This study addresses the challenge of monitoring oxide layer formation in 1045 steel, a critical issue affecting mechanical properties and phase stability during high-temperature processes (900 °C). To tackle this, an image processing algorithm was developed to detect and segment regions of interest (ROIs) in oxidized steel surfaces, utilizing infrared thermography as a non-contact, real-time measurement technique. Controlled heating experiments ensured standardized data acquisition, and the algorithm demonstrated exceptional accuracy with performance metrics such as 96% accuracy and a Dice coefficient of 96.15%. These results underscore the algorithm’s capability to monitor oxide scale formation, directly impacting surface quality, thermal uniformity, and material integrity. The integration of thermography with machine learning techniques enhances steel manufacturing processes by enabling precise interventions, reducing material losses, and improving product quality. This work highlights the potential of advanced monitoring systems to address challenges in industrial steel production and contribute to the sustainability of advanced steel materials.

Weather disturbances pose a significant challenge when estimating the energy production of photovoltaic panel systems. Energy production and forecasting models have recently been used to improve energy estimations and maintenance tasks. However, these models often rely on environmental measurements from meteorological units far from the photovoltaic systems. To enhance the accuracy of the developed model, a measurement Internet of Things (IoT) prototype was developed in this study, which collects on-site voltage and current measurements from the panel, as well as the environmental factors of lighting, temperature, and humidity in the system’s proximity. The measurements were then subjected to correlation analysis, and various artificial neural networks (ANNs) were implemented to develop energy estimations and forecasting models. The most effective model utilizes lighting, temperature, and humidity. The model achieves a root mean squared error (RMSE) of 0.255326464. The ANN models are compared to an MLR model using the same data. Using previous power measurements and actual weather data, a non-autoregressive neural network (Non-AR-NN) model forecasts future output power values. The best Non-AR-NN model produces an RMSE of 0.1160, resulting in accurate predictions based on the IoT device.

This study presents a pioneering approach, integrating infrared thermography and deep learning to analyse surface oxide layers on AISI 1045 steel, addressing the critical need for advanced monitoring in steelmaking processes. Using thermography for observation and semantic segmentation for accurate identification, 50 tests between 200 and 700 °C were analysed in a Joule-controlled heating system to study the formation and thickening of oxide layers on steel surfaces. A convolutional neural network (CNN), specifically SegNet, was trained for semantic segmentation, facilitating detailed analysis. The model achieved an overall accuracy of 96.40% in identifying the presence of oxide. By quantifying pixelation changes, relationships in oxide evolution kinetics were obtained, and by quantifying the activation energy in isothermal cases, the magnitude is in the range reported by other works. The approach also highlighted the potential for non-destructive monitoring and control on a large scale without compromising personnel safety. This potential could improve industrial process control, predict surface quality or provide data relevant to sub-processes.

Medical questionnaires and forms play a crucial role in diagnosing diseases and gathering essential patient information. Traditionally, these assessments are conducted through face-to-face interactions or phone calls, which can be time-consuming, costly, and inefficient. To address these challenges, digital adaptations of medical questionnaires have been developed, enabling faster and more accessible data collection across various platforms and applications.ResearchKit, an open-source framework introduced by Apple, allows researchers and developers to create robust mobile applications for medical research. By leveraging this technology, large-scale data collection can be conducted efficiently, facilitating real-time analysis while reaching a broader population. The availability of extensive datasets is essential for computational techniques such as Machine Learning, which require significant amounts of data for classification, pattern recognition, and predictive modeling in healthcare.This paper focuses on the digitization of medical questionnaires, specifically the International Physical Activity Questionnaire (IPAQ) and the Mini-Mental State Examination (MMSE), using ResearchKit. The transition from paper-based to digital forms significantly improves the efficiency of medical assessments, allowing healthcare professionals to analyze results remotely and optimize patient diagnosis and treatment plans. The findings emphasize the impact of digital health solutions in advancing medical research, reducing costs, and enhancing the accuracy and scalability of data-driven healthcare applications.