eXAI: uma técnica inovadora de ensemble com inteligência artificial explicável aplicada à visão computacional em contextos críticos

• Ano de defesa: 2025
• Autor(a) principal: Neves, Miguel Jose das [UNESP]
• Tipo de documento: Tese
• Tipo de acesso: Acesso aberto
• Idioma: por
• Instituição de defesa: Universidade Estadual Paulista (Unesp)
• Palavras-chave em Português: Aprendizagem profunda (aprendizado do computador); Inteligência artificial; Redes neurais; Explainable artificial intelligence (XAI); Ensemble learning; Diabetic retinopathy
• Link de acesso: https://hdl.handle.net/11449/314259

The growing complexity of Deep Learning models, particularly Convolutional Neural Networks (CNNs), presents a fundamental challenge in critical applications: the opacity of their decisionmaking processes. This thesis addresses this interpretability gap by proposing and validating a methodological framework termed eXAI (Ensemble Explainable Artificial Intelligence), designed to create image analysis systems that merge high predictive performance with transparency. Conceptually inspired by Ensemble Learning, the framework’s novelty lies not in combining predictive models, but in synergistically integrating an ensemble of explainability methods specifically combining SHAP for pixel-level attribution with Grad-CAM for region-level localization to provide a multi-faceted interpretation of a single model’s decisions. The framework’s flexibility and efficacy are demonstrated through two case studies in distinct domains. The first, focused on Diabetic Retinopathy diagnosis, implements a stacking architecture that integrates deep visual features from a CNN with structured clinical data, classified by a LightGBM (LGBM) meta-model. This multimodal approach achieved outstanding accuracy, while the XAI analysis validated the clinical relevance of its decision factors. The second case study, in digital forensics, applies a direct classification CNN to detect Seam Carving image manipulations. Here, XAI was crucial in revealing that the model learned to identify subtle structural distortion artifacts rather than relying on semantic content. The collective results demonstrate that the eXAI framework is a robust and adaptable approach for building trustworthy AI models for critical contexts. By delivering comprehensive and understandable explanations, this methodology enhances the confidence in, and practical utility of, artificial intelligence in both healthcare and information security.