Publication Details
Overview
 
 
Ahmed Amamou, , Bilal Ben Mahria, Younes Balboul, Said Hraoui, Omar Hegazy, Abdellah Touhafi
 

Contribution to journal

Abstract 

Agricultural Internet of Things (Agri-IoT) systems need strong anomaly detection to monitor crops effectively. However, current approaches lack accuracy and efficiency. To mitigatethis problem, we proposed an advanced hierarchical ensemble framework with neural network fusion and uncertainty quantification (AHE-FNUQ). This framework combinessix detection algorithms: Isolation Forest, ECOD (empirical cumulative distribution-based outlier detection), COPOD (copula-based outlier detection), HBOS (histogram-based outlierscore), OC-SVM (one-class support vector machine), and KNN (k-nearest neighbors). It uses a three-level decision process: (1) selecting models with good performance (ROCAUC > 0.75), (2) applying recall-weighted ensemble fusion, and (3) using a fusion neural network (FusionNN) to improve uncertain predictions in the confidence range [0.75, 0.9].The framework was tested on three agricultural datasets with contamination levels between 10% and 50%. The result showed strong performance: ROC AUC between 0.93 and 0.99,PR AUC between 0.90 and 0.98, and F1-scores between 0.85 and 0.90. Moreover, we have conducted a statistical test (Friedman test, χ2 = 63.02, p < 0.0001) and confirmed thatAHE-FNUQ is significantly better than common methods such as COPOD, ECOD, HBOS, Isolation Forest, and KNN.

Reference