity and the conservation of water and other resources. However, smart farming also faces challenges such as high costs, dependence on technology, and network security, with network and information security in IoT agriculture being among the most critical concerns. One common issue is Distributed Denial of Service (DDoS) attacks, which pose a significant threat to IoT agriculture networks. A DDoS attack in IoT generally refers to the temporary or permanent disruption or suspension of services to a host connected to the IoT agriculture network. This makes the intelligent farming network inaccessible, causing substantial damage to farms and fields. This paper presents a proposed combined method based on deep learning using the RapidMiner program for more accurate classification and detection of attacks in IoT agriculture networks. The proposed method integrates deep learning, Decision Tree, and K-nearest neighbors (KNN) algorithms. The results show that the proposed method performs exceptionally well, achieving an accuracy of 99.82% and an error rate of 0.18%.

Keywords

Agriculture Smart agriculture Smart farming Technology

Article Details

How to Cite
Hassand, A. M. (2024). Detection of DDoS Attacks in Smart Agriculture Based on Deep Learning. Journal of Natural Sciences – Kabul University, 7(Special.Issue), 75–89. https://doi.org/10.62810/jns.v7iSpecial.Issue.91

References

Read More