ISEP - LSA - Laboratório de Sistemas Autónomos
Permanent URI for this community
LSA is a R&D unit from ISEP the Engineering School of Porto Polytechnic. It conducts research in autonomous systems and related areas such as navigation, control and coordination of multiple robots.The laboratory activity is developed in four lines of work:
R&D programs;
Educational project;
Dissemination projects;
Strategic positioning projects for the school ISEP/IPP.
Browse
Browsing ISEP - LSA - Laboratório de Sistemas Autónomos by Sustainable Development Goals (SDG) "09:Indústria, Inovação e Infraestruturas"
Now showing 1 - 3 of 3
Results Per Page
Sort Options
- Engineering a Sustainable Future with EPS@ISEPPublication . Malheiro, Benedita; Guedes, Pedro; Leal Filho, Walter; Gasparetto Rebelatto, Bianca; Annelin, Alice; Boström, Gert-OlofThe challenge of engineering education is to transform engineering students into agents of innovation and well-being. In addition to solid scientific and technical knowledge, critical thinking, problem-solving and interpersonal competencies, it implies the ability to design and implement solutions supported by ethical and sustainability principles. With this goal in mind, the European Project Semester (EPS) provides a student-centred project-based learning framework. It is offered by a group of European higher education institutions, including the Instituto Superior de Engenharia do Porto (ISEP), the engineering school of the Polytechnic of Porto. Students work in teams of four to six, from different fields of study and nationalities, to design solutions to problems that affect individuals, society or the planet, taking into account the state of the art, the market and the ethical and sustainability implications of their decisions. These solutions are then implemented in a proof-of-concept prototype. Most of the projects address problems in education, the environment, food production and smart cities and have a strong educational, ethical and sustainability drive, encouraging students to develop sustainability competencies. This work analyses team papers of illustrative EPS@ISEP projects searching for evidences of the development of sustainability competencies. The proposed method maps keywords related to the sixteen United Nations Sustainable Development Goals to the contents of team papers by applying natural language processing and reusing the list of SDG keywords proposed by Auckland University. The results confirm EPS@ISEP fosters sustainability competencies in engineering undergraduates.
- Identification and explanation of disinformation in wiki data streamsPublication . Arriba-Pérez, Francisco de; García-Méndez, Silvia; Leal, Fátima; Malheiro, Benedita; Burguillo, Juan C.Social media platforms, increasingly used as news sources for varied data analytics, have transformed how information is generated and disseminated. However, the unverified nature of this content raises concerns about trustworthiness and accuracy, potentially negatively impacting readers’ critical judgment due to disinformation. This work aims to contribute to the automatic data quality validation field, addressing the rapid growth of online content on wiki pages. Our scalable solution includes stream-based data processing with feature engineering, feature analysis and selection, stream-based classification, and real-time explanation of prediction outcomes. The explainability dashboard is designed for the general public, who may need more specialized knowledge to interpret the model’s prediction. Experimental results on two datasets attain approximately 90% values across all evaluation metrics, demonstrating robust and competitive performance compared to works in the literature. In summary, the system assists editors by reducing their effort and time in detecting disinformation.
- Unraveling emotions with pre-trained modelsPublication . Pajón-Sanmartín, Alejandro; Arriba-Pérez, Francisco de; García-Méndez, Silvia; Leal, Fátima; Malheiro, Benedita; Burguillo-Rial, Juan Carlos; BENEDITA CAMPOS NEVES MALHEIRO, MARIATransformer models have significantly advanced the field of emotion recognition. However, there are still open challenges when exploring open-ended queries for Large Language Models (LLMs). Although current models offer good results, automatic emotion analysis in open texts presents significant challenges, such as contextual ambiguity, linguistic variability, and difficulty interpreting complex emotional expressions. These limitations make the direct application of generalist models difficult. Accordingly, this work compares the effectiveness of fine-tuning and prompt engineering in emotion detection in three distinct scenarios: (i) performance of fine-tuned pre-trained models and general-purpose LLMs using simple prompts; (ii) effectiveness of different emotion prompt designs with LLMs; and (iii) impact of emotion grouping techniques on these models. Experimental tests attain metrics above 70 % with a fine-tuned pre-trained model for emotion recognition. Moreover, the findings highlight that LLMs require structured prompt engineering and emotion grouping to enhance their performance. These advancements improve sentiment analysis, human-computer interaction, and understanding of user behavior across various domains.