RT Journal Article
T1 Model-agnostic local explanation: Multi-objective genetic algorithm explainer
A1 Nematzadeh, Hossein
A1 García-Nieto, José Manuel
A1 Hurtado-Requena, Sandro José
A1 Aldana-Montes, José Francisco
A1 Navas-Delgado, Ismael
K1 Programación genética (Informática)
AB Late detection of plant diseases leads to irreparable losses for farmers, threatening global food security, economic stability, and environmental sustainability. This research introduces the Multi-Objective Genetic Algorithm Explainer (MOGAE), a novel model-agnostic local explainer for image data aimed at the early detection of citrus diseases. MOGAE enhances eXplainable Artificial Intelligence (XAI) by leveraging the Non-dominated Sorting Genetic Algorithm II (NSGA-II) with an adaptive Bit Flip Mutation (BFM) incorporating densify and sparsify operators to adjust superpixel granularity automatically. This innovative approach simplifies the explanation process by eliminating several critical hyperparameters required by traditional methods like Local Interpretable Model-Agnostic Explanations (LIME). To develop the citrus disease classification model, we preprocess the leaf dataset through stratified data splitting, oversampling, and augmentation techniques, then fine-tuning a pre-trained Residual Network 50 layers (ResNet50) model. MOGAE’s effectiveness is demonstrated through comparative analyses with the Ensemble-based Genetic Algorithm Explainer (EGAE) and LIME, showing superior accuracy and interpretability using criteria such as numeric accuracy of explanation and Number of Function Evaluations (NFE). We assess accuracy both intuitively and numerically by measuring the Euclidean distance between expert-provided explanations and those generated by the explainer. The appendix also includes an extensive evaluation of MOGAE on the melanoma dataset, highlighting its versatility and robustness in other domains. The related implementation code for the fine-tuned ResNet50 and MOGAE is available at https://github.com/KhaosResearch/Plant-disease-explanation
PB Elsevier
YR 2024
FD 2024
LK https://hdl.handle.net/10630/35359
UL https://hdl.handle.net/10630/35359
LA spa
NO Hossein Nematzadeh, José García-Nieto, Sandro Hurtado, José F. Aldana-Montes, Ismael Navas-Delgado, Model-agnostic local explanation: Multi-objective genetic algorithm explainer, Engineering Applications of Artificial Intelligence, Volume 139, Part B, 2025, 109628, ISSN 0952-1976, https://doi.org/10.1016/j.engappai.2024.109628
NO Funding for open access charge: Universidad de Málaga / CBUA .This work has been partially funded by grants PID2020-112540RB-C41, AETHER-UMA (A smart data holistic approach for context-aware data analytics: semantics and context exploitation) and QUAL21 010UMA (Junta de Andalucía). I
DS RIUMA. Repositorio Institucional de la Universidad de Málaga
RD 23 ene 2026