SMSamuel Macedo

Samuel Macedo

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Samuel Macedo has a total of 29 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Digital platform for experimental and technical support to the cultivation of cactus pear

    by Bruno Vinícius Castro Guimarães, Sérgio Luiz Rodrigues Donato, Ignacio Aspiazú, Alcinei Mistico Azevedo, Fábio dos Santos Lima, Samuel Victor Medeiros de Macêdo, Cleiton Fernando Barbosa Brito, Hiago Fagundes Couto

    Among the forage species, especially in semiarid ecosystems, cactus pear is exceptional because of its high tolerance to adverse conditions and high productivity. Due to this alone, several studies have been conducted to identify the main technologies for this crop. Despite being consolidated and integrated, the cactus pear production system has limited accessibility, technical assistance, and availability of information for those dedicated to its production. This study aimed to present a digital platform, website, and applications to provide technical information on the cactus pear and demonstrate the efficiency of these applications through experimental data. On this digital platform, applications were made available for predicting the productivity of cactus pear using artificial neural networks (ANN) on a computer with routines in the R software and by simple linear regression (SLR) on smartphones on the Android system of the MIT App Inventor 2 platform. In addition, using the smartphone app, it is possible to obtain the cladode area through multiple linear regression (MLR). It is also possible to obtain the estimates of the experimental plot sizes by the maximum modified curvature, linear and quadratic methods with plateau response, relative information, comparison of variances, and convenient plot size. The platform provides technical information associated with the cactus pear crop from different sources (dissertations, theses, articles) and formats (video classes and teaching resources), offline for applications, and online with download for publications, dissertations, theses and articles, video classes, and several didactic resources. The biomathematical models integrated with the applications were highly precise in predicting the phenomena, in which the variation explained by the models in the prediction of responses for future observations had R² values of 0.95, 0.72, and 0.92, respectively, for productivity with computer-ANN and smartphone-SLR, and for the cladode area with a smartphone - MLR.


  • Open Access

    Local Processing of Massive Databases with R: A National Analysis of a Brazilian Social Programme

    by Hellen Paz, Mateus Maia, Fernando Moraes, Ricardo Lustosa, Lilia Costa, Samuel Macêdo, Marcos E. Barreto, Anderson Ara

    The analysis of massive databases is a key issue for most applications today and the use of parallel computing techniques is one of the suitable approaches for that. Apache Spark is a widely employed tool within this context, aiming at processing large amounts of data in a distributed way. For the Statistics community, R is one of the preferred tools. Despite its growth in the last years, it still has limitations for processing large volumes of data in single local machines. In general, the data analysis community has difficulty to handle a massive amount of data on local machines, often requiring high-performance computing servers. One way to perform statistical analyzes over massive databases is combining both tools (Spark and R) via the sparklyr package, which allows for an R application to use Spark. This paper presents an analysis of Brazilian public data from the Bolsa Família Programme (BFP—conditional cash transfer), comprising a large data set with 1.26 billion observations. Our goal was to understand how this social program acts in different cities, as well as to identify potentially important variables reflecting its utilization rate. Statistical modeling was performed using random forest to predict the utilization rated of BFP. Variable selection was performed through a recent method based on the importance and interpretation of variables in the random forest model. Among the 89 variables initially considered, the final model presented a high predictive performance capacity with 17 selected variables, as well as indicated high importance of some variables for the observed utilization rate in income, education, job informality, and inactive youth, namely: family income, education, occupation and density of people in the homes. In this work, using a local machine, we highlighted the potential of aggregating Spark and R for analysis of a large database of 111.6 GB. This can serve as proof of concept or reference for other similar works within the Statistics community, as well as our case study can provide important evidence for further analysis of this important social support programme.


  • Open Access

    A comparative study of grayscale conversion techniques applied to SIFT descriptors

    by Samuel Macêdo, Givânio Melo, Judith Kelner

    In computer vision, gradient-based tracking is usually performed from monochromatic inputs. However, a few research studies consider the influence of the chosen color-tograyscale conversion technique. This paper evaluates the impact of these conversion algorithms on tracking and homography calculation results, both being fundamental steps of augmented reality applications. Eighteen color-to-greyscale algorithms were investigated. These observations allowed the authors to conclude that the methods can cause significant discrepancies in the overall performance. As a related finding, experiments also showed that pure color channels (R, G, B) yielded more stability and precision when compared to other approaches. Nenhum resumo disponível


  • A Comparative Study of Grayscale Conversion Techniques Applied to Descriptor Based Tracking

    by Samuel Macedo, Givanio Melo, Judith Kelner

    In computer vision, gradient-based tracking is usually performed from monochromatic inputs. However, few researches consider the influence of the chosen color-to-grayscale conversion technique. This paper evaluates the impact of these conversion algorithms on tracking and homography calculation results, both being fundamental steps of augmented reality applications. Eighteen color-to-greyscale algorithms were investigated. These observations allowed to conclude that the methods can cause significant discrepancy in the overall performance. As a related finding, experiments also showed that pure color channels (R, G, B) yielded more stability and precision when compared to other approaches.


  • Uncalibrated Image Rectification for Coplanar Stereo Cameras

    by Vinícius Cesar, Thiago Farias, Saulo Pessoa, Samuel Macedo, Judith Kelner, Ismael Santos

  • SKen: A Statistical Test for Removing Outliers in Optical Flow - A 3D Reconstruction Case

    by Samuel Macedo, Luis Vasconcelos, Vinicius Cesar, Saulo Pessoa, Judith Kelner

  • Open/Closed Hand Classification Using Kinect Data

    by Joao Marcelo Teixeira, Bernardo Reis, Samuel Macedo, Judith Kelner

    This work proposes a study over five different hand gesture classifiers using depth and skeleton data from the Kinect sensor. Evaluations of sensibility, specificity and computational costs are performed for the purpose of choosing which methods are the most adequate. In spite of the low computational complexity of the tested classifiers, the results obtained are of similar quality compared to other complex approaches. All tested classifiers have been gathered in an open-source library for hand classification using the Kinect.


  • Towards a Standalone Methodology for Robust Algorithms Evaluation: A Case Study in 3D Reconstruction

    by Samuel Macêdo, Thiago Farias, Juliane Lima, Judith Kelner, Eduardo Albuquerque

    In the field of 3D reconstruction there are two main challenging tasks that require careful consideration, namely, feature detection and matching. The corresponding automatic process introduces noise resulting from the image capture and spurious features matching. A number of robust algorithms for hypothesis evaluation have been suggested, they would deal with these limitations by removing outliers. Most of these works are merely comparisons to previous algorithms and lack any standalone evaluation. This paper attempts to fill this gap by introducing a novel and robust statistical methodology. It has the advantage of evaluating related algorithms using non-dimensional metrics for fixed and continuous intervals. In addition, the proposed methodology is validated using a proof of concept scenario based on the 3D pose estimation phase in the 3D reconstruction pipeline. The obtained results are very promising and emphasize the methodology's generic nature, clearing the way for its application in a multitude of scenarios, such as computer vision and 3D reconstruction.