Ciências e Tecnologia | Capítulos/artigos em livros internacionais / Book chapters/papers in international books
Permanent URI for this collection
Browse
Recent Submissions
- Causal machine learning in social impact assessmentPublication . Lopes, Nuno Castro; Cavique, Luís; Moutinho, Luiz; Cavique, Luís; Bigné, EnriqueSocial impact assessment is a fundamental process to verify the achievement of the objectives of interventions and, consequently, to validate investments in the social area. Generally, this process is based on the analysis of the average effects of the intervention, which does not allow a detailed understanding of the individualization of these effects. Causal machine learning methods mark an evolution in causal inference, as they allow for a more heterogeneous assessment of the effects of interventions. Applying these methods to evaluate the impact of social projects and programs offers the advantage of improving the selection of target audiences and optimizing and personalizing future interventions. In this chapter, in a non-technical way, the authors explore classical causal inference methods to estimate average effects and new causal machine learning methods to evaluate heterogeneous effects. They address adapting the Uplift Modeling method to assess social interventions. They also address the advantages, limitations, and research needs for using these new techniques in social intervention.
- Impact of artificial intelligence in industry 4.0 and 5.0Publication . Moutinho, Luiz; Cavique, Luís; Moutinho, Luiz; Cavique, Luís; Bigné, EnriqueIndustry 4.0 uses the network concept to establish an interconnected manufacturing system. Industry 4.0 integrates the more recent digital concepts such as artificial intelligence (AI), the internet of things (IoT), big data, cloud computing, and 3D printing. The next maturity level, Industry 5.0, aims to shift the focus back to human-centric production by creating a sustainable and collaborative environment with humans and machines. Every manufacturer aims to find new ways to increase profits, reduce risks, and improve production efficiency. AI tools can process and interpret vast volumes of data from the production floor to spot patterns, analyze and predict consumer behavior, and detect real-time anomalies in production processes. This work studies the impact of AI in Industries 4.0 and 5.0. In Industry 4.0, AI can help in classic tasks such as predictive maintenance, production optimization, and customer personalization. Industry 5.0 enables sustainable manufacturing development and human-AI interaction. In this work, the authors demonstrate the impact of AI in Industry 4.0 and 5.0.
- Causality: the next step in artificial intelligencePublication . Cavique, Luís; Moutinho , Luiz; Cavique , Luís; Bigné, EnriqueJudea Pearl’s ladder of causation framework has dramatically influenced the understanding of causality in computer science. Despite artificial intelligence (AI) advancements, grasping causal relationships remains challenging, emphasizing the causal revolution’s significance in improving AI’s understanding of cause and effect. The work presents a novel taxonomy of causal inference methods, clarifying diverse approaches for inferring causality from data. It highlights the implications of causality in responsible AI and explainable AI (xAI), addressing bias in AI systems. The chapter points out causality as the next step in AI for creating new questions, developing causal tools, and clarifying opaque models with xAI approaches. The work clarifies causal models’ significance and implications in various AI subareas.
- Networks and connectivity: metrics and modelsPublication . Cavique, LuísThis work explores network science to understand and visualize the intricate interconnectivity within organizations. The age of big data emphasizes the importance of deriving new insights by transforming data into networks to study their connections. The document introduces a three-step maturity framework for navigating network science, starting with the basics of network construction, moving on to standard metrics, and examining network topology and dynamics. The authors aim to clarify the subject and encourage further exploration, suggesting that while network science may not have all the answers, it offers a critical analytical framework.
- Texture for neuroimagingPublication . Nunes, Ana; Serranho, Pedro; Castelo-Branco, Miguel; Bernardes, RuiTexture analysis is an umbrella term for multiple image analysis techniques that quantify and characterize the distribution of the image’s gray levels. It has a natural application in biomedical image analysis, where texture-based techniques are increasingly being incorporated into neuroimaging research. In this chapter, the role of texture analysis in the field of neuroimaging is addressed. Neuroimaging applications of texture-based approaches are contextualized within past and recent developments in image texture analysis, the categories of texture analysis methods, and the typical texture-based problem types, namely, classification and segmentation. Neuroimaging applications using magnetic resonance imaging, positron emission tomography, and optical coherence tomography are individually reviewed, and some considerations on the future perspectives for texture-based approaches in neuroimaging are made.
- Sustainability of fisheriesPublication . Pierce, Graham; Pita, Cristina; Santos, M. Begona; Seixas, SóniaThis chapter reviews the concept of sustainability in fisheries, focussing on fisheries in Europe and paying particular attention to the human dimensions of fisheries. The particular problems presented by fisheries (related to the “Tragedy of the Com- mons”) are introduced, followed by brief accounts of the importance of fisheries worldwide and of their history in Europe. We attempt to summarize the concepts embodied in fisheries management and governance and review the different dimensions (pillars) of sustainability in the context of fisheries: environmental, economic, social and institutional. We describe some current developments in management and governance of European fisheries, including the introduction of property rights, the role of ecological labelling and the concept of demand-led management, participation and co-management, marine protected areas and Integrated Marine Management. We advocate a system of governance under which more attention is placed on achieving the possible than in quantifying the unachievable, a system which delivers successful implementation of sustainabil- ity objectives based on holistic (and multidisciplinary) assessments of environ- mental, economic and social-cultural consequences of proposed actions and which is based on the full and active participation of all relevant stakeholders
- The future of cephalopod populations, fisheries, culture, and research in EuropePublication . Pierce, Graham; Belcari, Paola; Bustamante, Paco; Challier, Laurence; Cherel, Yves; González, Ángel; Guerra, Ángel; Jereb, Patrizia; Koueta, Noussithé; Lefkaditou, Eugenia; Moreno, Ana; Pereira, João; Piatkowski, Uwe; Pita, Cristina; Robin, Jean‐Paul; Roel, Beatriz; Santos, M. Begoña; Santurtun, Marina; Seixas, Sónia; Shaw, Paul; Smith, Jennifer; Stowasser, Gabrielle; Valavanis, Vasilis; Villanueva, Roger; Wang, Jianjun; Wangvoralak, Sansanee; Weis, Manuela; Zumholz, Karsten
- Aquarium as a tool for teaching sciences at all grades levelsPublication . Seixas, Sónia; Martinho, Marco
- Sepia orbignyana Férussac in d’Orbigny, 1826Publication . Jereb, Patrizia; Sobrino, Ignacio; Allcock, Louise; Seixas, Sónia; Lefkaditou, Evgenia
- Eledone moschata (Lamarck, 1798)Publication . Sobrino, Ignacio; Moreno, Ana; Jereb, Patrizia; Balguerias, Eduardo; Seixas, Sónia; Pierce, Graham; Lefkaditou, Evgenia; Allcock, Louise