EUVIMEDEUVIMED entdecken
Crossref

Convolutional neural network analysis of Diaphorina citri (Hemiptera: Liviidae) vibrational communication signals for enhanced mating disruption

R W Mankin iD, S McNeill iD, C McNeill

Journal of Economic Entomology · 01.08.2026 · 119 (4) · 2639-2652

DOI: 10.1093/jee/toag154 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Economic Entomology, online erschienen am 19.06.2026. Verfasst von R W Mankin und 2 weiteren Autor:innen. Beteiligte Einrichtung: US Department of Agriculture, Agriculture Research Service, Center for Medical, Agricultural, and Veterinary Entomology, Gainesville, FL, USA. Hauptthemen laut MEDLINE: Hemiptera, Sexual Behavior, Animal, Animal Communication, Insect Control. Die Arbeit nennt 148 Literaturangaben. Gefördert von: Citrus Research and Development Foundation, USDA ARS.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Diaphorina citri Kuwayama (Hemiptera: Liviidae) vector bacteria (Candidatus Liberibacter asiaticus) that cause huanglongbing, an economically devastating disease of citrus. Management of D. citri infestations is primarily through insecticides, but alternative control methods remain under consideration including the co-opting and disruption of D. citri mating-duet vibrational communication signals. This study applies generative adversarial network and convolutional neural network methods to distinguish among female and male duetting signals when the sex of the signaler is not visually verifiable or when multiple male–female pairs are duetting. Up to 99% accuracy was achieved in identifying D. citri female and male signalers in experiments where standard statistical analyses fail to distinguish them at P < 0.05 statistical significance. Such knowledge has potential to increase mating disruption effectiveness by identifying signals to which females have greater preference. Although these studies were conducted only with D. citri, there is future opportunity to consider interference from communication signals produced when vibrational signals of multiple pest species are present and, combined with Internet of Things (IoT) technological capabilities, to further improve the capability for early detection and management of insect pests.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

HemipteraSexual Behavior, AnimalAnimal CommunicationInsect ControlAnimalsVibrationConvolutional Neural NetworksFemaleMaleNeural Networks, ComputerGenerative Adversarial Networks

Stichwörter der Autor:innen

IoT (Internet of Things)citrusconvolutional neural network (CNN)generative adversarial networks (GANs)microcontroller

Autor:innen und Institutionen

  • US Department of Agriculture, Agriculture Research Service, Center for Medical, Agricultural, and Veterinary Entomology, Gainesville, FL, USA.
  • Department of Natural and Mathematical Sciences, Morningside University, Sioux City, IA, USA.
  • Department of Biology, Morningside University, Sioux City, IA, USA.

ORCID-Profile: R W Mankin, S McNeill

Förderung

  • Citrus Research and Development Foundation
  • USDA ARS

Zitieren

APA

Mankin, R. W., McNeill, S., & McNeill, C. (2026). Convolutional neural network analysis of Diaphorina citri (Hemiptera: Liviidae) vibrational communication signals for enhanced mating disruption. Journal of Economic Entomology, 119(4), 2639-2652. https://doi.org/10.1093/jee/toag154

Vancouver

Mankin RW, McNeill S, McNeill C. Convolutional neural network analysis of Diaphorina citri (Hemiptera: Liviidae) vibrational communication signals for enhanced mating disruption. Journal of Economic Entomology. 2026;119(4):2639-2652. doi:10.1093/jee/toag154

BibTeX
@article{Mankin2026,
  author = {Mankin, R W and McNeill, S and McNeill, C},
  title = {Convolutional neural network analysis of Diaphorina citri (Hemiptera: Liviidae) vibrational communication signals for enhanced mating disruption},
  journal = {Journal of Economic Entomology},
  year = {2026},
  volume = {119},
  number = {4},
  pages = {2639--2652},
  doi = {10.1093/jee/toag154}
}
Kostenlos starten →