Percorrer por data de Publicação, começado por "2026-03-24"
A mostrar 1 - 2 de 2
Resultados por página
Opções de ordenação
- Predicting Order Activity Sequence Using Contextual Process MiningPublication . Barbeiro, Diogo A.; Martinho, Ricardo F. G.; Ferreira, Carlos J. R.Logistics processes depend heavily on changing conditions and making accurate forecasts is becoming more and more important to preventing delays and/or predict risks. Predictive Process Monitoring has advanced through deep learning and process-mining approaches, yet current methods often lack interpretability and lose accuracy when context varies. Recent research shows that contextual factors can improve predictions, but their integration into transparent, model-driven frameworks remains limited. This article presents a context-aware predictive approach that filters historical event logs by important attributes, discovers process models with the Inductive Miner, and predicts future activities and timestamps using token-based replay and polynomial regression. Experiments with real logistics data show that incorporating context reduces prediction errors, while the use of process mining ensures an interpretable and operationally practical forecasting solution for logistics environments.
- VE4OCPM: An Object-Centric Process Mining Variant Explorer Visualisation ApproachPublication . Gaspar, Marco A. P.; Martinho, Ricardo F. G.; Ferreira, Carlos J. R.This work presents the Variant Explorer, a dual-mode visualisation for Object-Centric Process Mining that reveals control-flow variability and object interactions across process variants, combining object details and subway-map views for intuitive analysis of complex processes. Understanding process variants is essential to detect deviations, exceptions, and improvement opportunities. However, traditional process mining tools assume one case per process instance, which do not work well when events involve multiple objects, such as orders, products, and packages. Existing Object-Centric approaches, like OCπ and Object-Centric Process Analysis (OCPA), introduced models and libraries to support multi-object analysis, but many face technical and usability limitations. To address this gap, this proposal provides two complementary visualisations that show object participation and variant differences side-by-side. Evaluation with real logistics data and user interpretation tests shows that users are able to identify repetitions, skipped activities, deviations, and object interactions clearly. This work offers a practical and interpretable solution for variant analysis in Object-Centric Process Mining (OCPM) and supports better understanding for analysts and business stakeholders.