Tiago Almeida de Oliveira

Dr. Tiago Almeida de Oliveira

orcid
avatar
Co-authors
avatar
Following
avatar
Followers

Research Focus & Metrics

Explore full metrics on Scilit

Academic Career Length

7Years (2020-Present)

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

Representative Publications

View All Publications
20 September 2024 in Animals
Verified
Journal Article
Open access
PDF file
FBFernando De Oliveira Bussiman
Fernando De Oliveira Bussiman
Anderson A. AlvesAnderson A. Alves
Anderson A. Alves
JRJennifer Richter
Jennifer Richter
Jorge HidalgoJorge Hidalgo
Jorge Hidalgo
RVRenata Veroneze
Renata Veroneze
TOTiago Almeida de Oliveira
Tiago Almeida de Oliveira
Gait scores are widely used in the genetic evaluation of horses. However, the nature of such measurement may limit genetic progress since there is subjectivity in phenotypic information. This study aimed to assess the application of machine learning techniques in the prediction of breeding values for five visual gait scores in Campolina horses: dissociation, comfort, style, regularity, and development. The dataset contained over 5000 phenotypic records with 107,951 horses (14 generations) in the pedigree. A fixed model was used to estimate least-square solutions for fixed effects and adjusted phenotypes. Variance components and breeding values (EBV) were obtained via a multiple-trait model (MTM). Adjusted phenotypes and fixed effects solutions were used to train machine learning models (using the EBV from MTM as target variable): artificial neural network (ANN), random forest regression (RFR) and support vector regression (SVR). To validate the models, the linear regression method was used. Accuracy was comparable across all models (but it was slightly higher for ANN). The highest bias was observed for ANN, followed by MTM. Dispersion varied according to the trait; it was higher for ANN and the lowest for MTM. Machine learning is a feasible alternative to EBV prediction; however, this method will be slightly biased and over-dispersed for young animals.
6 March 2025 in Insects
Verified
Journal Article
Open access
PDF file
JRJohanna Ramirez-Diaz
Johanna Ramirez-Diaz
AMArianna Manunza
Arianna Manunza
TOTiago Almeida de Oliveira
Tiago Almeida de Oliveira
TBTania Bobbo
Tania Bobbo
FNFrancesco Nutini
Francesco Nutini
GMGiulietta Minozzi
Giulietta Minozzi
Bees are crucial for food production and biodiversity. However, extreme weather variation and harsh winters are the leading causes of colony losses and low honey yields. This study aimed to identify the most important features and predict Total Honey Harvest (THH) by combining machine learning (ML) methods with climatic conditions and environmental factors recorded from the winter before and during the harvest season. The initial dataset included 598 THH records collected from five apiaries in Lombardy (Italy) during spring and summer from 2015 to 2019. Colonies were classified into medium-low or high production using the 75th percentile as a threshold. A total of 38 features related to temperature, humidity, precipitation, pressure, wind, and enhanced vegetation index–EVI were used. Three ML models were trained: Decision Tree, Random Forest, and Extreme Gradient Boosting (XGBoost). Model performance was evaluated using accuracy, sensitivity, specificity, precision, and area under the ROC curve (AUC). All models reached a prediction accuracy greater than 0.75 both in the training and in the testing sets. Results indicate that winter climatic conditions are important predictors of THH. Understanding the impact of climate can help beekeepers in developing strategies to prevent colony decline and low production.
18 June 2020 in Research, Society and Development
Verified
Journal Article
Open access
PDF file
SJSilvio Fernando ALVES XAVIER JÚNIOR
Silvio Fernando ALVES XAVIER JÚNIOR
ÉXÉrika Fialho Morais Xavier
Érika Fialho Morais Xavier
JJJader da Silva Jale
Jader da Silva Jale
TOTiago Almeida de Oliveira
Tiago Almeida de Oliveira
ASAntonio Leopoldo Cardoso Sabino
Antonio Leopoldo Cardoso Sabino
We study the daily precipitation in the municipality of Campina Grande, estimating the parameters of Gamma, Log-Normal, and Weibull distributions. To evaluate the parameter estimators, we compared the Particle Swarm Optimization (PSO) versus Maximum Likelihood Estimation (MLE) to analyze and understand the behaviour of the daily precipitation in Campina Grande. In most cases, our results show evidence that the PSO algorithm is an efficient and robust technique. Notwithstanding, the algorithm also presents an efficient parameter estimation due to its fast convergence.
10 March 2025 in Applied Sciences
Verified
Journal Article
Open access
PDF file
RGRuth Luna do Nascimento Gonçalves
Ruth Luna do Nascimento Gonçalves
ACAnna Carolina Amorim Costa
Anna Carolina Amorim Costa
Mário César de Siqueira LimaMário César de Siqueira Lima
Mário César de Siqueira Lima
KNKarine Nóbrega
Karine Nóbrega
WCWaleska Rodrigues Pontes da Costa
Waleska Rodrigues Pontes da Costa
LALuciana Viana Amorim
Luciana Viana Amorim
Palygorskite has shown satisfactory performance in salted water-based fluids, especially as a rheological agent. However, this type of formulation has been used in the petroleum industry only in well drilling operations. This study proposes the development of a salted water-based fluid with palygorskite, which presents an adequate performance as a liquid barrier element in temporary abandonment operations of wells. Based on a factorial design, seven fluid formulations were prepared with varying concentrations of palygorskite and PAC LV and were tested by measuring the HPHT filtrate volume, rheological properties, density, and pH. For comparison purposes, the results of the seven formulations were evaluated against a formulation without palygorskite and analyzed for their performance in abandonment operations. The results showed that the presence of palygorskite reduces filtrate volumes by at least 21%, thereby helping control the pressure exerted by the fluid column, which is the primary requirement for abandonment operations. Furthermore, the fluid that contained the highest amount of palygorskite and PAC LV (20 g and 8 g, respectively) showed the best results regarding filtrate control (11.2 mL) and solid sedimentation. Therefore, it is a very promising alternative for use as a well barrier element in the temporary abandonment of wells.
6 December 2023 in Processes
Verified
Journal Article
Open access
PDF file
WCWaleska Rodrigues Pontes da Costa
Waleska Rodrigues Pontes da Costa
LOLaura Rafaela Cavalcanti de Oliveira
Laura Rafaela Cavalcanti de Oliveira
KNKarine Nóbrega
Karine Nóbrega
ACAnna Carolina Amorim Costa
Anna Carolina Amorim Costa
RGRuth Luna do Nascimento Gonçalves
Ruth Luna do Nascimento Gonçalves
LALuciana Viana Amorim
Luciana Viana Amorim
One of the operational challenges regarding the use of bentonite pellets as sealing materials in the abandonment of offshore fields consists of their placement inside the well. This study aimed to analyze the interaction of fluid media, consisting of saline solutions (NaCl, CaCl2 and KCl) and organic compounds (diesel, glycerin and olefin), with bentonite pellets, for their applications as displacement fluids in offshore oil well abandonment operations. The physical integrity of the bentonite pellets in contact with the fluids was verified through visual inspections and dispersibility tests. Linear swelling tests were also performed to evaluate the swelling potentials of the pellets in deionized water after their contact with the fluid media. The results indicated that the NaCl, CaCl2 and KCl solutions completely compromised the physical integrity of the pellets, while diesel and olefin showed the best responses regarding the structural preservation. Furthermore, the linear swelling tests showed that, even after the contact with diesel and olefin for 1 h, the bentonite pellets reached a total swelling of 78% in water after 24 h. In this way, diesel and olefin proved to be highly promising alternatives to be used as displacement fluids for bentonite pellets in wells that will be abandoned in a submarine environment.
17 September 2020 in Research, Society and Development
Verified
Journal Article
Open access
PDF file
GFGlaucia Amorim Faria
Glaucia Amorim Faria
APAna Patricia Bastos Peixoto
Ana Patricia Bastos Peixoto
AMAugusto Ramalho de Morais
Augusto Ramalho de Morais
TCTáis Ferreira Costa
Táis Ferreira Costa
COCintia Patrícia Martins de Oliveira
Cintia Patrícia Martins de Oliveira
LFLucas Menezes Felizardo
Lucas Menezes Felizardo
As espécies do gênero Passiflora apresentam grande importância comercial, ornamental e fitoterapêutica. Contudo, são escassas as informações sobre o tamanho ideal de parcelas em experimentos visando o estabelecimento in vitro de Passiflora. Este trabalho teve por objetivo determinar o tamanho ótimo de parcelas em experimentos de estabelecimento in vitro das espécies de Passiflora edulis Sims f. edulis, Passiflora giberti N. E. Brown. e Passiflora laurifolia L. Para cada espécie foram conduzidos ensaios de uniformidade com duas concentrações de sais do meio de cultura (MS e ½ MS) e em cada ensaio realizaram-se avaliações aos 45, 75 e 105 dias após incubação dos explantes. Em cada avaliação e meio de cultura foram simulados diversos tamanhos de parcelas, variando de uma (1) unidade básica até 50 por parcela, sendo cada unidade básica constituída por uma planta. Para a estimação do tamanho ótimo de parcelas empregou-se o método da máxima curvatura modificado. Em experimentos de estabelecimento in vitro o tamanho ótimo de parcela recomendado deve ser o de 11 explantes para P. edulis Sims f. edulis, de 15 explantes para P. giberti N. E. Brown. e de 9 explantes para P. laurifolia L..