Browsing by Author "Rodrigues, Pedro João"
Now showing 1 - 10 of 74
Results Per Page
Sort Options
- Adaptação local da Abelha Ibérica (Apis mellifera iberiensis): uma experiência de translocação recíprocaPublication . Lopes, Ana; Neves, Cátia J.; Ventura, Paulo J.C.; Vilas-Boas, Miguel; Rodrigues, Pedro João; Perez, Fernando; Garnery, Lionel; Biron, David G.; Pinto, M. AliceNa Europa, várias experiências de translocação recíproca com diferentes subespécies de abelha melífera (Apis mellifera L.) têm demonstrado a existência de adaptação local, sobretudo quando a pressão de selecção é mais forte devido, por exemplo, a novas doenças e parasitas, agroquímicos, ou rápidas mudanças climáticas. Contudo, até agora nenhum desses estudos abrangeu a subespécie da Península Ibérica, Apis mellifera iberiensis. Assim, o objetivo deste estudo foi avaliar a existência de adaptação local em A. m. iberiensis. Em 2015 foram instalados dois apiários, com 36 colónias cada, em dois extremos latitudinais de Portugal: Bragança e Vila do Bispo. As 36 colónias (18 da origem Bragança e 18 da origem Algarve) foram avaliadas para várias características durante um ano. Entre as características avaliadas incluem-se o número de alvéolos com mel, produção de mel, e o peso mensal das colónias. Na análise destas características foram usadas duas abordagens: (i) comparação entre as duas origens no mesmo apiário e (ii) comparação da mesma origem entre os dois apiários. Os resultados indicam que embora as três características possam sugerir uma interação genótipo-ambiente, apenas a produção de mel e o peso da colónia demostraram adaptação local, uma vez que as abelhas locais tiveram um melhor desempenho no seu apiário de origem. Adicionalmente, verificou-se que as diferenças entre as duas origens foram mais evidentes no ambiente considerado menos hostil (Vila do Bispo), onde cada colónia pode expressar todo o seu potencial genético.
- 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.
- 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.
- An antibiogram classificattion 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 disco 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 susceptibilfty evaluation.
- Assessing the 3D Position of a Car with a Single 2D Camera Using Siamese NetworksPublication . Yahia, Youssef; Lopes, Júlio Castro; Bezerra, Eduardo; Rodrigues, Pedro João; Lopes, Rui PedroUsing computer vision for the classification of an object’s 3D position using a 2D camera is a topic that has received some attention from researchers over the years. Visual data is interpreted by the computer to recognize the objects found. In addition, it is possible to infer their orientation, evaluating their spatial arrangement, rotation, or alignment in the scene. The work presented in this paper describes the training and selection of a siamese neural network for classifying the 3D orientation of cars using 2D images. The neural network is composed of an initial phase for feature selection through convolutional neural networks followed by a dense layer for embedding generation. For feature selection, four architectures were tested: VGG16, VGG19, ResNet18 and ResNet50. The best result of 95.8% accuracy was obtained with the VGG16 and input images preprocessed for background removal.
- Assessment of honey bee cells using deep learningPublication . Alves, Thiago da Silva; Ventura, Paulo J.C.; Neves, Cátia J.; Candido Junior, Arnaldo; Paula Filho, Pedro L. de; Pinto, M. Alice; Rodrigues, Pedro JoãoTemporal assessment of honey bee colony strength is required for different applications in many research projects. This task often requires counting the number of cells with brood and food reserves multiple times a year from images taken in the apiary. There are thousands of cells in each frame, which makes manual counting a time-consuming and tedious activity. Thus, the assessment of frames has been frequently been performed in the apiary in an approximate way by using methods such as the Liebefeld. The automation of this process using modern imaging processing techniques represents a major advance. The objective of this work was to develop a software capable of extracting each cell from frame images, classify its content and display the results to the researcher in a simple way. The cells’ contents display a high variation of patterns which added to light variation make their classification by software a challenging endeavor. To address this challenge, we used Deep Neural Networks (DNNs) for image processing. DNNs are known by achieving the state-of-art in many fields of study including image classification, because they can learn features that best describe the content being classified, such as the interior of frame cells. Our DNN model was trained with over 60,000 manually labeled images whose cells were classified into seven classes: egg, larvae, capped larvae, honey, nectar, pollen, and empty. Our contribution is an end-to-end software capable of doing automatic background removal, cell detection, and classification of its content based on an input image. With this software the researcher is able to achieve an average accuracy of 94% over all classes and get better results compared with approximation methods and previous techniques that used handmade features like color and texture.
- Autent+ Desenvolvimento de abordagem inovadoras com vista à valorização e exploração do potencial de mercado do mel PortuguêsPublication . Amaral, Joana S.; Quaresma, Andreia; Rodrigues, Pedro João; Rufino, José; Henriques, Dora; Calaim, Luís; Gaspar, Albino; Pinto, M. AliceA FENAPICOLA candidatou-se, como proponente, a uma medida de investigação aplicada, tendo convidado o Instituto Politécnico de Bragança (IPB) como entidade parceira, envolvendo este último uma equipa multidisciplinar de 6 investigadores provenientes dos centros de investigação CIMO (Centro de Investigação de Montanha) e CEDRI (Centro de Investigação em Digitalização e Robótica Inteligente). Assim foi criado o projeto AUTENT+, um projeto financiado pelo Instituto de Financiamento da Agricultura e Pescas (IFAP), em resultado da candidatura submetida ao Plano Apícola Nacional (PAN) 2020/2022, medida 5.1 "Apoio a projetas de investigação aplicada”. O AUTENT + tem como principal objetivo a valorização do mel nacional como um produto autêntico e sustentável, através de abordagens que visam diferenciar, acrescentar valor e o potencial de mercado a este produto. Para tal, o projeto centra-se no desenvolvimento de metodologias inovadoras com vista à deteção de adulterações do mel, em particular no que respeita à origem botânica e entomológica/geográfica, e no desenvolvimento de ferramentas que permitam , de uma forma simples, informar o consumidor sobre as caraterísticas do produto que adquirem.
- Automatic detection and classification of honey bee comb cells using deep learningPublication . Alves, Thiago da Silva; Pinto, M. Alice; Ventura, Paulo J.C.; Neves, Cátia J.; Biron, David G.; Candido Junior, Arnaldo; Paula Filho, Pedro L. de; Rodrigues, Pedro JoãoIn a scenario of worldwide honey bee decline, assessing colony strength is becoming increasingly important for sustainable beekeeping. Temporal counts of number of comb cells with brood and food reserves offers researchers data for multiple applications, such as modelling colony dynamics, and beekeepers information on colony strength, an indicator of colony health and honey yield. Counting cells manually in comb images is labour intensive, tedious, and prone to error. Herein, we developed a free software, named DeepBee©, capable of automatically detecting cells in comb images and classifying their contents into seven classes. By distinguishing cells occupied by eggs, larvae, capped brood, pollen, nectar, honey, and other, DeepBee© allows an unprecedented level of accuracy in cell classification. Using Circle Hough Transform and the semantic segmentation technique, we obtained a cell detection rate of 98.7%, which is 16.2% higher than the best result found in the literature. For classification of comb cells, we trained and evaluated thirteen different convolutional neural network (CNN) architectures, including: DenseNet (121, 169 and 201); InceptionResNetV2; InceptionV3; MobileNet; MobileNetV2; NasNet; NasNetMobile; ResNet50; VGG (16 and 19) and Xception. MobileNet revealed to be the best compromise between training cost, with ~9 s for processing all cells in a comb image, and accuracy, with an F1-Score of 94.3%. We show the technical details to build a complete pipeline for classifying and counting comb cells and we made the CNN models, source code, and datasets publicly available. With this effort, we hope to have expanded the frontier of apicultural precision analysis by providing a tool with high performance and source codes to foster improvement by third parties (https://github.com/AvsThiago/DeepBeesource).
- Automatic tracking of red blood cells in micro channels using OpenCVPublication . Rodrigues, Vânia; Rodrigues, Pedro João; Pereira, Ana I.; Lima, Rui A.; Rodrigues, VâniaThe present study aims to develop an automatic method able to track red blood cells (RBCs) trajectories flowing through a microchannel using the Open Source Computer Vision (OpenCV). The developed method is based on optical flux calculation assisted by the maximization of the template-matching product. The experimental results show a good functional performance of this method.
- Avaliação da composição química e atividade antimicrobiana do óleo essencial de bagas de zimbro (Juniperus communis L.)Publication . Falcão, Soraia; Bacém, Isabel; Igrejas, Getúlio; Rodrigues, Pedro João; Vilas-Boas, Miguel; Amaral, Joana S.As bagas do zimbro (Juniperus communis L.) são usadas na gastronomia de diferentes países Europeus, sendo consideradas a única especiaria obtida de plantas da família Cupressaceae e um dos poucos exemplos de especiarias produzidas em regiões de clima temperado [1]. Em Trás-os-Montes, são tradicionalmente utilizadas como condimento em pratos de carne de caça, com o objetivo de lhes conferir um aroma e sabor particulares. A nível mundial, são ainda frequentemente utilizadas na aromatização de bebidas, tais como o gin e bebidas tradicionais. As bagas de zimbro estão também descritas como tendo atividade diurética, estomáquica e antisséptica, estando o óleo essencial de bagas de zimbro inscrito em diferentes farmacopeias. Neste trabalho, foram avaliadas 3 amostras de óleo essencial de bagas de zimbro, sendo uma obtida por extração em sistema de Clevenger a partir de bagas colhidas em Portugal (OE1) e duas amostras comerciais (OE2 e OE3). A análise foi realizada por cromatografia gasosa com deteção por espetrometria de massa (GC-MS), permitindo a identificação de um total de 97 compostos. Os três óleos essenciais estudados evidenciaram perfis químicos distintos: OE1 apresentou como compostos maioritários α-pineno (41,6%), β-pineno (27,6%) e limoneno (6,4%), OE2 apresentou α-pineno (31,1%), β-mirceno (16,3%) e sabineno (7,5%), enquanto que OE3 apresentou δ-cadineno (16,0%), α-pineno (12,2%) e sabineno (9,4%). O perfil químico distinto dos óleos essenciais foi ainda evidenciado pela análise de componentes principais (PCA), obtendo-se uma clara separação das amostras analisadas. Numa das amostras comerciais, foi detetada a presença de propaclor, um herbicida banido na União Europeia. Todos os óleos essenciais demonstraram ter atividade antimicrobiana relevante, uma vez que apresentaram atividade microbicida contra Candida albicans e pelo menos seis das dez bactérias testadas. Um dos óleos comerciais evidenciou um potencial antimicrobiano superior, inibindo o crescimento de todos os microrganismos testados (MIC entre 0,039 a 1,25%, v/v), o que poderá estar relacionado com o seu conteúdo superior em sesquiterpenos, particularmente em sesquiterpenos oxigenados.