Óscar Oliveira

Dr. Óscar Oliveira

Computer Science, Escola Superior de Tecnologia e Gestão, Felgueiras, Porto, Portugal
orcid

Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
17 November 2022 in International Transactions in Operational Research
Verified
Journal Article
Open access
Óscar OliveiraÓscar Oliveira
Óscar Oliveira
DGDorabela Gamboa
Dorabela Gamboa
ESElsa Silva
Elsa Silva
Cutting and packing problems have been widely studied in the last decades, mainly due to the variety of industrial applications where the problems emerge. This paper presents an overview of the solution approaches that have been proposed for solving two‐dimensional rectangular cutting and packing problems. The main emphasis of this work is on two distinct problems that belong to the cutting and packing problem family. The first problem aims to place onto an object the maximum‐profit subset of items, that is, output maximization, while the second one aims to place all the items using as few identical objects as possible, that is, input minimization. The objective of this paper is not to be exhaustive but to provide a solid grasp on two‐dimensional rectangular cutting and packing problems by describing their most important solution approaches.

31 March 2025 in Systems
Verified
Journal Article
Open access
PDF file
Terresa PeixotoTerresa Peixoto
Terresa Peixoto
Bruno OliveiraBruno Oliveira
Bruno Oliveira
Óscar OliveiraÓscar Oliveira
Óscar Oliveira
FRFillipe Ribeiro
Fillipe Ribeiro
Data quality in IoT and smart manufacturing environments is essential for optimizing workflows, enabling predictive maintenance, and supporting informed decisions. However, data from sensors present significant challenges due to their real-time nature, diversity of formats, and high susceptibility to faults such as missing values or inconsistencies. Ensuring high-quality data in these environments is crucial to maintaining operational efficiency and process reliability. This paper analyzes some of the data quality metrics presented in the literature, with a focus on adapting them to the context of Industry 4.0. Initially, three models for the classification of the dimensions of data quality are presented, proposed by different authors, which group together dimensions such as accuracy, completeness, consistency, and timeliness in different approaches. Next, a systematic methodology is adopted to evaluate the metrics related to these dimensions, always using a real-time monitoring scenario. This approach combines dynamic thresholds with historical data to assess the quality of incoming data streams and provide relevant insights. The analysis carried out not only facilitates continuous monitoring of data quality but also supports informed decision-making, helping to improve operational efficiency in Industry 4.0 environments. Finally, this paper presents a table summarizing the selected metrics, highlighting the advantages, disadvantages, and potential usage scenarios, and providing a practical basis for implementation in real environments.

1 January 2016 in Procedia Computer Science
Verified
Journal Article
Open access
Óscar OliveiraÓscar Oliveira
Óscar Oliveira
DGDorabela Gamboa
Dorabela Gamboa
PFPedro Fernandes
Pedro Fernandes
Due to the current European economic stagnation and to face the increasing competition from emerging economies, significant changes in the European furniture industry need to be undertaken. Several institutions have produced reports showing that the European furniture industry must innovate the products, the production processes, the promotion strategies and the organizational structure in order to attain flexibility and productivity. The most relevant factor for the decrease in market share in the European furniture industry is the production cost, mainly due to labour and raw materials costs. The proposed information system aims to reduce the waste of raw materials generated in the production process, optimizing their purchase and consumption, boosting corporate profitability and sustainability

20 June 2025 in Computers
Verified
Journal Article
Open access
PDF file
Terresa PeixotoTerresa Peixoto
Terresa Peixoto
Óscar OliveiraÓscar Oliveira
Óscar Oliveira
ESEliana Costa e Silva
Eliana Costa e Silva
Bruno OliveiraBruno Oliveira
Bruno Oliveira
FRFillipe Ribeiro
Fillipe Ribeiro
In modern industrial environments, data-driven decision-making plays a crucial role in ensuring operational efficiency, predictive maintenance, and process optimization. However, the effectiveness of these decisions is highly dependent on the quality of the data. Industrial data is typically generated in real time by sensors integrated into IoT devices and smart manufacturing systems, resulting in high-volume, heterogeneous, and rapidly changing data streams. This paper presents the design and implementation of a data quality pipeline specifically adapted to such industrial contexts. The proposed pipeline includes modular components responsible for data ingestion, profiling, validation, and continuous monitoring, and is guided by a comprehensive set of data quality dimensions, including accuracy, completeness, consistency, and timeliness. For each dimension, appropriate metrics are applied, including accuracy measures based on dynamic intervals and validations based on consistency rules. To evaluate its effectiveness, we conducted a case study in a real manufacturing environment. By continuously monitoring data quality, problems can be proactively identified before they impact downstream processes, resulting in more reliable and timely decisions.

8 February 2023 in Electronics
Verified
Journal Article
Open access
PDF file
Miguel GuimarãesMiguel Guimarães
Miguel Guimarães
Davide CarneiroDavide Carneiro
Davide Carneiro
GPGuilherme Palumbo
Guilherme Palumbo
FOFilipe Oliveira
Filipe Oliveira
Óscar OliveiraÓscar Oliveira
Óscar Oliveira
Paulo NovaisPaulo Novais
Paulo Novais
Despite major advances in recent years, the field of Machine Learning continues to face research and technical challenges. Mostly, these stem from big data and streaming data, which require models to be frequently updated or re-trained, at the expense of significant computational resources. One solution is the use of distributed learning algorithms, which can learn in a distributed manner, from distributed datasets. In this paper, we describe CEDEs—a distributed learning system in which models are heterogeneous distributed Ensembles, i.e., complex models constituted by different base models, trained with different and distributed subsets of data. Specifically, we address the issue of predicting the training time of a given model, given its characteristics and the characteristics of the data. Given that the creation of an Ensemble may imply the training of hundreds of base models, information about the predicted duration of each of these individual tasks is paramount for an efficient management of the cluster’s computational resources and for minimizing makespan, i.e., the time it takes to train the whole Ensemble. Results show that the proposed approach is able to predict the training time of Decision Trees with an average error of 0.103 s, and the training time of Neural Networks with an average error of 21.263 s. We also show how results depend significantly on the hyperparameters of the model and on the characteristics of the input data.

25 June 2021 in Annals of Mathematics and Artificial Intelligence
Verified
Journal Article
Closed access
PDF file
TMTelmo Matos
Telmo Matos
Óscar OliveiraÓscar Oliveira
Óscar Oliveira
DGDorabela Gamboa
Dorabela Gamboa