Cookies
Usamos cookies para melhorar nosso site e a sua experiência. Ao continuar a navegar no site, você aceita a nossa política de cookies. Ver mais
Fechar
  • Menu
Sobre

Sobre

Raul Manuel Pereira Morais dos Santos licenciou-se em Engenharia Electrotécnica (Ramo de Electrónica, Instrumentação e Computação), pela Universidade de Trás-os-Montes e Alto Douro (UTAD), Portugal, em 1993. Obteve o grau de Mestre em Electrónica Industrial pela Universidade do Minho, em 1998. O seu doutoramento, em Engenharia Electrotécnica e de Computadores, especialidade de microeletrónica, foi obtido na UTAD, em 2004. A sua Agregação em Engenharia Electrotécnica e de Computadores foi obtida na UTAD em 2009. Atualmente é Professor Associado com Agregação no Departamento de Engenharias da Escola de Ciências e Tecnologia da UTAD. As suas principais áreas de interesse incluem: sensores e interfaces sensoriais em microeletrónica, técnicas de recolha de energia para alimentação de dispositivos eletrónicos e redes de sensores sem fios em contextos de agricultura/viticultura de precisão. Tem também interesses no campo dos dispositivos biomédicos implantáveis, em particular nos sistemas de biotelemetria e nos microgeradores vibracionais para produção de energia no interior de dispositivos implantáveis. É atualmente membro integrado no Instituto de Engenharia de Sistemas e Computadores do Porto (INESC-TEC)

Tópicos
de interesse
Detalhes

Detalhes

003
Publicações

2019

Localization Based on Natural Features Detector for Steep Slope Vineyards

Autores
Mendes, JM; dos Santos, FN; Ferraz, NA; do Couto, PM; dos Santos, RM;

Publicação
Journal of Intelligent and Robotic Systems: Theory and Applications

Abstract
Placing ground robots to work in steep slope vineyards is a complex challenge. The Global Positioning System (GPS) signal is not always available and accurate. A reliable localization approach to detect natural features for this environment is required. This paper presents an improved version of a visual detector for Vineyards Trunks and Masts (ViTruDe) and, a robot able to cope pruning actions in steep slope vineyards (AgRob V16). In addition, it presents an augmented data-set for other localization and mapping algorithm benchmarks. ViTruDe accuracy is higher than 95% under our experiments. Under a simulated runtime test, the accuracy lies between 27% - 96% depending on ViTrude parametrization. This approach can feed a localization system to solve a GPS signal absence. The ViTruDe detector also considers economic constraints and allows to develop cost-effective robots. The augmented training and datasets are publicly available for future research work. © 2018 Springer Science+Business Media B.V., part of Springer Nature

2018

Distributed monitoring system for precision enology of the Tawny Port wine aging process

Autores
Morais, R; Peres, E; Boaventura Cunha, J; Mendes, J; Cosme, F; Nunes, FM;

Publicação
Computers and Electronics in Agriculture

Abstract

2018

Application of bioelectrical impedance analysis in prediction of light kid carcass and muscle chemical composition

Autores
Silva, SR; Afonso, J; Monteiro, A; Morais, R; Cabo, A; Batista, AC; Guedes, CM; Teixeira, A;

Publicação
animal

Abstract
Carcass data were collected from 24 kids (average live weight of 12.5±5.5 kg; range 4.5 to 22.4 kg) of Jarmelista Portuguese native breed, to evaluate bioelectrical impedance analysis (BIA) as a technique for prediction of light kid carcass and muscle chemical composition. Resistance (Rs, ?) and reactance (Xc, ?), were measured in the cold carcasses with a single frequency bioelectrical impedance analyzer and, together with impedance (Z, ?), two electrical volume measurements (VolA and VolB, cm2/O), carcass cold weight (CCW), carcass compactness and several carcass linear measurements were fitted as independent variables to predict carcass composition by stepwise regression analysis. The amount of variation explained by VolA and VolB only reached a significant level (P<0.01 and P<0.05, respectively) for muscle weight, moisture, protein and fat-free soft tissue content, even so with low accuracy, with VolA providing the best results (0.326?R 2?0.366). Quite differently, individual BIA parameters (Rs, Xc and Z) explained a very large amount of variation in dissectible carcass fat weight (0.814?R 2?0.862; P<0.01). These individual BIA parameters also explained a large amount of variation in subcutaneous and intermuscular fat weights (respectively 0.749?R 2?0.793 and 0.718?R 2?0.760; P<0.01), and in muscle chemical fat weight (0.663?R 2?0.684; P<0.01). Still significant but much lower was the variation in muscle, moisture, protein and fat-free soft tissue weights (0.344?R 2?0.393; P<0.01) explained by BIA parameters. Still, the best models for estimation of muscle, moisture, protein and fat-free soft tissue weights included Rs in addition to CCW, and accounted for 97.1% to 99.8% (P<0.01) of the variation observed, with CCW by itself accounting for 97.0% to 99.6% (P<0.01) of that variation. Resistance was the only independent variable selected for the best model predicting subcutaneous fat weight. It was also selected for the best models predicting carcass fat weight (combined with carcass length, CL; R 2=0.943; P<0.01) and intermuscular fat weight (combined with CCW; R 2=0.945; P<0.01). The best model predicting muscle chemical fat weight combined CCW and Z, explaining 85.6% (P<0.01) of the variation observed. These results indicate BIA as a useful tool for prediction of light kids’ carcass composition.

2018

Machine learning classification methods in hyperspectral data processing for agricultural applications

Autores
Hruska, J; Adão, T; Pádua, L; Marques, P; Cunha, A; Peres, E; Sousa, AMR; Morais, R; Sousa, JJ;

Publicação
Proceedings of the International Conference on Geoinformatics and Data Analysis - ICGDA '18

Abstract

2018

UAS-based imagery and photogrammetric processing for tree height and crown diameter extraction

Autores
Pádua, L; Marques, P; Adão, T; Hruska, J; Peres, E; Morais, R; Sousa, AMR; Sousa, JJ;

Publicação
Proceedings of the International Conference on Geoinformatics and Data Analysis - ICGDA '18

Abstract

Teses
supervisionadas

2017

Interfaces para sistemas de domótica

Autor
Tiago Manuel Afonso Porto

Instituição
UTAD

2017

Sistemas de domótica sobre tecnologias sem fios wi-fi

Autor
Jorge Miguel Carvalho Gonçalves

Instituição
UTAD

2017

Avaliação de atividade muscular através de eletromiografia

Autor
Inês Filipa Vaz da Silva

Instituição
UTAD

2016

Monitorização não invasiva do nível de lactato

Autor
Sónia Isabel Martins Pereira

Instituição
UTAD

2016

A utilização de QRCode na indústria vinícola

Autor
Afonso de Sousa Ferreira Gomes

Instituição
UTAD