Loading...
74 results
Search Results
Now showing 1 - 10 of 74
- Graphical simulator of mathematical algorithms (GraSMA)Publication . Balsa, Carlos; Alves, Luís M.; Pereira, Maria João; Rodrigues, Pedro JoãoOur goal is to develop an interactive software GraSMA that illustrates the execution of mathematical algorithms in the context of numerical methods. We want to create a working tool for teachers and learning tool for students. To achieve it we only use free software (as it is the Open Source software). The strategy followed was to extend the original algorithm code, implemented in Octave, with inspector instructions, recording in a XML (eXtensible Markup Language) file everything that happened during the execution. Subsequently, the XML file is parsed by a Java application that graphically represents the mathematic objects and their behaviour during execution. In this paper, we report the procedures followed, the difficulties encountered and the first results we achieved.
- Sistema integrado de gestão de centros emissores de radiodifusãoPublication . Figal, David; Igrejas, Getúlio; Rodrigues, Pedro JoãoDevido à elevada dimensão das áreas geográficas abrangidas pelas células radioelétricas, bem como à limitação de recursos humanos, atualmente as empresas que executam a manutenção de postos retransmissores de radiodifusão têm dificuldade em garantir um rápido atendimento na reparação dos sistemas de radiodifusão. Adicionalmente, verifica-se que a maioria das faltas evidenciadas pelos referidos sistemas são de natureza reversível, o que possibilita solucionar este problema através da utilização de um equipamento de telecontrolo, não sendo necessária qualquer intervenção presencial, o que permitiria a redução de custos e tempo despendido nas deslocações. Após uma vasta pesquisa de mercado, não foi identificado qualquer equipamento ou solução que permita realizar, de forma integrada, as ações de monitorização e controlo remoto dos transmissores de radiodifusão. As tecnologias disponíveis ou permitem apenas a monitorização dos equipamentos, não permitindo a interação com os mesmos, ou quando permitem alguma interação não fornecem alguns serviços considerados fundamentais, designadamente a escuta do áudio. Desta forma, este trabalho consistiu no desenvolvimento de um dispositivo de telecontrolo aplicado a centros de radiodifusão. O dispositivo construído permite monitorizar e controlar os equipamentos do centro, remotamente, a partir de um dispositivo com acesso à rede GSM. Permite também uma análise contínua do sinal de áudio retransmitido, baseada em descritores estatísticos, que permitem avaliar com sucesso as anomalias típicas deste sinal (e.g. ausência de portadora, ruído aleatório padronizado, etc). O sistema inclui ainda funcionalidades de gestão de permissões e utilizadores, difusão de alarmes e de registo em memória não volátil de todas as ocorrências e solicitações ao dispositivo.
- Interação genótipo - ambiente entre duas origens e localizações na abelha ibérica (Apis mellifera iberiensis)Publication . Neves, Cátia J.; Lopes, Ana; Rodrigues, Pedro João; Pérez-Rodríguez, Fernando; Vilas-Boas, Miguel; Ventura, Paulo J.C.; Henriques, Dora; Chávez-Galarza, Julio; Garnery, Lionel; Biron, David G.; Pinto, M. AliceNa europa, vários estudos revelaram que as populações nativas de Apis mellifera estão adaptadas ao clima e flora locais. Contudo, até agora, não existe informação para a abelha ibérica, Apis mellifera iberiensis. Neste contexto, o principal objetivo deste estudo foi avaliar a existência de adaptação local na abelha ibérica. Este estudo foi dividido em três partes: (1) instalação de dois apiários nos dois extremos de Portugal (Gimonde e Zavial), cada um com duas origens genéticas da abelha ibérica (18 colónias do Algarve e 18 colónias de Bragança); (2) estimação do número de abelhas, número de alvéolos com criação, mel e pólen em três estações (primavera, verão e outono) e do comportamento higiénico e percentagem de infestação de Varroa destructor em uma estação (verão); (3) análise estatística, utilizando testes estatísticos adequados tais como teste t-Student e Mann-Whitney (software R, versão 3.4.1), para comparar as características de diferentes origens no mesmo apiário e características da mesma origem em diferentes apiários. No apiário do Zavial observaram-se diferenças significativas no número de abelhas, criação e pólen entre as duas origens genéticas. Contrariamente ao Zavial, no apiário de Gimonde não se registaram diferenças significativas em nenhuma das características avaliadas entre as duas origens. Além disso, ambas as origens mostraram um melhor desempenho no apiário do Zavial do que no de Gimonde. Os resultados obtidos indicam que as diferenças entre as duas origens são reveladas em ambientes mais favoráveis onde as abelhas podem melhor expressar o seu potencial genético.
- Classificação de óleos alimentares com base na composição em ácidos gordos e aplicação de um modelo de lógica difusaPublication . Igrejas, Getúlio; Amaral, Joana S.; Rodrigues, Pedro João; Oliveira, BeatrizSegundo a Legislação Portuguesa, os óleos alimentares (OA) são obtidos por mistura de dois ou mais óleos vegetais estremes (óleos obtidos de uma 56 semente), refinados isoladamente ou em conjunto, com excepção do azeite. Dos óleos vegetais estremes (OV) utilizados na alimentação humana, os óleos de girassol, soja e milho são os mais representativos em Portugal. Estes óleos têm composições diferentes, quer a nível do perfil de ácidos gordos (AO) quer em compostos minoritários (fitosteróis, tocoferóis e tocotrienóis). Actualmente, a indústria produz OA resultantes de misturas específicas, estudando cuidadosamente n proporção dos diferentes óleos, de forma a obter produtos com características particulares. Assim, podem ser encontrados no mercado diversos OA de composições diferentes que procuram responder às preferências do consumidor, nomeadamente no que respeita a qualidade/nutrição, desempenho na fritura e/ou preço.
- An antibiogram classification system based on an hybrid hough transform and gradient approachPublication . Ferreira, Rayssa Lopes Dantas; Amaral, Joana S.; Igrejas, Getúlio; Rodrigues, Pedro JoãoThe antibiogram performed by the disc diffusion method is a test frequently used in clinical microbiology. In this test, the result is given by the diameter of the inhibition zone formed around the antibiotic disc. In general, this measurement is performed manually. The main objective of this work was to develop an automatic image analysis system to assess the susceptibility of microorganisms to different antibiotics. As a first step, several images of antibiograms were obtained. Subsequently the images were subjected to image processing techniques. After the elimination of noise, the Hough transform was used to detect the antibiotic discs. Next, from the center of each identified disc, the inhibition zone was detected recurring to a gradient method. According to the diameter of the inhibition zone a susceptibility classification was made. The results prove the validity of the developed tool to detect the antibiotics discs and to segment the inhibition zones used in microorganism’s susceptibility evaluation.
- A neural network based fall detectorPublication . Rodrigues, Pedro João; Amaral, J.S.; Igrejas, GetúlioIn this project we present an intelligent fall detector system based on a 3-axis accelerometer and a neural network model that allows recognizing several possible motion situations and performing an emergency call only when a fall situation occurs, with low false negatives rate and low false positives rate. The system is based on a two module platform. The first one is a Mobile Station (MS) and should be carried always by the person. An accelerometer is implemented in this module and its information is transferred via a radio-frequency channel (RF) to the Base Station (BS). The BS is fixed and is connected to a GSM (Global System for Mobile communication) module. A neural network model was built into the BS and is able to identify falls from other possible motion situations, based on the received information. According to the neural network response the system sends a SMS (Short Message Service) to a destination number requesting for assistance.
- Comparison of Iberian honey bee colony variables continuously monitored with thermo-hygro-buttons and electronic scales set up in two latitudinal extremes of PortugalPublication . Neves, Cátia J.; Rodrigues, Pedro João; Pérez-Rodríguez, Fernando; Vilas-Boas, Miguel; Ventura, Paulo J.C.; Chávez-Galarza, Julio; Garnery, Lionel; Biron, David G.; Pinto, M. AliceHoney bee colony data collected continuously together with climate data are of great importance because they provide the opportunity to understand colony phenology. Continuous monitoring of honey bee colonies initiated long time ago with Gates (1914) and Hambleton (1925), when they assessed weather effects on hive weight using mechanical scales. Currently, the study of colony dynamics has been intensified with development of new technologies such as electronic scales, hygro-buttons, thermo-buttons, and computer-assisted digital image analysis of brood combs. Studies of colony dynamics are of great interest in Portugal because of large climatic (and flora) differences between the two latitudinal extremes and because of distinct genetic backgrounds of the native subspecies, Apis mellifera iberiensis (Pinto et al. 2013). In this study we will compare the temporal dynamics of colony weight and nest temperature and humidity of 12 colonies, which have been continuously monitored since July of 2015 with electronic scales and thermo-hygro-buttons, set up in apiaries located in two latitudinal extremes of Portugal. These colony variables will be correlated with climatic data (temperature, humidity, wind speed, and rain) obtained from automatic weather stations installed in the two apiaries. This research is funded through the 2013-2014 BiodivERsA/FACCE-JPI Joint call for research proposals, with the national funders FCT (Portugal), CNRS (France), and MEC (Spain).
- Prediction of Health of Corals Mussismilia hispida Based on the Microorganisms Present in their MicrobiomePublication . Barque, Barry Malick; Rodrigues, Pedro João; Paula Filho, Pedro Luiz de; Peixoto, Raquel Silva; Leite, Deborah Catharine de AssisOne of the most diverse and productive marine ecosystems in the world are the corals, providing not only tourism but also an important economic contribution to the countries that have them on their coasts. Thanks to genome sequencing techniques, it is possible to identify the microorganisms that form the coral microbiome. The generation of large amounts of data, thanks to the low cost of sequencing since 2005, provides an opening for the use of artificial neural networks for the advancement of sciences such as biology and medicine. This work aims to predict the healthy microbiome present in samples of Mussismilia hispida coral, using machine learning algorithms, in which the algorithms SVM, Decision Tree, and Random Forest achieved a rate of 61%, 74%, and 72%, respectively. Additionally, it aims to identify possible microorganisms related to the disease in question in corals.
- Super-resolution face recognition: an approach using generative adversarial networks and joint-learnPublication . Oliveira, Rafael Augusto de; Scheeren, Michel Hanzen; Rodrigues, Pedro João; Junior, Arnaldo Candido; Paula Filho, Pedro LuizFace Recognition is a challenging task present in different applications and systems. An existing challenge is to recognize faces when imaging conditions are adverse, for example when images come from low-quality cameras or when the subject and the camera are far apart, thus impacting the accuracy of these recognizing systems. Super-Resolution techniques can be used to improve both image resolution and quality, hopefully improving the accuracy of the face recognition task. Among these techniques, the actual state-of-the-art uses Generative Adversarial Networks. One promising option is to train Super-Resolution and Face Recognition as one single network, conducting the network to learn super resolution features that will improve its capability when recognizing faces. In the present work, we trained a super resolution face recognition model using a jointly-learn approach, combining a generative network for super resolution and a ResNet50 for Face Recognition. The model was trained with a discriminator network, following the generative adversarial training. The images generated by the network were convincing, but we could not converge the face recognition model. We hope that our contributions could help future works on this topic. Code is publicly available at https://github.com/OliRafa/SRFR-GAN.
- Segmentation of fetal 2D images with deep learning: a reviewPublication . Rodrigues, Pedro João; Rehman, M. Anees ur; Igrejas, GetúlioImage segmentation plays a vital role in providing sustainable medical care in this evolving biomedical image processing technology. Nowadays, it is considered one of the most important research directions in the computer vision field. Since the last decade, deep learning-based medical image processing has become a research hotspot due to its exceptional performance. In this paper, we present a review of different deep learning techniques used to segment fetal 2D images. First, we explain the basic ideas of each approach and then thoroughly investigate the methods used for the segmentation of fetal images. Secondly, the results and accuracy of different approaches are also discussed. The dataset details used for assessing the performance of the respective method are also documented. Based on the review studies, the challenges and future work are also pointed out at the end. As a result, it is shown that deep learning techniques are very effective in the segmentation of fetal 2D images.