Answers are grounded in this paper and cite their sources.
Demonstrates enhanced intrusion detection in smart agriculture, suggesting a robust security solution.
Internet of Things (IoT) technologies in smart agriculture have enhanced monitoring,automation, and decision-making, but also present major security challenges, including DDoS,spoofing, and data injection attacks. Such threats are especially hard to identify because thedata related to the IoT networks is highly imbalanced, with instances of attacks beingunderrepresented. In dealing with this, the paper suggests an Adaptive Focal Loss-basedExtreme Gradient Boosting (AFL-XGB) framework to the efficient intrusion detection in IoTbased farm setups. The model uses a dynamically scaled focal loss term that maximizesminority attack detection and minimizes false negatives, increasing generalization as comparedto traditional methods. Further, selective blockchain record mechanism is proposed where onlyhigh-confidence benign information is stored, which reduces storage overhead and maintainsdata integrity and trust to distributed systems. Experimental results through the Farm-Flowdataset illustrate that the proposed model is able to achieve a higher performance, with 96%accuracy, 94.5% F1-score, and 0.97 AUC in comparison to the traditional models of SVM,Random Forest, and the default XGBoost. Another advantage of the framework is that itminimizes the blockchain storage overhead. Altogether, the proposed AFL-XGB system offersa scalable, secure and efficient intrusion detection solution to smart agriculture IoT systems.
No takes yet. Share an insight, caveat, or question.
SR Ajitha (2026) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: