EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Proposal for Computationally Efficient Fog Computing System for Coffee Berry Borer Detection via Optimized YOLOv26

Ingrid P Huaman-Pacco iD, Erwin J Sacoto-Cabrera iD, Vinie Lee Silva-Alvarado iD, Ali Ahmad iD, Sandra Sendra iD, Jaime Lloret iD, Edison Moreno-Cardenas iD

Sensors · 03.04.2026 · 26 (7) · 2212

DOI: 10.3390/s26072212 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 03.04.2026. Verfasst von Ingrid P Huaman-Pacco und 6 weiteren Autor:innen. Beteiligte Einrichtung: TESLA Laboratory, Universidad Nacional de San Antonio Abad del Cusco, Cusco 08003, Peru. Hauptthemen laut MEDLINE: Coffea, Fruit. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 51 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National University of Saint Anthony the Abbot in Cuzco, Politecnica Salesiana University, Agencia Estatal de Investigación (AEI) MICIU/AEI/10.13039/501100011033.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The Coffee Berry Borer is the most destructive pest affecting global production of Coffea arabica. Early detection of pest-induced fruit damage remains challenging due to the small size of infestation symptoms and the dense clustering of coffee berries under complex field conditions. This study evaluates optimized object detection architectures designed to improve the balance between detection accuracy and computational efficiency. Three baselines were established: YOLOv8n (M0), YOLOv11n (M1), and YOLOv26n (M2). Seven architectural variants (M3–M9) were then developed by integrating FasterNet, SimSPPF, and EMA. Experimental results showed that M0 achieved the highest detection accuracy (mAP@0.5 = 0.9534 and 6.09 GFLOPs), whereas model M6, combining FasterNet and SimSPPF, provided the best accuracy–efficiency trade off with mAP@0.5 = 0.9446 and 5.12 GFLOPs. Pareto analysis confirmed M6 as the optimal configuration. Finally, in situ validation across 25 points achieved a mean F1-score of 0.7255 (SD = 0.0504) for infected berries despite cast shadows, proving its readiness for real-time agricultural deployment.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

CoffeaFruitAnimalsDetection AlgorithmsAlgorithmsImage Processing, Computer-Assisted

Stichwörter der Autor:innen

CNNWSNadvanced AIfog computingimage analysismachine learningobject optimizationprecision agriculture

Autor:innen und Institutionen

  • TESLA Laboratory, Universidad Nacional de San Antonio Abad del Cusco, Cusco 08003, Peru.
  • GIHP4C, Universidad Politécnica Salesiana, Cuenca 010102, Ecuador.
  • Instituto de Investigación para la Gestión Integrada de Zonas Costeras, Universitat Politécnica de València, C/Paranimf, 1, 46730 Grao de Gandia, Valencia, Spain.
  • Technology and Engineering Group, EM Research & Tech, Cusco 08003, Peru.

ORCID-Profile: Ingrid P Huaman-Pacco, Erwin J Sacoto-Cabrera, Vinie Lee Silva-Alvarado, Ali Ahmad, Sandra Sendra, Jaime Lloret, Edison Moreno-Cardenas

Förderung

  • National University of Saint Anthony the Abbot in Cuzco
  • Politecnica Salesiana University
  • Agencia Estatal de Investigación (AEI) MICIU/AEI/10.13039/501100011033
  • Universitat Politècnica de València

Zitieren

APA

Huaman-Pacco, I. P., Sacoto-Cabrera, E. J., Silva-Alvarado, V. L., Ahmad, A., Sendra, S., Lloret, J., & Moreno-Cardenas, E. (2026). Proposal for Computationally Efficient Fog Computing System for Coffee Berry Borer Detection via Optimized YOLOv26. Sensors, 26(7), 2212. https://doi.org/10.3390/s26072212

Vancouver

Huaman-Pacco IP, Sacoto-Cabrera EJ, Silva-Alvarado VL, Ahmad A, Sendra S, Lloret J, et al. Proposal for Computationally Efficient Fog Computing System for Coffee Berry Borer Detection via Optimized YOLOv26. Sensors. 2026;26(7):2212. doi:10.3390/s26072212

BibTeX
@article{HuamanPacco2026,
  author = {Huaman-Pacco, Ingrid P and Sacoto-Cabrera, Erwin J and Silva-Alvarado, Vinie Lee and Ahmad, Ali and Sendra, Sandra and Lloret, Jaime and Moreno-Cardenas, Edison},
  title = {Proposal for Computationally Efficient Fog Computing System for Coffee Berry Borer Detection via Optimized YOLOv26},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {7},
  pages = {2212},
  doi = {10.3390/s26072212}
}
Kostenlos starten →