Examinando por Autor "Psaila, Giuseppe"

Mostrando 1 - 3 de 3
  • Miniatura
    Ítem
    Bayesian generation of synthetic datasets for machine-learning tasks: a performance study
    (Elsevier B.V., 2026-03-14) Fosci, Paolo; Nieves Acedo, Javier; Psaila, Giuseppe; Boffelli, Jacopo; García Bringas, Pablo
    Performing Machine Learning (ML) tasks on large-scale datasets, as well as simply storing them for subsequent analysis or for long-term archival, require large computational power. The described approach builds on the technique known as “Bayesian Generation” to produce synthetic datasets in such a way that the probability distribution in the source dataset is maintained as much as possible in the new synthetic ones, even if they are much smaller than the original (large) dataset. In fact, this study investigates the impact of generating smaller synthetic datasets for training ML models in place of the original dataset, adopting a twofold perspective. Firstly, the impact on the effectiveness of ML models trained on these smaller synthetic datasets is assessed. Secondly, the amount of computational resources required to generate the synthetic datasets, train ML models on them, and perform the testing phase is measured. Specifically, both execution time and main memory usage are taken into account. Finally, this research work shows that the loss in terms of effectiveness remains consistently limited and stable, and it identifies the scenarios and ML techniques for which incorporating the generation of small synthetic datasets into the ML pipeline can be beneficial for practical deployment in environments with constrained computational resources, such as mobile or industrial devices.
  • Miniatura
    Ítem
    BlockChain platforms in financial services: current perspective
    (Sciendo, 2020-12-03) García Bringas, Pablo; Pastor López, Iker; Psaila, Giuseppe
    BlockChain technology was invented to support bitcoin, currently the most popular virtual currency. The purpose of this paper is to investigate contemporary BlockChain platforms in financial services. An unstructured literature review has been used. BlockChain in financial services is mostly associated with bitcoin exchange. However, this is a partial view of both BlockChain technology and its possible adoption for financial services: In fact, many BlockChain platforms are now available and many different financial services can be effectively supported by BlockChain platforms, even though they are not based on virtual-money exchange. Furthermore, people are attracted by the concept of smart contract, i.e., a contract that is automatically executed by computer technology, without human intervention. The contribution of this paper is twofold: First of all, we introduce the four BlockChain platforms that are now most popular, discussing how they support the smart contract concept; second, we identify some typical categories of financial services, matching each of them with the platform that provides the best support for each category.
  • No hay miniatura disponible
    Ítem
    Quality assessment methodology based on machine learning with small datasets: industrial castings defects
    (Elsevier B.V., 2021-10-07) Pastor López, Iker; Sanz Urquijo, Borja; Tellaeche Iglesias, Alberto; Psaila, Giuseppe; Gaviria de la Puerta, José; García Bringas, Pablo
    Nowadays there are numerous problems for which use of a multi-objective in image classification would be desirable although, unfortunately, the number of samples is too low. In these situations, higher level classifications could also work (for example, in surface defect detection, it is important to identify the defect, but it could also be useful to detect whether or not the object has a defect). To this end, we present a methodology called BoDoC which allows to improve this classification. To evaluate the methodology, we have created a new dataset, obtained from a foundry, to detect surface errors in casting pieces with 2 different defects: (i) inclusions, (ii) coldlaps and (iii) misruns. We also present a collection of techniques to select featu res from the images. We prove that our methodology improves the direct classification results in real world scenarios, with 91.305% precision.