João Gustavo Atkinson Amorim

João Gustavo Atkinson Amorim

Auto-generated profile, based on publicly available information

João Gustavo Atkinson Amorim

Department of Informatics and Statistics, Federal University of Santa Catarina, Florianópolis, Brazil

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
26 March 2022 in Applied Artificial Intelligence
Verified
Journal Article
Closed access
LSLincoln Vinicius Schreiber
Lincoln Vinicius Schreiber
JAJoão Gustavo Atkinson Amorim
João Gustavo Atkinson Amorim
LGLeticia Guimarães
Leticia Guimarães
DMDebora Motta Matos
Debora Motta Matos
CCCelso Maciel da Costa
Celso Maciel da Costa
APAdriane Parraga
Adriane Parraga
Evaluation of biomass is essential in agriculture to delineate crop management practices, and this is usually done manually, which is time-consuming and destructive. This work proposes an artificial neural network and convolutional neural network to estimate the above-ground biomass (AGB) of wheat using visible spectrum images captured by an unmanned aerial vehicle. The utilized dataset has two Brazilian wheat types, called Parrudo and Toruk. Furthermore, the experimental area has variability in crop growth by varying the amount of nitrogen. To determine AGB, samples of plants were collected at three different crop growth stages, approximately a month apart, making our database spatial and temporal variability. We have shown the feasibility of developing a regression model using RGB images for biomass estimation for two wheat types. The best results for ANN were 489.5, 826.4, and 0.9056 for MAE, RMSE, and R2, respectively. In CNN, MAE = 699.2, RMSE = 940.5, and R2 = 0.9065. These results show high accuracy in estimation of biomass, and the R2 shows good estimation and generalization capacity. The results demonstrate that our methodology can be used in precision agriculture to predict the spatial and temporal variability of AGB.

3 July 2022 in International Journal of Remote Sensing
Verified
Journal Article
Closed access
JAJoão Gustavo Atkinson Amorim
João Gustavo Atkinson Amorim
LSLincoln Vinicius Schreiber
Lincoln Vinicius Schreiber
MSMirayr Raul Quadros de Souza
Mirayr Raul Quadros de Souza
MNMarcelo Negreiros
Marcelo Negreiros
ASAltamiro Susin
Altamiro Susin
APAdriane Parraga
Adriane Parraga
Remote biomass estimation can benefit agricultural practices in several ways, especially larger areas since it does not require local measurements. The advances of the last few decades in machine learning techniques have created new possibilities for estimating aboveground biomass. A pipeline was established from image acquisition to modelling shoot biomass of two wheat cultivars used in Southern Brazil (TBIO Toruk and BRS Parrudo). A UAV was used to acquire multispectral images with high spatial resolution to calculate vegetation indices (VIs). These VIs along with machine learning approaches are used to model the measured biomass of crops in different growth phases. To correlate the wheat images with measured shoot dry biomass, the following regression models were investigated: random forest, support vector regression, and artificial neural networks. An experiment was designed and conducted at the Agriculture Experimental Station of the Federal University of Rio Grande do Sul (EEA/UFRGS) to assess wheat growth. Variability in crop growth was created for all test areas by varying nitrogen availability. To determine shoot biomass, plants were sampled at three different crop growth stages: V6 (stage of six fully developed leaves), three nodes, and flowering. Our results indicate the importance of the radiometric calibration used. Also, the features extracted from images, such as the VIs combined with machine learning models can be used in precision agriculture for predicting the spatial variability of shoot biomass. The best model for Brazilian wheat cultivars was an artificial neural network with R2 of 0.90, RMSE of 0.83t/ha, and nRMSE of 8.95%. We also found a strong correlation between ground NDVI with image-based NDVI, with an R2 of 0.84.

1 July 2021 in Computerized Medical Imaging and Graphics
Verified
Journal Article
Closed access
AMAndré Victória Matias
André Victória Matias
JAJoão Gustavo Atkinson Amorim
João Gustavo Atkinson Amorim
LMLuiz Antonio Buschetto Macarini
Luiz Antonio Buschetto Macarini
ACAllan Cerentini
Allan Cerentini
AOAlexandre Sherlley Casimiro Onofre
Alexandre Sherlley Casimiro Onofre
Aldo von WangenheimAldo von Wangenheim
Aldo von Wangenheim

21 May 2021 in SN Computer Science
Verified
Journal Article
Closed access
PDF file
AMAndré Victória Matias
André Victória Matias
ACAllan Cerentini
Allan Cerentini
LMLuiz Antonio Buschetto Macarini
Luiz Antonio Buschetto Macarini
JAJoão Gustavo Atkinson Amorim
João Gustavo Atkinson Amorim
FDFelipe Perozzo Daltoé
Felipe Perozzo Daltoé
Aldo von WangenheimAldo von Wangenheim
Aldo von Wangenheim

1 July 2020
Verified
Conference Paper
Closed access
JAJoao Gustavo Atkinson Amorim
Joao Gustavo Atkinson Amorim
LMLuiz Antonio Buschetto Macarini
Luiz Antonio Buschetto Macarini
AMAndre Victoria Matias
Andre Victoria Matias
ACAllan Cerentini
Allan Cerentini
FOFabiana Botelho De Miranda Onofre
Fabiana Botelho De Miranda Onofre
AWAldo Von Wangenheim
Aldo Von Wangenheim
Cervical cancer is the second most common cancer type in women. This is a deadly disease that could benefit from early detection methods. Cytology is a possible, noninvasive, alternative to biopsy for diagnosis of malignant lesions, where information about the cells can be obtained. This process consists of staining the slides being able to visualize the nuclei of the cells and then be properly diagnosed. In this work, silver-stained slides, a method known as Argyrophilic Nucleolar Organizer Regions (AgNOR), is employed. This method shows great potential for the diagnosis of the malignancy of lesions. However, it has not yet been much explored, mainly using computational methods. In this work, we propose the use of Convolutional Neural Networks on silver stained images to measure AgNOR quantitative image information. We will present the entire process, starting from pre-processing, passing through neural network training and results evaluation. The best results we obtained were 0.87 of Mean Intersection Over Union (mIoU) and 0.99 of Dice Similarity Coefficient (DSC) using an U-Net model with a ResNet18 as its backbone. The code and the dataset employed in this work are publicly available.

9 November 2018
Verified
Book Chapter
Closed access
PDF file
APAdriane Parraga
Adriane Parraga
DDDionisio Doering
Dionisio Doering
JAJoao Gustavo Atkinson
Joao Gustavo Atkinson
TBThiago Bertani
Thiago Bertani
CAClódis De Oliveira Andrades-Filho
Clódis De Oliveira Andrades-Filho
ASAltamiro Amadeu Susin
Altamiro Amadeu Susin