A carregar...
Publicação
Dados.IPB: Making Research Data Discoverable, Interoperable and Reusable
Autores
Orientador(es)
Resumo(s)
Data is a crucial resource in the Knowledge era, and data repositories are important tools for sharing and preserving it. In open science, it is mandatory to make data repositories easily discoverable and usable across tools to generate big and complex datasets - Big Data.
Machine Learning (ML) uncovers patterns in Big Data and enables, for example, automatic object detection in images for fraud detection. IPB maintains its Research Data Repository (DADOS.IPB1), aggregated with other data repositories. DADOS.IPB metadata are integrated with metadata from other OpenAIRE repositories (via the OAI-PMH protocol). Using a Python script to collect all Croissant metadata files and their respective files from all Dataverse instances worldwide. This article presents a case study of detecting Bactrocera Oleae exemplars in photos using YOLO, achieving high accuracy.
Descrição
Palavras-chave
Dados.IPB Open ccience Metadata Croissant metadata format Machine learning
Contexto Educativo
Citação
Alves, Adília; Pais, Clarisse (2026). Dados.IPB: Making Research Data Discoverable, Interoperable and Reusable. In IV Conferência Internacional de Políticas Públicas e Ciência de Dados: Livro de Resumos Alargados. Bragança: Instituto Politécnico de Bragança. ISBN 978-972-745-371-9
Editora
Instituto Politécnico de Bragança