Percorrer por data de Publicação, começado por "2026-03-24"
A mostrar 1 - 4 de 4
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.
- Validation of the Arabic-Language Version of the Laune-Slade Hallucinations Scale-Extended (LSHS-E) in Young General Population AdultsPublication . Fekih‐Romdhane, Feten; Marrakchi, Salma; Laranjeira, Carlos; Ghrissi, Farah; Cheour, Majda; El Haj, Mohamad; Hallit, Souheil; McGorry, Patrick DBackground: To date, no validated Arabic version of the Laune- Slade Hallucination Scale (LSHS) has been reported, and this scale has not been used in any Arab countries including Tunisia. This study has as main goal to investigate the psychometric reliability and validity of the Arabic version of the extended version of the LSHS (LSHS- E) scores in a Tunisian sample. Methods: Cross- sectional data were collected from April 2025 to June 2025. Our target population consisted of 416 young adults aged 18–35 years. The forward–backward translation methodology was followed to obtain the Arabic version of the LSHS- E. The Arabic LSHS- E was tested against the Prodromal Questionnaire- brief for convergent validity and for other relevant measures for concurrent validity of the scores. Confirmatory factor analysis was used to estimate construct validity indicators. Results: Findings showed that up to 93.3% of our sample endorsed at least one of the hallucination experiences. Fit indices showed that the four- factor solution determined by previous factorial studies fitted the data well. Besides, the psychometric equivalence of the LSHS- E between sex groups has been tested and verified at the metric, scalar, and configural levels. No differences in the intensity of hallucinatory experiences between males and females were found. As expected, results revealed that individuals with greater levels of hallucinatory experiences were more likely to admit having endorsed positive psychotic experiences. Finally, higher LSHS- E scores were associated with greater depression, anxiety, lower sleep quality, and more suicidal ideation. Conclusion: Our findings provide the first evidence supporting the reliability and validity of the Arabic version of the LSHS- E scores for assessing hallucinatory experiences in the Tunisian community population. The scale can benefit clinicians by helping them to timely and successfully detect people at risk for or experiencing hallucinations. Researchers and policymakers developing prevention programs could make use of the scale when designing and implementing hallucination prevention strategies to ensure their effectiveness and cultural appropriateness.
- Quality of life after preoperative home-based exercise training in patients with lung cancer: a secondary analysisPublication . Pimenta, Sara; Machado, Pedro; Silva, Cândida G.; Garcia, Ana Luís; Nogueira, Tiago; Silva, Sónia; Santos, Claúdia Lares dos; Martins, Maria Vitória; Canha, André; Oliveiros, Bárbara; Martins, Raul A.; Cruz, JoanaBackground: A preoperative home-based exercise training (PHET) program appeared to improve health-related quality of life (HRQoL) in patients undergoing lung cancer surgery. However, inter-individual variability in response was observed. This secondary analysis aimed to identify characteristics of responders/non-responders to PHET, determine predictors of response, and examine whether preoperative HRQoL response to PHET is associated with postoperative HRQoL maintenance. Methods: This was a secondary analysis of pooled data from a feasibility study and a randomized controlled trial, including sociodemographic/clinical data, physical performance and HRQoL (EORTC-QLQ-C30). Responders/non-responders were classified based on a change of ≥5 points in Global QoL score (EORTC QLQ-C30) from baseline to pre-surgery time point. Between-group differences and predictors of PHET response (logistic regression) were analysed. Results: 32 patients (63% male, 67.1±7.8 years) were included, from which 56% (n=18) were responders to PHET in Global QoL. Responders had lower baseline scores in Global QoL, Emotional Function and Summary Score compared to non-responders (P<0.05), and 50% of responders had chronic obstructive pulmonary disease (COPD) (P=0.02). No other between-group differences were found (P>0.05). In the regression model including the Summary Score (EORTC-QLQ-C30) and COPD (Nagelkerke R2=0.511), COPD was a significant predictor of response: COPD patients were 13.4 times more likely to be responders (odds ratio =13.4; 95% confidence interval: 1.4; 132.2). 65% of PHET-responders maintained/improved HRQoL 1-month post-surgery. Conclusions: Most patients awaiting lung cancer surgery responded in HRQoL to a PHET, however, a considerable proportion did not. Further research is needed to identify characteristics of non-responders and optimize prehabilitation strategies accordingly.