An explainable log-driven maintenance pipeline utilizing a sentiment-aware BERT model and SHAP to prioritize subsystem maintenance at the Paranal Observatory.
An automated scheduling algorithm, PULSAR, that integrates uncertainty-aware lookahead and adaptive rebalancing to dynamically schedule observations at ALMA.
An interpretable, sentiment-aware transformer model (BERT-ITPT-FiT) combined with SHAP for parser-free, word-level explainable anomaly detection in individual log entries.
Una introducción moderna y aplicada a los fundamentos y herramientas de la ciencia de datos, combinando análisis estadístico, programación y visualización.
Protecting natural ecosystems requires monitoring approaches that work as early warning systems to avoid degradation and protect biodiversity. However, separating forest disturbance causes in change-detection pipelines is challenging due to the …