Cookies
O website necessita de alguns cookies e outros recursos semelhantes para funcionar. Caso o permita, o INESC TEC irá utilizar cookies para recolher dados sobre as suas visitas, contribuindo, assim, para estatísticas agregadas que permitem melhorar o nosso serviço. Ver mais
Aceitar Rejeitar
  • Menu
Sobre

Sobre

Benedita Malheiro holds a five-year degree in Electrical Engineering, and an M.Sc. and a Ph.D. in Electrical and Computers Engineering, all from the University of Porto. She is a Coordinator Professor at the Electrical Engineering Department of Instituto Superior de Engenharia do Porto, the School of Engineering of the Polytechnic Institute of Porto, and director of the European Project Semester. She is specialized in engineering education and, as a senior researcher of the Centre of Robotics and Autonomous Systems of INESC TEC, in solving distributed, dynamic, and decentralized problems with the help of artificial intelligence (AI) and distributed computing. She is a member of AAAI, ACM, APPIA (Portuguese Association for AI) and OE, the Portuguese Engineers Association.

Tópicos
de interesse
Detalhes

Detalhes

  • Nome

    Benedita Malheiro
  • Cargo

    Investigador Sénior
  • Desde

    01 janeiro 2013
Publicações

2024

Smart Stress Relief – An EPS@ISEP 2022 Project

Autores
Cifuentes, GR; Camps, J; do Nascimento, JL; Bode, JA; Duarte, J; Malheiro, B; Ribeiro, C; Justo, J; Silva, F; Ferreira, P; Guedes, P;

Publicação
Lecture Notes in Networks and Systems

Abstract
Mild is a smart stress relief solution created by DSTRS, an European Project Semester student team enrolled at the Instituto Superior de Engenharia do Porto in the spring of 2022. This paper details the research performed, concerning ethics, marketing, sustainability and state-of-the-art, the ideas, concept and design pursued, and the prototype assembled and tested by DSTRS. The designed kit comprises a bracelet, pair of earphones with case, and a mobile app. The bracelet reads the user heart beat and temperature to automatically detect early stress signs. The case and mobile app command the earphones to play sounds based on the user readings or on user demand. Moreover, the case includes a tactile distractor, a scent diffuser and vibrates. This innovative multi-sensory output, combining auditory, olfactory, tactile and vestibular stimulus, intends to sooth the user. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

2024

Explainable Classification of Wiki Streams

Autores
García Méndez, S; Leal, F; de Arriba Pérez, F; Malheiro, B; Burguillo Rial, JC;

Publicação
Lecture Notes in Networks and Systems

Abstract
Web 2.0 platforms, like wikis and social networks, rely on crowdsourced data and, as such, are prone to data manipulation by ill-intended contributors. This research proposes the transparent identification of wiki manipulators through the classification of contributors as benevolent or malevolent humans or bots, together with the explanation of the attributed class labels. The system comprises: (i) stream-based data pre-processing; (ii) incremental profiling; and (iii) online classification, evaluation and explanation. Particularly, the system profiles contributors and contributions by combining features directly collected with content- and side-based engineered features. The experimental results obtained with a real data set collected from Wikivoyage – a popular travel wiki – attained a 98.52% classification accuracy and 91.34% macro F-measure. In the end, this work seeks to address data reliability to prevent information detrimental and manipulation. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

2024

Balancing Plug-In for Stream-Based Classification

Autores
de Arriba Pérez, F; García Méndez, S; Leal, F; Malheiro, B; Burguillo Rial, JC;

Publicação
Lecture Notes in Networks and Systems

Abstract
The latest technological advances drive the emergence of countless real-time data streams fed by users, sensors, and devices. These data sources can be mined with the help of predictive and classification techniques to support decision-making in fields like e-commerce, industry or health. In particular, stream-based classification is widely used to categorise incoming samples on the fly. However, the distribution of samples per class is often imbalanced, affecting the performance and fairness of machine learning models. To overcome this drawback, this paper proposes Bplug, a balancing plug-in for stream-based classification, to minimise the bias introduced by data imbalance. First, the plug-in determines the class imbalance degree and then synthesises data statistically through non-parametric kernel density estimation. The experiments, performed with real data from Wikivoyage and Metro of Porto, show that Bplug maintains inter-feature correlation and improves classification accuracy. Moreover, it works both online and offline. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

2024

Emotional Evaluation of Open-Ended Responses with Transformer Models

Autores
Sanmartín, AP; Arriba Pérez, Fd; Méndez, SG; Burguillo, JC; Leal, F; Malheiro, B;

Publicação
Good Practices and New Perspectives in Information Systems and Technologies - WorldCIST 2024, Volume 1, Lodz, Poland, 26-28 March 2024.

Abstract

2024

Exposing and explaining fake news on-the-fly

Autores
de Arriba-Pérez, F; García-Méndez, S; Leal, F; Malheiro, B; Burguillo, JC;

Publicação
MACHINE LEARNING

Abstract
Social media platforms enable the rapid dissemination and consumption of information. However, users instantly consume such content regardless of the reliability of the shared data. Consequently, the latter crowdsourcing model is exposed to manipulation. This work contributes with an explainable and online classification method to recognize fake news in real-time. The proposed method combines both unsupervised and supervised Machine Learning approaches with online created lexica. The profiling is built using creator-, content- and context-based features using Natural Language Processing techniques. The explainable classification mechanism displays in a dashboard the features selected for classification and the prediction confidence. The performance of the proposed solution has been validated with real data sets from Twitter and the results attain 80% accuracy and macro F-measure. This proposal is the first to jointly provide data stream processing, profiling, classification and explainability. Ultimately, the proposed early detection, isolation and explanation of fake news contribute to increase the quality and trustworthiness of social media contents.

Teses
supervisionadas

2022

Desenho de um neurónio analógico com recurso a tecnologia de filmes finos

Autor
Teresa Margarida Pereira Pias

Instituição
UP-FEUP

2021

Gestão e Atualização Automática de Firmware para Câmaras de Videovigilância em Shop Floor

Autor
LUÍS MIGUEL PINTO LISBOA

Instituição
IPP-ISEP

2021

Controlo de Aerogeradores para Proteção da Avifauna

Autor
JOÃO RICARDO RIBEIRO MACIO

Instituição
IPP-ISEP

2020

Ensemble-based Deep Learning Models for Detecting DeepFake Media

Autor
Rui Pedro da Silva Rodrigues Machado

Instituição
UP-FCUP

2020

Emergency Landing Spot Detection for Unmanned Aerial Vehicle

Autor
GABRIEL DA SILVA MARTINS LOUREIRO

Instituição
IPP-ISEP