Brazilian Journal of Biometrics

Classification of sugarcane areas in Landsat images using machine learning algorithms

Ana Clara Arantes Villas Bôas de Barros — 2024-04-15

Monitoring sugarcane areas through remote sensing is essential for planning and management of the national sugarcane industry. The use of machine learning algorithms has provided many benefits to remote sensing. This article aims to compare the prediction quality of three important machine learning methods in identifying sugarcane areas using Landsat images: Logistic Regression (LR), Decision Tree (DT) and RandomForest (RF). LR was applied in three versions: LR without penalization, LR with Ridge penalization (LR-R) and LR with Lasso penalization (LR-L). Data obtained in this study refer to a region of approximately 306,000 ha located in the state of São Paulo, Brazil, which was segmented into approximately 46,000 polygons (observations). Six spectral bands and vegetation indices observed along 17 months resulted in 102 covariates, which were reduced via Principal Component Analysis (PCA). In total, 19 Principal Components were chosen to account for 94.61% of the cumulative explained variance ratio and were used in machine learning methods to classify each polygon as sugarcane or other land covers. The method with the highest accuracy considering testing sample of 20% of data was RF (78.51%), followed by DT (72.30%), LR-L (69.64%), LR-R (69.64%), and LR (69.52%).

Probabilistic Modeling of the Coffee Market in Brazil

Otávio Magno Teixeira — 2024-04-15

The coffee is one of the most valuable commodities in the world and in this scenario, Brazil presents itself as the largest producer and exporter in the world. However, the high fluctuations in prices promote insecurity in the agents of the sector. In this sense, the objective of this work is to propose the best probabilistic model for the monthly analysis of prices and to calculate probabilities of occurrences of average prices of coffee bags according to levels of practical interest. To this end, we use historical data provided by COOXUPÉ corresponding to the period from January 1981 to December 2022, arranged into monthly subseries. For supporting the results, goodness of fit test were performed. The results indicated that the Gamma and log-Normal distributions fit the coffee bag price data in all months. The log-Normal distribution outperformed in all months. The Gamma and log-Normal distributions fitted the monthly data of average coffee bags prices. The Log-Normal distribution is more suitable for the probabilistic study of the variable in all months. January, February, and March are the months with the highest probability of higher average values and are therefore the most recommended for coffee trading.

Reliability of repairable systems with Non-Central Gamma frailty

Adriane Caroline Teixeira Portela — 2024-04-15

Maintenance actions on industrial equipment are essential to reduce expenses associated with equipment failures. Based on a well-fitted model, it is possible, through the estimated parameters, to predict several functions of interest, such as the cumulative average and reliability functions. In this paper, a new frailty model is proposed to analyze failure times of repairable systems subject to unobserved heterogeneity actions. The Non-Central Gamma distribution is assumed to the frailty random variable effect. The class of minimal repair models for repairable systems is explored considering an approach that includes the frailty term to estimate the unobserved heterogeneity over the systems’ failure process. Classical inferential methods were used to parameter estimation and define the reliability prediction functions. A simulation study was conducted to confirm the properties expected in the estimators. Two real-world data known in literature were used to illustrate the estimation procedures and validate the proposed model as a viable alternative to those already established in the literature. The results obtained highlight the potential of our proposed approach, particularly for industries dealing with such systems, where unquantifiable factors may impact equipment failure times.

Analysis of environmental sustainability perception in Paraná Basin III residents via Item Response Theory

Renan Barufaldi Bueno — 2024-04-15

Environmental sustainability perception encompasses an individual’s ability to process and interpret sensory information related to the environment. This understanding guides them to consciously and actively protect and care for the environment through continuous learning. This article aims to analyze the environmental sustainability perception of residents of the Paraná Basin III using IRT models for polytomous items, relating it to socio-economic and location characteristics. The choice to conduct the research in this Brazilian territory is driven by the hydrographic basin’s substantial influence on the Itaipu hydroelectric power plant and its significance as a crucial water resource for the region. Results showed that: (1) 13.1% of residents have a low perception of sustainability, (2) there were significant differences in perception between cities, with Toledo having the lowest values, and (3) there was a positive relationship between remuneration and perception of sustainability. By analyzing the results presented, it becomes possible to develop effective public policies to improve the region’s perception of sustainability.

Bayesian analysis of the growth of pears in the cultivate Shinseiki using non-linear models

Gabriela Rodrigues — 2024-04-15

The pear of the Pyrus genus is the third most consumed fruit in Brazil, however, internal production is low and most demand is obtained through imports. Brazil has favorable conditions for its cultivation and one of its main economic sectors is agriculture, being responsible for generating a large number of jobs and income for the country. In this sense, studies related to this fruit can provide information and encourage its production. Using non-linear models, it is possible to identify growth patterns such as fruit length and diameter, which can help determine the ideal harvest point. Therefore, the goal of this article was to compare the Logistic and Gompertz non-linear models in describing the growth curves in diameter and length of the Asian pear tree using the Bayesian approach. The results indicated the Logistic model as the best to describe these two variables and provided asymptotic averages of 70.0607 and 79.706 for length and diameter, respectively.

Linear mixed-effects models and least confounded residuals in the modelling of Holstein calves’ performance

Allison Queiroz de Oliveira — 2024-04-15

Some experimental studies are carried out considering a longitudinal feature. In view of this, the classical regression models are not able to handle with it, since the independence assumption between the observations is violated. To handle with this kind of data it was proposed the called linear mixed-effects models, where it is possible to model the response variable taking into account the correlation between the observations, and even between the response variables, when there are two or more of them in study, setting a bivariate or multivariate scenario, respectively. For the diagnosis of the linear mixed-effects models the least confounded residuals are quite recommended due to their lower bias in relation to other types of residuals, but it is not so used in the literature. Using a data set of dairy calves’ performance according to three different diets over eight weeks, the linear mixed-effects models theory under univariate and bivariate approach was applied alongside the least confounded residuals in the diagnosis of the model for both approaches. Comparing the univariate and bivariate approaches, the last one was more informative presenting lower standard errors’ values for its estimates, while the least confounded residuals was more efficient than the classical residuals present in the literature.

Sequential Bayesian approach for genetic diversity analysis of the piracanjuba fish (Brycon orbignyanus)

Isabela da Silva Lima — 2024-04-15

In the sequential Bayesian approach, the sample size is not fixed before the experiment; it is determined based on the observations made. The procedure concludes when there is enough information to estimate the parameters, according to a stopping criterion. A parameter of interest in population genetics is the proportion obtained from the allele frequency at one or more loci to verify Hardy-Weinberg equilibrium (HWE). The objective of this study was to assess the occurrence of HWE in a population of piracanjuba fish (Brycon orbignyanus) by estimating the allele proportion and expected genotype proportions using a sequential Bayesian approach. Additionally, a comparison was made with frequentist and Bayesian approaches. Initially, genotypic profiles were analyzed at a microsatellite DNA locus, Bh6, in 49 fish, to determine the frequency of observed alleles and genotypes at the UFSJ Genetic Resources Laboratory. Seven allele classes were observed; thus, under the assumption of sampling independence, the likelihood is multinomial. The estimation of allele and genotype proportions was then carried out using frequentist, Bayesian, and sequential Bayesian approaches. A uniform prior and a cost of 10–3 were considered. The estimates from the three approaches were compared, and it was concluded that the sequential approach proved effective, utilizing only 55.1% of the available data, thereby reducing the sample size and optimizing the procedure. Using a chi-square test at a 5% probability level, it was concluded that the studied sample is in Hardy-Weinberg equilibrium (p-value: 0.9800245).

Special issue on (bio)statistics and biometrics in the age of the digital revolution

Rodrigo Pescim — 2024-04-15

This special issue explores the thematic areas presented at the 67th Reunião da Região Brasileira da Sociedade Internacional de Biometria (RBras) and 20th Simpósio de Estatística Aplicada à Experimentação Agronômica (SEAGRO).