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

Ricardo Sousa, é doutorado em Engenharia Eletrotécnica e de Computadores pela Faculdade de Engenharia da Universidade do Porto desde 2011 e atualmente é investigador no Laboratório de Inteligência Artificial e Apoio à Decisão (LIAAD) no INESC TEC. Participou em projetos europeus (e.g., MAESTRA), nacionais (e.g., ADIRA4.0) e projetos científicos com empresas (e.g., NDTech-Amorim) relacionados com Processamento de Sinal, Data Mining e Machine Learning. Atualmente, coordenada equipas num programa mobilizador PRODUTECH (relacionado com a Gestão de Produção e Qualidade) e num projeto P2020/FCT/MIT Portugal (Tecnologia para transformadores de potência). Tem interesse específicos nas áreas de Manutenção e Qualidade Preditiva, Process Mining e Previsão com aplicação na área da Indústria/Produção. Deu aulas na Faculdade de Engenharia da Universidade do Porto, em cadeiras de programação e sistemas de informação. Co-orientou/orientou mais de 17 dissertações de mestrado nas áreas de Processamento de Sinal e Data mining/Machine Learning.

Tópicos
de interesse
Detalhes

Detalhes

  • Nome

    Ricardo Teixeira Sousa
  • Cluster

    Informática
  • Cargo

    Adjunto da Coordenação de Centro
  • Desde

    16 setembro 2005
008
Publicações

2022

Exploiting BIM Objects for Synthetic Data Generation toward Indoor Point Cloud Classification Using Deep Learning

Autores
Frías, E; Pinto, J; Sousa, R; Lorenzo, H; Díaz Vilariño, L;

Publicação
Journal of Computing in Civil Engineering

Abstract
Advances in technology are leading to more and more devices integrating sensors capable of acquiring data quickly and with high accuracy. Point clouds are no exception. Therefore, there is increased research interest in the large amount of available light detection and ranging (LiDAR) data by point cloud classification using artificial intelligence. Nevertheless, point cloud labeling is a time-consuming task. Hence the amount of labeled data is still scarce. Data synthesis is gaining attention as an alternative to increase the volume of classified data. At the same time, the amount of Building Information Models (BIMs) provided by manufacturers on website databases is increasing. In line with these recent trends, this paper presents a deep-learning framework for classifying point cloud objects based on synthetic data sets created from BIM objects. The method starts by transforming BIM objects into point clouds deriving a data set consisting of 21 object classes characterized with various perturbation patterns. Then, the data set is split into four subsets to carry out the evaluation of synthetic data on the implemented flexible two-dimensional (2D) deep neural framework. In the latter, binary or greyscale images can be generated from point clouds by both orthographic or perspective projection to feed the network. Moreover, the surface variation feature was computed in order to aggregate more geometric information to images and to evaluate how it influences the object classification. The overall accuracy is over 85% in all tests when orthographic images are used. Also, the use of greyscale images representing surface variation improves performance in almost all tests although the computation of this feature may not be robust in point clouds with complex geometry or perturbations. © 2022 American Society of Civil Engineers.

2022

Exploiting BIM Objects for Synthetic Data Generation toward Indoor Point Cloud Classification Using Deep Learning

Autores
Frias, E; Pinto, J; Sousa, R; Lorenzo, H; Diaz Vilarino, L;

Publicação
JOURNAL OF COMPUTING IN CIVIL ENGINEERING

Abstract
Advances in technology are leading to more and more devices integrating sensors capable of acquiring data quickly and with high accuracy. Point clouds are no exception. Therefore, there is increased research interest in the large amount of available light detection and ranging (LiDAR) data by point cloud classification using artificial intelligence. Nevertheless, point cloud labeling is a time-consuming task. Hence the amount of labeled data is still scarce. Data synthesis is gaining attention as an alternative to increase the volume of classified data. At the same time, the amount of Building Information Models (BIMs) provided by manufacturers on website databases is increasing. In line with these recent trends, this paper presents a deep-learning framework for classifying point cloud objects based on synthetic data sets created from BIM objects. The method starts by transforming BIM objects into point clouds deriving a data set consisting of 21 object classes characterized with various perturbation patterns. Then, the data set is split into four subsets to carry out the evaluation of synthetic data on the implemented flexible two-dimensional (2D) deep neural framework. In the latter, binary or greyscale images can be generated from point clouds by both orthographic or perspective projection to feed the network. Moreover, the surface variation feature was computed in order to aggregate more geometric information to images and to evaluate how it influences the object classification. The overall accuracy is over 85% in all tests when orthographic images are used. Also, the use of greyscale images representing surface variation improves performance in almost all tests although the computation of this feature may not be robust in point clouds with complex geometry or perturbations. (C) 2022 American Society of Civil Engineers.

2022

Exploiting BIM Objects for Synthetic Data Generation toward Indoor Point Cloud Classification Using Deep Learning

Autores
Frías, E; Pinto, J; Sousa, R; Lorenzo, H; Díaz Vilariño, L;

Publicação
Journal of Computing in Civil Engineering

Abstract

2022

Exploiting BIM Objects for Synthetic Data Generation toward Indoor Point Cloud Classification Using Deep Learning

Autores
Frías, E; Pinto, J; Sousa, R; Lorenzo, H; Díaz-Vilariño, L;

Publicação
Journal of Computing in Civil Engineering

Abstract

2020

BRIGHT - Drift-Aware Demand Predictions for Taxi Networks

Autores
Saadallah, A; Moreira Matias, L; Sousa, R; Khiari, J; Jenelius, E; Gama, J;

Publicação
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING

Abstract
Massive data broadcast by GPS-equipped vehicles provide unprecedented opportunities. One of the main tasks in order to optimize our transportation networks is to build data-driven real-time decision support systems. However, the dynamic environments where the networks operate disallow the traditional assumptions required to put in practice many off-the-shelf supervised learning algorithms, such as finite training sets or stationary distributions. In this paper, we propose BRIGHT: a drift-aware supervised learning framework to predict demand quantities. BRIGHT aims to provide accurate predictions for short-term horizons through a creative ensemble of time series analysis methods that handles distinct types of concept drift. By selecting neighborhoods dynamically, BRIGHT reduces the likelihood of overfitting. By ensuring diversity among the base learners, BRIGHT ensures a high reduction of variance while keeping bias stable. Experiments were conducted using three large-scale heterogeneous real-world transportation networks in Porto (Portugal), Shanghai (China) and Stockholm (Sweden), as well as controlled experiments using synthetic data where multiple distinct drifts were artificially induced. The obtained results illustrate the advantages of BRIGHT in relation to state-of-the-art methods for this task. IEEE

Teses
supervisionadas

2022

Combination of multi-paradigm models for Power Transformer fault prediction

Autor
Francisco José Guedes de Melo Aguiar

Instituição
UP-FEUP

2022

Unsupervised learning approach for predictive maintenance in power transformers

Autor
Duarte Miguel de Novo Faria

Instituição
UP-FEUP

2022

Online Process Extractor and Updater

Autor
Sónia Rafaela Costa da Rocha

Instituição
UP-FCUP

2022

Online Process Extractor and Updater

Autor
Sónia Rafaela Costa da Rocha

Instituição
UP-FCUP

2020

Data-Driven Models for Predictive Quality in Precision Metalworking

Autor
António Fernando Lacerda Queiroz Almeida

Instituição
UP-FEUP