Fernando de Lima Alves

Dr. Fernando de Lima Alves

orcid

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
1 January 2024 in Revista Brasileira de Engenharia Agrícola E Ambiental
Verified
Journal Article
Open access
PDF file
FAFernando de Lima Alves
Fernando de Lima Alves
ESEduardo Souza
Eduardo Souza
RSRicardo Sobjak
Ricardo Sobjak
CBClaudio Leones Bazzi
Claudio Leones Bazzi
AHAntonio Marcos Massao Hachisuca
Antonio Marcos Massao Hachisuca
EMErivelto Mercante
Erivelto Mercante
Outliers and inliers often arise during sample data acquisition. While outliers represent anomalous observations, inliers are erroneous data points within the main body of the dataset. It was aimed to conduct a systematic literature study (SLS) to survey methods and software employed for outlier and inlier removal, particularly within exploratory data analysis. The study was conducted in three phases: (i) systematic literature mapping (SLM), (ii) snowballing (SB), and (iii) SLR. Initially, 772 scientific studies were identified, subsequently narrowed down to 86 after applying selection criteria. Backward (BSB) and forward (FSB) snowballing further yielded 16 studies, resulting in a final pool of 102 studies for analysis. It was identified three outlier removal techniques (Chebyshev’s inequality, boxplot, and principal component analysis), one inlier removal technique (local Moran’s index), and thirteen commonly used software.

16 October 2023 in Communications in Soil Science and Plant Analysis
Verified
Journal Article
Closed access
WOWendel Kaian Mendonça Oliveira
Wendel Kaian Mendonça Oliveira
ESEduardo Souza
Eduardo Souza
HBHumberto Martins Beneduzzi
Humberto Martins Beneduzzi
RSRicardo Sobjak
Ricardo Sobjak
CBClaudio Leones Bazzi
Claudio Leones Bazzi
Marlon RodriguesMarlon Rodrigues
Marlon Rodrigues

14 August 2026 in Agronomy
Verified
Journal Article
Open access
PDF file
FAFernando de Lima Alves
Fernando de Lima Alves
ESEduardo Souza
Eduardo Souza
RSRicardo Sobjak
Ricardo Sobjak
CBClaudio Leones Bazzi
Claudio Leones Bazzi
Miguel Angel Uribe-OpazoMiguel Angel Uribe-Opazo
Miguel Angel Uribe-Opazo
EMErivelto Mercante
Erivelto Mercante
Yield maps (YMs) are essential precision agriculture tools for assessing spatial variability in crop yields within an agricultural area. However, their quality is often compromised by duplicate points, negative or null points, outliers, and inliers, requiring the cleaning of raw harvest monitor data. This study aimed to develop, implement, and evaluate AgDataBox-Map-Clean v4.0.2 (ADB-Clean v4.0.2), a computational web module for cleaning raw harvest monitor data and integrating it with the AgDataBox-Map (ADB-Map) application from AgDataBox v4.0.2 (ADB). ADB is a web platform that integrates data, software, procedures, and methodologies for digital agriculture, and it is the only free, all-inclusive platform worldwide. The module cleans raw yield monitor data by removing duplicate points, negative or null points, outliers, and inliers. In a case study, three cleaning software programs (web module ADB-Clean v4.0.2, Map Filter v2.0, and Yield Editor v2.0.7) were compared. The YMs constructed from data processed by the three software programs were visually similar, but their similarity to raw-data YMs (without cleaning) was much worse. On average across the evaluated datasets, the cleaning process reduced the standard deviation (SD) by 68%, the coefficient of variation (CV) by 70%, and the dataset size by 23%, while increasing the mean yield by 11%. The results demonstrate that, for the datasets evaluated in this study, automated error removal from yield monitor data is feasible and can support improved agricultural decision-making. Because its cleaning algorithms operate on georeferenced point data, the module is expected to apply to other agricultural datasets, although this capability was not evaluated in the present study.

27 November 2024
Verified
Conference Paper
Open access
PDF file
GMGabriel Costa de Moraes
Gabriel Costa de Moraes
HSHeloísa Raquel Siebeneichler
Heloísa Raquel Siebeneichler
FAFernando de Lima Alves
Fernando de Lima Alves
OSOdair Moreira de Souza
Odair Moreira de Souza
No âmbito do Instituto Federal do Paraná, Campus Cascavel, levantou-se a necessidade de desenvolver um software capaz de otimizar tarefas diárias dos estudantes e da Seção Pedagógica e de Assuntos Educacionais (SEPAE). Neste contexto, esse trabalho realizou o desenvolvimento do aplicativo MeuIF, voltado para dispositivos Android, que auxilia a SEPAE na identificação da evasão escolar, por meio de análises automáticas da frequência escolar de cada estudantes. Ademais contribuindo para o controle das retiradas do PNAE pelos discentes. Além disso, também auxilia no gerenciamento das entradas atrasadas e saídas antecipadas dos estudantes. O desenvolvimento do aplicativo MeuIF foi implementado no ambiente do Android Studio, empregando a linguagem de programação Java, enquanto as informações relevantes são armazenadas e gerenciadas via Google Cloud. Em conclusão, o desenvolvimento do aplicativo MeuIF representa um avanço significativo na otimização e simplificação das atividades diárias dos alunos e da SEPAE. Ao atender à necessidade premente de aprimoramento das operações.

12 November 2026 in SSRN Electronic Journal
Verified
Preprint
Open access
LSLeandro Pereira dos Santos
Leandro Pereira dos Santos
FAFernando de Lima Alves
Fernando de Lima Alves
Brazil's federal secondary schools kept in-person classes suspended longer than state and private schools during the COVID-19 pandemic but gave their students far more support for remote learning. We ask how federal students fared relative to students in the other networks, using ENEM results for the cohorts that completed secondary school from 2017 to 2025, School Census enrollment and INEP's survey of the pandemic response. Because the ENEM is voluntary, we measure participation against Census enrollment and compare equal shares of each network's enrolled cohort with changes-in-changes, a scale-free estimator. Participation fell by 26% in the federal network in 2020, against 39% in the state network. Without accounting for participation, federal students appear to lose ground relative to state students in every test, but the size of this decline depends on the score scale. Comparing equal shares of each cohort, in our main specification we find no evidence of a relative federal decline in Mathematics, Social Sciences, and Languages and Codes in the cohorts most affected by remote teaching, and relative losses in Natural Sciences and the Essay that are smaller than without the correction but statistically significant. These estimates are sensitive to assumptions on selection into the exam, to the enrollment denominators, to how students without an identified school are assigned and to prepandemic trends. The results show that conclusions about pandemic learning drawn from voluntary exams can change with the treatment of participation, the score scale and the estimator.