Abstract

Abstract

Abstract
This study explores models for synthetic data generation of time series. In order to improve the achieved results, i.e., the data generated, new ways of improvement are explored and different models of synthetic data generation are compared. The model addressed in this work is the Generative Adversarial Networks (GANs), known for generating data similar to the original basis data through the training of a generator. The GANs are applied using the datasets of Quinta de Santa Barbara and the Pinhao region, with the main variables being the Average temperature, Wind direction, Average wind speed, Maximum instantaneous wind speed and Solar radiation. The model allowed to generate missing data in a given period and, in turn, enables to analyze the results and compare them with those of a multiple linear regression method, being able to evaluate the effectiveness of the generated data. In this way, through the study and analysis of the GANs we can see if the model presents effectiveness and accuracy in the synthetic generation of meteorological data. With the proper conclusions of the results, this information can be used in order to improve the search for different models and the ability to generate synthetic time series data, which is representative of the real, original, data.

Abstract
This paper proposes a novel and comprehensive framework for the integration of manufacturing management processes, spanning strategic and operational levels, within and across organizational boundaries. The framework combines a robust set of technologies-such as cyber-physical systems, digital twins, AI, and blockchain-designed to support real-time decision-making, interoperability, and collaboration in Industry 4.0 and 5.0 contexts. Implemented and validated in a Portuguese manufacturing group comprising three interoperating factories, the framework demonstrated its ability to improve agility, coordination, and stakeholder integration through a multi-layered architecture and modular software platform. Quantitative and qualitative feedback from 32 participants confirmed enhanced decision support, operational responsiveness, and external collaboration. While tailored to a specific industrial setting, the results highlight the framework's scalability and adaptability, positioning it as a meaningful contribution toward sustainable, human-centric digital transformation in manufacturing environments.

Abstract
The Laplacian learning method has proven effective in classical graph-based semi-supervised learning, yet its quantum counterpart remains underexplored. This study systematically evaluates the Laplacian-based quantum semi-supervised learning (QSSL) approach across four benchmark datasets-Iris, Wine, Breast Cancer Wisconsin, and Heart Disease. By experimenting with varying qubit counts and entangling layers, we demonstrate that increased quantum resources do not necessarily lead to improved performance. Our findings reveal that the effectiveness of the method is highly sensitive to dataset characteristics, as well as the number of entangling layers. Optimal configurations, generally featuring moderate entanglement, strike a balance between model complexity and generalization. These results emphasize the importance of dataset-specific hyperparameter tuning in quantum semi-supervised learning frameworks.

Abstract