A5029813227- Genetic and phenotypic traits in livestock
- Genetic Mapping and Diversity in Plants and Animals
- African Botany and Ecology Studies
- Global Trade and Competitiveness
- Agriculture and Rural Development Research
- Evolutionary Algorithms and Applications
- Soil and Land Suitability Analysis
- Gene expression and cancer classification
- Agricultural and Food Sciences
- Remote-Sensing Image Classification
- Genetics and Plant Breeding
- Smart Agriculture and AI
Universidade Federal de Viçosa
2019-2020
Genome-Wide Selection (GWS) uses molecular markers to predict the genetic merit of animals and plants.Usually, a high density this is used.Thus, statistical methods need deal with problems dimensionality, multicollinearity computational efficiency.We examined set machine learning methods, in particular treebased regression (Regression Tree, Bagging, Random Forest Boosting) evaluated them relation predictive ability bias.Moreover, these were compared Bayesian Least Absolute Shrinkage Operator...
We compared two statistical methodologies applied to genetic and genomic analyses of categorical traits.The first one consists a Bayesian approach the Linear Mixed Model (BLMM), which addresses problems prediction.The second methodology, called Generalized (BGLMM) is similar, but it used when distribution response variable not Gaussian, as in case disease resistance phenotype categories.These models were according predictive ability, bias, computational time cross validation error rate...
Artificial neural networks (ANNs) are powerful nonparametric tools for estimating genomic breeding values (GEBVs) in genetic breeding. One significant advantage of ANNs is their ability to make predictions without requiring prior assumptions about data distribution or the relationship between genotype and phenotype. However, come with a high computational cost, may be underestimated when including all molecular markers. This study proposes two-step prediction procedure using address these...
The objective of this work is to develop a system identify areas cultivated with coffee using ANNs having as input variables descriptors Haralick. We used the training algorithm Back-propagation and Levenberg -Marquardt method. There were two cases study: in first step, ANN was trained representative samples each class interest (coffee, forest, water, bare soil, urban area), thus verifying potential discriminate output classes; second step classify plantations accordingly age. For evaluation...