Browsing by resource type "text"
Now showing 1 - 10 of 30
Results Per Page
Sort Options
- Adaptive and Scalable Database Management with Machine Learning Integration: A PostgreSQL Case StudyPublication . Abbasi, Maryam; Bernardo, Marco V.; Vaz, Paulo; Silva, José; Martins, Pedro; ANTUNES VAZ, PAULO JOAQUIM; Silva, JoséThe increasing complexity of managing modern database systems, particularly in terms of optimizing query performance for large datasets, presents significant challenges that traditional methods often fail to address. This paper proposes a comprehensive framework for integrating advanced machine learning (ML) models within the architecture of a database management system (DBMS), with a specific focus on PostgreSQL. Our approach leverages a combination of supervised and unsupervised learning techniques to predict query execution times, optimize performance, and dynamically manage workloads. Unlike existing solutions that address specific optimization tasks in isolation, our framework provides a unified platform that supports real-time model inference and automatic database configuration adjustments based on workload patterns. A key contribution of our work is the integration of ML capabilities directly into the DBMS engine, enabling seamless interaction between the ML models and the query optimization process. This integration allows for the automatic retraining of models and dynamic workload management, resulting in substantial improvements in both query response times and overall system throughput. Our evaluations using the Transaction Processing Performance Council Decision Support (TPC-DS) benchmark dataset at scale factors of 100 GB, 1 TB, and 10 TB demonstrate a reduction of up to 42% in query execution times and a 74% improvement in throughput compared with traditional approaches. Additionally, we address challenges such as potential conflicts in tuning recommendations and the performance overhead associated with ML integration, providing insights for future research directions. This study is motivated by the need for autonomous tuning mechanisms to manage large-scale, hetero geneous workloads while answering key research questions, such as the following: (1) How can machine learning models be integrated into a DBMS to improve query optimization and workload management? (2) What performance improvements can be achieved through dynamic configuration tuning based on real-time workload patterns? Our results suggest that the proposed framework significantly reduces the need for manual database administration while effectively adapting to evolving workloads, offering a robust solution for modern large-scale data environments.
- Analysis of Governance models for sustainable and healthy food systemsPublication . Florença, Sofia de Guiné e; Amaral, Ana Luísa; Costa, Filipa; Guiné, Raquel; Costa, Cristina Amaro daSustainable food systems are systems that safeguard economic, social and environmental sustainability by fomenting social progress, promoting efficient management of natural resources, providing nutritious food and ensuring fair compensation for all actors in the food chain. In recent years, several initiatives worldwide have been created to ensure and promote the sustainability of the current food systems. These initiatives aim to enable people to have access to quality, nutritious and sustainable foods, combat social and economic inequalities and promote synergies between consumers and producers. To promote these initiatives is crucial in order to contribute to improved food consumption and production patterns towards more nutritive and sustainable foods. The objective of this research was to identify and characterize sustainable food initiatives in order to understand their structure, model of governance, motivations, typology of actors involved and future prospects. This investigation was based on an interview guide that was applied to the managers or those responsible for the sustainable initiatives related with the food system. Seven initiatives were included, and the semi- structured interviews were carried out online during the summer of 2024. The recorded interviews were transcribed, and the content analysed. The results obtained by the interviews showed that the principal motivators are related to food and sustainability, in all three, economic, environmental and social, dimensions. It was further identified that the most important cause of success was the availability and commitment of the people involved in the initiative. The seven initiatives analysed were implemented to meet local needs, both of producers and consumers, while promoting sustainability. Furthermore, they aimed at encouraging economic circularity, transference and sharing of knowledge, valorisation of local and rural resources, and management of food waste. These aspects contribute to more efficient and eco-friendly local food supply chains, providing the consumers with fresher and heathier food products. The existence of local or nationwide initiatives related with the sustainability of food system contribute to a more efficient use of natural resources in order to obtain healthy, sustainable and fair food products, that the modern consumers tend to value in search for a more friendly co-existence between the necessity to produce food and the recognized need to preserve the natural ecosystems.
- Assessing Cultural Variations in Nutrition Environment Measures Survey in Stores (NEMS-S): A Global Perspective on Food Availability and QualityPublication . Florença, Sofia de Guiné e; Simões J; Amaro da Costa, Cristina Isabel; Cunha Silva Reis Lima, Maria Joao; Guiné, Raquel; Teixeira-Lemos, Edite
- Characterization of Sustainable Food Initiatives: Preliminary Study.Publication . Florença, Sofia de Guiné e; Amaral, Ana Luísa; Costa, Filipa; Guiné, Raquel; Amaro da Costa, Cristina IsabelAbstract: A sustainable food system can be described as a system that ensures economic, social, and environmental sustainability to secure food and nutrition for current and future generations. The present research aimed to identify and characterize sustainable food initiatives to understand the governance framework, the motivations, the reasons for success, the typology of actors involved, and future prospects. Semi-structured interviews were conducted for seven initiatives between June and August 2024. The interviews were performed online, recorded, transcribed, and analyzed. The results showed that the main drivers of the initiatives relate to food, sustainability, and economic and social dimensions. Moreover, one of the reasons for the success of the initiatives is the availability and commitment of the people involved. These initiatives were created to meet local needs and promote sustainability as well as to encourage economic circularity, knowledge sharing, rural and local valorization, and waste management.
- Comparison of milk consumption habits across two European countries: Pilot study in Portugal and FrancePublication . Guiné, Raquel P. F.; Florença, Sofia de Guiné e; Bréjon, M.; Gonçalves, João Carlos; Ferreira, Manuela; Barroca, Maria João; Fragata, AnabelaHumans have been consuming milk obtained from domesticated animals since ancient times. Milk is a very complete food with important nutrients that can sup- port life. However, the patterns of consumption of milk have been shifting. On one hand, due to the increase in the number of people with intolerances (to lactose, for example), and on the other hand, due to some trend to avoid foods from animal origin owing to speci fi c convic- tion (like animal welfare, for example). In this context, this study focused on the milk consumption patterns in two di ff erent European Countries and the evaluation of pos- sible di ff erences. The object of study was milk obtained from animal sources, namely, cows, and no other derived fermented dairy products were included. For the develop- ment of the study, a questionnaire survey was applied to a sample of 542 participants from both countries using the Internet. The results showed that a high percentage of participants in both countries consume milk regularly, and the usual amount varies between 125 and 250 mL per day. For those who do not consume milk, the most relevant reason pointed out in both countries was because they do not feel the need to consume it. While in France, a high percentage also do not consume because they do not like milk, and in Portugal, a high percentage do not consume milk due to lactose intolerance. The most con- sumed is semi-skimmed milk, and preferences are towards consuming plain milk or consuming it with chocolate. Signi fi cant di ff erences were found in the consumption of white brands, which are preferred in France, while in Portugal, consumers prefer commercial brands, as well as the preferred package, tetra packs for the Portuguese, while the French prefer plastic bottles. In conclusion, although the results showed some similar trends among the participants from both countries, some di ff erences were also identi fi ed that can be used to better plan public policies in both countries.
- Comprehensive Evaluation of Deepfake Detection Models: Accuracy, Generalization, and Resilience to Adversarial AttacksPublication . Abbasi, Maryam; ANTUNES VAZ, PAULO JOAQUIM; Silva, José; Martins, PedroThe rise of deepfakes—synthetic media generated using artificial intelli gence—threatens digital content authenticity, facilitating misinformation and manipu lation. However, deepfakes can also depict real or entirely fictitious individuals, leveraging state-of-the-art techniques such as generative adversarial networks (GANs) and emerging diffusion-based models. Existing detection methods face challenges with generalization across datasets and vulnerability to adversarial attacks. This study focuses on subsets of frames extracted from the DeepFake Detection Challenge (DFDC) and FaceForensics++ videos to evaluate three convolutional neural network architectures—XCeption, ResNet, and VGG16—for deepfake detection. Performance metrics include accuracy, precision, F1-score, AUC-ROC, and Matthews Correlation Coefficient (MCC), combined with an assessment of resilience to adversarial perturbations via the Fast Gradient Sign Method (FGSM). Among the tested models, XCeption achieves the highest accuracy (89.2% on DFDC), strong generalization, and real-time suitability, while VGG16 excels in precision and ResNet provides faster inference. However, all models exhibit reduced performance under adversarial conditions, underscoring the need for enhanced resilience. These find ings indicate that robust detection systems must consider advanced generative approaches, adversarial defenses, and cross-dataset adaptation to effectively counter evolving deep fake threats
- Data Privacy and Ethical Considerations in Database ManagementPublication . Pina, Eduardo; Ramos, José; Jorge, Henrique; ANTUNES VAZ, PAULO JOAQUIM; Vaz, Paulo; Silva, José; Wanzeller, Cristina; Abbasi, Maryam; Martins, Pedro; Silva, José; Wanzeller Guedes de Lacerda, Ana CristinaData privacy and ethical considerations ensure the security of databases by respecting individual rights while upholding ethical considerations when collecting, managing, and using information. Nowadays, despite having regulations that help to protect citizens and organizations, we have been presented with thousands of instances of data breaches, unauthorized access, and misuse of data related to such individuals and organizations. In this paper, we propose ethical considerations and best practices associated with critical data and the role of the database administrator who helps protect data. First, we suggest best practices for database administrators regarding data minimization, anonymization, pseudonymization and encryption, access controls, data retention guidelines, and stakeholder communication. Then, we present a case study that illustrates the application of these ethical implementations and best practices in a real-world scenario, showing the approach in action and the benefits of privacy. Finally, the study highlights the importance of a comprehensive approach to deal with data protection challenges and provides valuable insights for future research and developments in this field
- EISuFood_Edible Insects SurveyPublication . Guiné, RaquelThis data collection is intended to investigate consumer perspectives and knowledge about insects for human consumption. It is developed within the scope of the EISuFood project taking place in 18 countries simultaneously (Coordinator: Raquel Guiné, Portugal). Ethical principles are strictly followed, participation is voluntary and all information collected is strictly confidential. Only adult participants, who give consent, respond to the questionnaire. Thank you in advance for your cooperation. We thank you in advance for your collaboration.
- Enhancing Visual Perception in Immersive VR and AR Environments: AI-Driven Color and Clarity Adjustments Under Dynamic Lighting ConditionsPublication . Abbasi, Maryam; Silva, José; Martins, Pedro; ANTUNES VAZ, PAULO JOAQUIM; Silva, JoséThe visual fidelity of virtual reality (VR) and augmented reality (AR) environments is essential for user immersion and comfort. Dynamic lighting often leads to chromatic distortions and reduced clarity, causing discomfort and disrupting user experience. This paper introduces an AI-driven chromatic adjustment system based on a modified U-Net architecture, optimized for real-time applications in VR/AR. This system adapts to dynamic lighting conditions, addressing the shortcomings of traditional methods like histogram equalization and gamma correction, which struggle with rapid lighting changes and real-time user interactions. We compared our approach with state-of-the-art color constancy algorithms, including Barron’s Convolutional Color Constancy and STAR, demonstrating superior performance. Experimental results from 60 participants show significant improvements, with up to 41% better color accuracy and 39% enhanced clarity under dynamic lighting conditions. The study also included eye-tracking data, which confirmed increased user engagement with AI-enhanced images. Our system provides a practical solution for developers aiming to improve image quality, reduce visual discomfort, and enhance overall user satisfaction in immersive environments. Future work will focus on extending the model’s capability to handle more complex lighting scenarios.
- THE EVOLUTION OF FOREIGN LANGUAGE LEARNING IN HIGHER EDUCATION: A RISKY APPROACHPublication . Delplancq, Véronique; Costa Lopes, Ana Maria; Pereira, José Manuel de Almeida; Martin, Justine; Casañ Pitarch, Ricardo; Gillain, Romain; Fidalgo, Susana; Mafalda, CarmoThe introduction of active pedagogies into teaching practices is creating renewed motivation and energy for teachers and students alike. These varied pedagogies, marked by a few trends, represent, particularly in higher education (HE), a tremendous opportunity to modernise content and make the learning environment livelier and more open. However, it should be acknowledged that many difficulties have arisen, and many challenges need to be overcome. It is not only a question of selecting suitable active teaching methods, but it is also vital to define strategies that are appropriate to the target audience, the time available, and theskills being pursued to be flexible and responsive enough to reorient learners very quickly, even during class time, and to create activities that are motivating and effective in terms of learning. The impact on assessment is evident. Digital tools play a major role in this new paradigm, but they can also lead to problems in the students' work if they do not identify with the target digital tools. Learning foreign languages (FL) is becoming more communicative and interactive. In this sense, online platforms, mobile applications, and multimedia resources offer tremendous opportunities to develop multiple skills and diversify knowledge influenced by social and professional demands. This research shows the results of studies carried out in recent years with students of the Media Studies degree at the Higher School of Education of the Polytechnic Institute of Viseu (Portugal) in FL courses. We will introduce the active teaching methods used, discuss the pedagogical devices, lesson plans and choices made regarding the digital tools used, and list the difficulties encountered by the teachers and the major challenges they had to tackle in order to guarantee and maintain the students’ motivation and commitment throughout the course. Keeping these ideas in mind, the assessment of skills and knowledge also needs to evolve to better guarantee the fulfilment of the learning objectives. In conclusion, the risks created by this deep and extremely rapid evolution are inherent to the extraordinary opportunities to rethink FL learning and test new activities characterised by promoting creativity at the HE level. The key factor lies in the adaptability of all the participants involved in the process, the willingness to move ahead, away from the comfort zone of traditional approaches and to innovate in a reasonable and effective way.
- «
- 1 (current)
- 2
- 3
- »