Biblioteca Digital do IPB
Repositório de Publicações do Instituto Politécnico de Bragança
Entradas recentes
Can the region of production affect the quality and composition of olive oil? Comparative study on two olive cultivars
Publication . Rocha, Pedrina; Lamas, Sandra; Casal, Susana; Martins, Luísa L.; Rodrigues, Nuno
Portugal is a notable olive oil-producing country, gaining prominence in the last decade. This study examined how geographic origin influences olive oil quality by analyzing samples from three key regions (Alentejo, Beira Interior, and Trás-os-Montes) and two major cultivars: Cobrançosa and Galega. All oils met the extra-virgin classification criteria, with free acidity consistently below 0.30%, and peroxide values ranging from 2.3 to 6.7 mEq O₂/kg. Alentejo oils were sensorially more intense, showing higher bitterness and pungency (up to 6.1 and 6.8, respectively). Significant chemical differences were also observed: Trás-os-Montes oils presented the highest monounsaturated fatty acid content (up to 76% MUFA), whereas Alentejo showed the greatest concentrations of hydroxytyrosol-based compounds (up to 450 mg/kg) and strong antioxidant activity (DPPH inhibition up to 80%). Beira Interior oils exhibited the highest α-tocopherol levels (up to 428 mg/kg). Heatmaps and principal component analysis (PCA) revealed clear chemical differences based on origin, demonstrating that environmental factors significantly influence composition, oxidative stability, and antioxidant potential. These results highlight the role of terroir in shaping both the sensory and chemical properties of Portuguese olive oils.
Temporalidades da paisagem vinhateira no concelho de Murça
Publication . Martins, Márcio Ribeiro; Pinto, Jorge R.;
Na mais antiga região demarcada e regulamentada do mundo podemos encontrar diferentes soluções de armação ou sistematização dos terrenos agrícolas que resultaram em paisagens de rara beleza. O Douro é um território marcado pelo despovoamento, pelo abandono dos campos, mas também pela introdução de novas construções que, de forma mais ou menos vincada, têm descaracterizado a paisagem rural tradicional, e que contribuem, no entanto, para a sua diversificação e enriquecimento enquanto património de uma paisagem cultural evolutiva e viva. Pretende-se com este trabalho, inserido no projeto de investigação interdisciplinar e de intervenção cultural, financiado pela FCT, Raízes da Educação para o Futuro (ReduF), descrever a evolução da paisagem rural das freguesias pertencentes ao concelho de Murça, localizadas na região demarcada, e explicá-la a partir do conhecimento relativo às dinâmicas sociodemográficas desse território, desde os finais do século XIX até à atualidade. Como metodologia de trabalho, serão cruzadas informações estatísticas, nomeadamente de carácter demográfico e de atividade agrícola e vinhateira.
Synergies for cross-border tourism: a collaborative proposal for rural revitalization in Northern Portugal and Spain
Publication . Fernandes, Joana; Nogueira, Sónia P.
Attracting tourists to rural areas is a complex challenge, often overshadowed by the allure of urban or beach destinations. Limited infrastructure, sparse amenities, and a lack of visibility in the tourism industry contribute to the difficulty in drawing visitors to these less-explored regions. Accessibility issues, stemming from limited transportation options, further deter potential tourists, as rural destinations may be challenging to reach compared to well-connected urban centres. To address these challenges, collaborative efforts are essential. Regional entities must work together to make rural areas more appealing to tourists seeking unique adventures off the beaten path. The visibility of rural destinations also requires collaborative promotional campaigns that leverage digital platforms and social media to reshape perceptions about rural travel. This study introduces a project aiming to develop an online platform supporting the structuring of tourist products in the cross-border areas of Northern Portugal and Castile and León in Spain. Focusing on nature tourism, wine and gastronomy, cultural and landscape tours, and active tourism, the project addresses common challenges such as aging populations, depopulation, and limited digital connectivity in both regions. By fostering collaboration and offering a structured approach to sustainable and ecological tourism, the project aims to enhance visitor attraction and promote synergies between the resources of both regions. The proposed online platform will provide comprehensive tourist information about the cross-border areas, facilitating the commercialization of tourist resources in a structured manner. Whether suggesting frequenting independent travellers or collaborating with tour operators and inbound travel agencies, the goal is to stimulate tourist attraction, prolong their stay in the region, and boost the economy of these cross-border areas.
Architecture for scalable deployment of AI models
Publication . Costa, João Vítor Nogueira da; Lopes, Rui Pedro; Rufino, José
This work presents a modular architecture for the scalable deployment of Artificial Intelligence (AI) models that combines Infrastructure-as-Code, container orchestration, and automated observability-driven control loops.
The system provisions compute resources on on-premises Proxmox environments using Terraform, applies post-provision configuration with Ansible, orchestrates containerized services through Docker Swarm, serves Machine Learning (ML) models via TorchServe, and stores and visualizes operational metrics using InfluxDB and Grafana.
The final design closes an autonomous feedback loop in which Grafana alerts trigger a backend that executes Terraform actions to add or remove worker nodes; newly created machines are configured and joined to the cluster automatically by Ansible.
The prototype was validated with two pretrained image classification models (ResNet-18, DenseNet-161), demonstrating functional correctness (idempotent provisioning, service replication, load balancing, and failover) and performance benefits under load when elastic scaling is enabled.
While the approach proved portable between Amazon Web Services (AWS) and Proxmox and effective for medium scale workloads, the evaluation surfaced practical constraints—most notably Virtual Machine (VM) provisioning latency and a five-minute alert resolution delay—that limit responsiveness to short bursts.
The architecture meets its primary objectives of scalable, automated model serving with minimal operator intervention, and outlines opportunities for reducing reaction time (e.g., container level scaling before VM creation) and enhancing scheduling sophistication.
Optimization of a feature selection tool for inference of gene regulatory networks
Publication . Cunha, João Vítor Fuzetti da; Rufino, José; Lopes, Fabrício Martins
This dissertation concerns the computational optimization of DimReduction, a feature selection tool for inference of Gene Regulatory Networks (GRN). The primary aim was to make it faster and more performance scalable, in order to to handle large amounts of data, which would bring it closer to the bioinformatics community. The approach involved the translation of the original Java GUI-based implementation into a CLI version and the re-implementation of the latter in Python. Once the performance of the Python version was lower than expected, the focus turned again to the Java CLI version. The major bottleneck in this version was determined and addressed, namely the elimination of explicit invocation of the Garbage Collector (GC) led to the runtime of a reference dataset (with 4511 genes) to reduce from more than 2 days to 42 minutes. The optimized version of Java was then parallelized, using a threaded approach, which yielded near-linear speedups. The new Java parallel implementation was then compared with other reference platforms from the literature (GENIE3, CLR, ARACNE, C3NET, BC3NET, MRNET, MRNETB, KBOOST and PCIT). The findings indicate that even though some alternatives ensure higher metrics of quality (AUROC/AUPR), DimReduction speed makes it a competitive tool in the field.