A carregar...
Projeto de investigação
Sem título
Financiador
Autores
Publicações
Exploring energy flexibility from smart electrical water heaters to improve electrification benefits in residential buildings
Publication . Lopes, Rui Amaral; Silva, Francisco; Menezes-Barros, Rafael; Amaro, Nuno; Carvalho, Ana Gonçalves de; Martins, João; CTS - Centro de Tecnologia e Sistemas; UNINOVA-Instituto de Desenvolvimento de Novas Tecnologias; Elsevier Science B.V., Amsterdam.
The integration of renewable energy sources, which often have limited dispatchability, along with the rising electrification of energy demand, is increasing the complexity of managing power systems. To address this challenge, smart solutions that leverage energy flexibility in buildings can support power system operations by adapting energy consumption according to existing needs. This study presents a forecasting and IoT-based solution for electric water heaters designed to improve energy flexibility, lower electricity costs, and enhance self-consumption of locally generated energy. Deployed in a real-world setting on Terceira Island, Portugal, the solution successfully replaced a gas boiler, achieving a 56 % decrease in electricity costs and a 34 % reduction in CO2 emissions (compared to a scenario with a 75 % efficiency gas boiler). These benefits were realized while maintaining acceptable levels of comfort and user engagement.
A Systematic Review on Multimodal Emotion Recognition
Publication . Kalateh, Sepideh; Estrada-Jimenez, Luis A.; Nikghadam-Hojjati, Sanaz; Barata, Jose; DEE - Departamento de Engenharia Electrotécnica e de Computadores; CTS - Centro de Tecnologia e Sistemas; UNINOVA-Instituto de Desenvolvimento de Novas Tecnologias; Institute of Electrical and Electronics Engineers (IEEE)
Emotion recognition involves accurately interpreting human emotions from various sources and modalities, including questionnaires, verbal, and physiological signals. With its broad applications in affective computing, computational creativity, human-robot interactions, and market research, the field has seen a surge in interest in recent years. This paper presents a systematic review of multimodal emotion recognition (MER) techniques developed from 2014 to 2024, encompassing verbal, physiological signals, facial, body gesture, and speech as well as emerging methods like sketches emotion recognition. The review explores various emotion models, distinguishing between emotions, feelings, sentiments, and moods, along with human emotional expression, categorized in both artistic and non-verbal ways. It also discusses the background of automated emotion recognition systems and introduces seven criteria for evaluating modalities alongside a current state analysis of MER, drawn from the human-centric perspective of this field. By selecting the PRISMA guidelines and carefully analyzing 45 selected articles, this review provides comprehensive perspectives into existing studies, datasets, technical approaches, identified gaps, and future directions in MER. It also highlights existing challenges and current applications of the MER.
A Factory of Fractional Derivatives
Publication . Ortigueira, Manuel D.; CTS - Centro de Tecnologia e Sistemas; UNINOVA-Instituto de Desenvolvimento de Novas Tecnologias; MDPI - Multidisciplinary Digital Publishing Institute
This paper aims to demonstrate that, beyond the small world of Riemann–Liouville and Caputo derivatives, there is a vast and rich world with many derivatives suitable for specific problems and various theoretical frameworks to develop, corresponding to different paths taken. The notions of time and scale sequences are introduced, and general associated basic derivatives, namely, right/stretching and left/shrinking, are defined. A general framework for fractional derivative definitions is reviewed and applied to obtain both known and new fractional-order derivatives. Several fractional derivatives are considered, mainly Liouville, Hadamard, Euler, bilinear, tempered, q-derivative, and Hahn.
Text clustering with large language model embeddings
Publication . Petukhova, Alina; Matos-Carvalho, João P.; Fachada, Nuno; CTS - Centro de Tecnologia e Sistemas; UNINOVA-Instituto de Desenvolvimento de Novas Tecnologias; KeAi Communications Co.
Text clustering is an important method for organising the increasing volume of digital content, aiding in the structuring and discovery of hidden patterns in uncategorised data. The effectiveness of text clustering largely depends on the selection of textual embeddings and clustering algorithms. This study argues that recent advancements in large language models (LLMs) have the potential to enhance this task. The research investigates how different textual embeddings, particularly those utilised in LLMs, and various clustering algorithms influence the clustering of text datasets. A series of experiments were conducted to evaluate the impact of embeddings on clustering results, the role of dimensionality reduction through summarisation, and the adjustment of model size. The findings indicate that LLM embeddings are superior at capturing subtleties in structured language. OpenAI's GPT-3.5 Turbo model yields better results in three out of five clustering metrics across most tested datasets. Most LLM embeddings show improvements in cluster purity and provide a more informative silhouette score, reflecting a refined structural understanding of text data compared to traditional methods. Among the more lightweight models, BERT demonstrates leading performance. Additionally, it was observed that increasing model dimensionality and employing summarisation techniques do not consistently enhance clustering efficiency, suggesting that these strategies require careful consideration for practical application. These results highlight a complex balance between the need for refined text representation and computational feasibility in text clustering applications. This study extends traditional text clustering frameworks by integrating embeddings from LLMs, offering improved methodologies and suggesting new avenues for future research in various types of textual analysis.
Power Functions and Their Relationship with the Unified Fractional Derivative
Publication . Ortigueira, Manuel Duarte; CTS - Centro de Tecnologia e Sistemas; UNINOVA-Instituto de Desenvolvimento de Novas Tecnologias; MDPI - Multidisciplinary Digital Publishing Institute
The different forms of power functions will be studied in connection with the unified fractional derivative, and their Fourier transform will be computed. In particular, one-sided, even, and odd powers will be studied.
Unidades organizacionais
Descrição
Palavras-chave
Contribuidores
Financiadores
Entidade financiadora
Fundação para a Ciência e a Tecnologia
Programa de financiamento
Concurso de avaliação no âmbito do Programa Plurianual de Financiamento de Unidades de I&D (2017/2018) - Financiamento Base
Número da atribuição
UIDB/00066/2020