Olacir Rodrigues Castro
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Olacir Rodrigues Castro has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Aurora Pozo
UFPR
7 shared publications - Jose Antonio Lozano
Basque Center for Applied Mathematics (BCAM)
2 shared publications Roberto Santana
University of the Basque Country (UPV/EHU)
2 shared publications- Roberto Santana
University of the Basque Country
2 shared publications - Ana Beatriz Alvarez
PAVIC Laboratory, Federal University of Acre (UFAC), Rio Branco, Brazil
1 shared publication - Clécio Elias Silva E. Silva
PAVIC Laboratory, University of Acre (UFAC), Rio Branco 69915-900, Brazil
1 shared publication
Latest Publications
- Open Access
- 1 May 2025
- Published by MDPI AG in Applied Sciences
- Vol. 15 (9) , 5040
Coffee-Leaf Diseases and Pests Detection Based on YOLO Models
Coffee cultivation is vital to the global economy, but faces significant challenges with diseases such as rust, miner, phoma, and cercospora, which impact production and sustainable crop management. In this scenario, deep learning techniques have shown promise for the early identification of these diseases, enabling more efficient monitoring. This paper proposes an approach for detecting diseases and pests on coffee leaves using an efficient single-shot object-detection algorithm. The experiments were conducted using the YOLOv8, YOLOv9, YOLOv10 and YOLOv11 versions, including their variations. The BRACOL dataset, annotated by an expert, was used in the experiments to guarantee the quality of the annotations and the reliability of the trained models. The evaluation of the models included quantitative and qualitative analyses, considering the mAP, F1-Score, and recall metrics. In the analyses, YOLOv8s stands out as the most effective, with a mAP of 54.5%, an inference time of 11.4 ms and the best qualitative predictions, making it ideal for real-time applications.
- 1 May 2025
- Published by MDPI AG in Applied Sciences
- Vol. 15 (9) , 5040
Open AccessCoffee-Leaf Diseases and Pests Detection Based on YOLO Models
Coffee cultivation is vital to the global economy, but faces significant challenges with diseases such as rust, miner, phoma, and cercospora, which impact production and sustainable crop management. In this scenario, deep learning techniques have shown promise for the early identification of these diseases, enabling more efficient monitoring. This paper proposes an approach for detecting diseases and pests on coffee leaves using an efficient single-shot object-detection algorithm. The experiments were conducted using the YOLOv8, YOLOv9, YOLOv10 and YOLOv11 versions, including their variations. The BRACOL dataset, annotated by an expert, was used in the experiments to guarantee the quality of the annotations and the reliability of the trained models. The evaluation of the models included quantitative and qualitative analyses, considering the mAP, F1-Score, and recall metrics. In the analyses, YOLOv8s stands out as the most effective, with a mAP of 54.5%, an inference time of 11.4 ms and the best qualitative predictions, making it ideal for real-time applications.
- 22 March 2018
- Published by Springer Nature in Journal of Heuristics
- Vol. 24 (4) , 581-616
Evaluating selection methods on hyper-heuristic multi-objective particle swarm optimization
- 22 March 2018
- Published by Springer Nature in Journal of Heuristics
- Vol. 24 (4) , 581-616
Evaluating selection methods on hyper-heuristic multi-objective particle swarm optimization
- 1 June 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1451-1458
Combining CMA-ES and MOEA/DD for many-objective optimization
Multi-objective Estimation of Distribution Algorithms (MOEDAS) have been successfully applied to solve Multi-objective Optimization Problems (MOPs) since they are able to model dependencies between variables of the problem and then sample new solutions to guide the search to promising areas. A state-of-the-art optimizer for single-objective continuous functions that also uses probabilistic modeling is the Covariance Matrix Adaptation Evolution Strategy (CMA-ES). Different variants of CMA-ES have been proposed for MOPs however most of them are based on Pareto dominance as the main selection criterion. Recently, a new multi-objective CMA-ES called MOEA/D-CMA was proposed combining the strengths of CMA-ES with those of the multi-objective evolutionary algorithm based on decomposition (MOEA/D). Nowadays, however, researchers on MOEAs agree that combining Pareto and decomposition can be beneficial for the search on MOPs. As a result, a new MOEA has been proposed, called MOEA/DD. This algorithm modifies the MOEA/D by including a new Pareto dominance update mechanism that brings more diversity into the search. In this study, we extend the MOEA/D-CMA by replacing its update mechanism by the one of MOEA/DD. The hypothesis is that this update mechanism will improve the performance of MOEA/D-CMA as it improved MOEA/D. MOEA/D-CMA and MOEA/DD-CMA are implemented and evaluated through an experimental study. The experimental study involves two well-known families of benchmark problems whose objective numbers scale from two to fifteen. Then, an extensive statistical analysis of the results is made to extract sound, statistically supported conclusions about the performance of the algorithms as the number of objectives scales.
- 1 June 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1451-1458
Combining CMA-ES and MOEA/DD for many-objective optimization
Multi-objective Estimation of Distribution Algorithms (MOEDAS) have been successfully applied to solve Multi-objective Optimization Problems (MOPs) since they are able to model dependencies between variables of the problem and then sample new solutions to guide the search to promising areas. A state-of-the-art optimizer for single-objective continuous functions that also uses probabilistic modeling is the Covariance Matrix Adaptation Evolution Strategy (CMA-ES). Different variants of CMA-ES have been proposed for MOPs however most of them are based on Pareto dominance as the main selection criterion. Recently, a new multi-objective CMA-ES called MOEA/D-CMA was proposed combining the strengths of CMA-ES with those of the multi-objective evolutionary algorithm based on decomposition (MOEA/D). Nowadays, however, researchers on MOEAs agree that combining Pareto and decomposition can be beneficial for the search on MOPs. As a result, a new MOEA has been proposed, called MOEA/DD. This algorithm modifies the MOEA/D by including a new Pareto dominance update mechanism that brings more diversity into the search. In this study, we extend the MOEA/D-CMA by replacing its update mechanism by the one of MOEA/DD. The hypothesis is that this update mechanism will improve the performance of MOEA/D-CMA as it improved MOEA/D. MOEA/D-CMA and MOEA/DD-CMA are implemented and evaluated through an experimental study. The experimental study involves two well-known families of benchmark problems whose objective numbers scale from two to fifteen. Then, an extensive statistical analysis of the results is made to extract sound, statistically supported conclusions about the performance of the algorithms as the number of objectives scales.
- Open Access
- 30 March 2017
- Published by Springer Nature in Swarm Intelligence
- Vol. 11 (2) , 101-130
An investigation of clustering strategies in many-objective optimization: the I-Multi algorithm as a case study
- 30 March 2017
- Published by Springer Nature in Swarm Intelligence
- Vol. 11 (2) , 101-130
Open AccessAn investigation of clustering strategies in many-objective optimization: the I-Multi algorithm as a case study
- 28 July 2016
- Published by Springer Nature in Memetic Computing
- Vol. 9 (2) , 153-180
Transfer weight functions for injecting problem information in the multi-objective CMA-ES
- 28 July 2016
- Published by Springer Nature in Memetic Computing
- Vol. 9 (2) , 153-180
Transfer weight functions for injecting problem information in the multi-objective CMA-ES
- 1 March 2016
- Published by Elsevier in Neurocomputing
- Vol. 180, 68-78
C-Multi: A competent multi-swarm approach for many-objective problems
- 1 March 2016
- Published by Elsevier in Neurocomputing
- Vol. 180, 68-78
C-Multi: A competent multi-swarm approach for many-objective problems
- 18 March 2015
- Published by Springer Nature
- p. 109-123
Using Hyper-Heuristic to Select Leader and Archiving Methods for Many-Objective Problems
- 18 March 2015
- Published by Springer Nature
- p. 109-123
Using Hyper-Heuristic to Select Leader and Archiving Methods for Many-Objective Problems
- 1 October 2014
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 426-431
A Hybrid Competent Multi-swarm Approach for Many-Objective Problems
Many-objective optimization problems (MaOPs) are a class of multi-objective problems that presents more than three functions to be optimized. As most Pareto based algorithms scale poorly according to the number of objectives, researchers are working on alternatives to overcome these limitations. An algorithm that has shown good results in solving MaOPs is the Iterated Multi-swarm (I-Multi) which presents a clever multi-swarm strategy to spread the solutions across different areas of the objective space while keeping a good convergence. As the I-Multi is a very recent algorithm, alternative approaches are yet to be explored. Here we investigate the use of an Estimation of Distribution Algorithm (EDA) in the multi-swarm stage of I-Multi. EDAs create a model based on the best solutions found and sample new solutions based in this model. An EDA that presents good performance is the rBOA which is a real-valued version of the Bayesian optimization algorithm. This work presents an algorithm called C-Multi consisting of a hybrid between the I-Multi and the rBOA with the aim to join the diversity strength of I-Multi and the convergence characteristic of rBOA. An experimental study is conducted using the seven well-known DTLZ test functions with 3, 5, 10, 15 and 20 objectives to evaluate the performance of the algorithms as the number of objectives scales up. The results point that the new algorithm presents superior convergence and diversity on hard problems.
- 1 October 2014
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 426-431
A Hybrid Competent Multi-swarm Approach for Many-Objective Problems
Many-objective optimization problems (MaOPs) are a class of multi-objective problems that presents more than three functions to be optimized. As most Pareto based algorithms scale poorly according to the number of objectives, researchers are working on alternatives to overcome these limitations. An algorithm that has shown good results in solving MaOPs is the Iterated Multi-swarm (I-Multi) which presents a clever multi-swarm strategy to spread the solutions across different areas of the objective space while keeping a good convergence. As the I-Multi is a very recent algorithm, alternative approaches are yet to be explored. Here we investigate the use of an Estimation of Distribution Algorithm (EDA) in the multi-swarm stage of I-Multi. EDAs create a model based on the best solutions found and sample new solutions based in this model. An EDA that presents good performance is the rBOA which is a real-valued version of the Bayesian optimization algorithm. This work presents an algorithm called C-Multi consisting of a hybrid between the I-Multi and the rBOA with the aim to join the diversity strength of I-Multi and the convergence characteristic of rBOA. An experimental study is conducted using the seven well-known DTLZ test functions with 3, 5, 10, 15 and 20 objectives to evaluate the performance of the algorithms as the number of objectives scales up. The results point that the new algorithm presents superior convergence and diversity on hard problems.