Eduardo T. Tiradentes

Dr. Eduardo T. Tiradentes

orcid

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

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

Representative Publications

View All Publications
22 July 2025 in Agriculture
Verified
Journal Article
Open access
PDF file
DAVID AUGUSTO RIBEIRODAVID AUGUSTO RIBEIRO
DAVID AUGUSTO RIBEIRO
DTDennis Tavares
Dennis Tavares
Eduardo T. TiradentesEduardo T. Tiradentes
Eduardo T. Tiradentes
FSFábio Santos
Fábio Santos
DRDemóstenes Zegarra Rodríguez
Demóstenes Zegarra Rodríguez
The automated detection and classification of immature macauba (Acrocomia aculeata) fruits is critical for improving post-harvest processing and quality control. In this study, we present a comparative evaluation of two state-of-the-art YOLO architectures, YOLOv11x and YOLOv12x, trained on the newly constructed VIC01 dataset comprising 1600 annotated images captured under both background-free and natural background conditions. Both models were implemented in PyTorch and trained until the convergence of box regression, classification, and distribution-focal losses. Under an IoU (intersection over union) threshold of 0.50, YOLOv11x and YOLOv12x achieved an identical mean average precision (mAP50) of 0.995 with perfect precision and recall or TPR (true positive rate). Averaged over IoU thresholds from 0.50 to 0.95, YOLOv11x demonstrated superior spatial localization performance (mAP50–95 = 0.973), while YOLOv12x exhibited robust performance in complex background scenarios, achieving a competitive mAP50–95. Inference throughput averaged 3.9 ms per image for YOLOv11x and 6.7 ms for YOLOv12x, highlighting a trade-off between speed and architectural complexity. Fused model representations revealed optimized layer fusion and reduced computational overhead (GFLOPs), facilitating efficient deployment. Confusion-matrix analyses confirmed YOLOv11x’s ability to reject background clutter more effectively than YOLOv12x, whereas precision–recall and F1-score curves indicated both models maintain near-perfect detection balance across thresholds. The public release of the VIC01 dataset and trained weights ensures reproducibility and supports future research. Our results underscore the importance of selecting architectures based on application-specific requirements, balancing detection accuracy, background discrimination, and computational constraints. Future work will extend this framework to additional maturation stages, sensor fusion modalities, and lightweight edge-deployment variants. By facilitating precise immature fruit identification, this work contributes to sustainable production and value addition in macauba processing.

31 January 2025 in Preprints.org
Verified
Preprint
Open access
PDF file
DAVID AUGUSTO RIBEIRODAVID AUGUSTO RIBEIRO
DAVID AUGUSTO RIBEIRO
DTDennis Santos Tavares
Dennis Santos Tavares
Eduardo T. TiradentesEduardo T. Tiradentes
Eduardo T. Tiradentes
FSFábio Santos
Fábio Santos
DRDemóstenes Zegarra Rodríguez
Demóstenes Zegarra Rodríguez
This study assessed the YOLO model’s effectiveness in identifying the phytobiometric patterns of Macaúba (Acrocomia aculeata), specifically detecting and classifying immature fruits. Conducted at Fazenda Limeira, Lavras, Minas Gerais, Brazil, the experiment used Macaúba fruits from spontaneously grown palm trees in a grazing area. Fruits were randomly selected, cleaned, and stored for 48 hours in a shaded area before photographic recording and biometric measurement. Performance analysis showed significant improvements, highlighting the model’s potential to optimize agro-industrial processes. Key loss metrics were substantially reduced: box_loss from 0.9 to 0.2, cls_loss from 1.4 to 0.1, and dfl_loss from 1.4 to 0.8. These reductions indicate enhanced accuracy in localization and classification, demonstrating YOLO’s ability to adjust bounding boxes and correctly identify fruit classes. Furthermore, the model achieved perfect Precision and Recall values (1.0) in the precision-recall (PR) curve, eliminating false positives and negatives. This ensures precise matching between predictions and actual instances of the Immature Macaúba ("Macuba Imatura") class. Applying the model in Macaúba processing offers benefits such as automatic sorting, improved quality control, and waste reduction. This work emphasizes the feasibility of using artificial intelligence in precision agriculture, promoting automation and sustainability within production chains.