Percorrer por data de Publicação, começado por "2025-12-23"
A mostrar 1 - 2 de 2
Resultados por página
Opções de ordenação
- Teleconsulta de Enfermagem como Estratégia de Follow-up em Utentes com Ferida Traumática: Estudo ComparativoPublication . Rosa, Cátia de Sousa; Bom, Luís Filipe Pereira Todo; Costeira, Cristina Raquel BatistaBackground: Follow-up telenursing is recommended as an effective strategy for reducing hospital admissions and associated costs. A telenursing service was implemented in an outpatient clinic to monitor patients with traumatic wounds. Objective: To compare satisfaction and healthcare utilization among patients with traumatic wounds who received follow-up telenursing and those who did not. Methodology: A descriptive-comparative study was conducted. The experimental group (n = 33) received follow-up telenursing in addition to conventional care, while the control group (n = 35) received conventional care only. The study was conducted between May and July 2022, with data collected via questionnaire and analyzed using SPSS® software. Ethical standards were observed. Results: Males predominated in both groups, with a mean age of 40 years. The experimental group reported higher satisfaction with nursing care and lower use of in-person services (p ≤ 0.05). Conclusion: Telenursing contributed to health improvements, supporting its potential as an effective tool for monitoring patients with traumatic wounds.
- Polymer Melt Stability Monitoring in Injection Moulding Using LSTM-Based Time-Series ModelsPublication . Costa, Pedro; Mendes, Sílvio Priem; Loureiro, PauloThis work presents a data-driven framework for early detection of polymer melt instability in industrial injection moulding using Long Short-Term Memory (LSTM) time-series models. The study uses six months of continuous production data comprising approximately 280,000 injection cycles collected from a fully operational thermoplastic injection line. Because melt behaviour evolves gradually and conventional threshold-based monitoring often fails to capture these transitions, the proposed approach models temporal patterns in torque, pressure, temperature, and rheology to identify drift conditions that precede quality degradation. A physically informed labelling strategy enables supervised learning even with sparse defect annotations by defining volatile zones as short time windows preceding operator-identified non-conforming parts, allowing the model to recognise instability windows minutes before defects emerge. The framework is designed for deployment on standard machine signals without requiring additional sensors, supporting proactive process adjustments, improved stability, and reduced scrap in injection moulding environments. These findings demonstrate the potential of temporal deep-learning models to enhance real-time monitoring and contribute to more robust and adaptive manufacturing operations.