Invasive insect pest monitoring using low-cost, field deployable, machine-learning-assisted sensor systems

Seth A. McNeill, Aviad Golan, Heeirthan Shanthan, Richard W. Mankin, Yabin Liao

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

The Asian citrus psyllid (ACP), Diaphorina citri Kuwayama (Hemiptera: Liviidae), is a citrus pest that vectors the bacterium that causes huanglongbing (HLB) disease between citrus trees. It has become a very large problem to the US citrus growers. Male ACP find females by vibrating the substrate (branch) to call them. The females vibrate a response and the males track these responses to find them in a citrus tree. We have created three ACP call recognition systems–one using Matlab, one using TensorFlow implemented on a Raspberry Pi, and one using Edge Impulse implemented on a RP2040 microcontroller. All three systems recognized calls with an accuracy greater than 79.5%. A demonstration on a single, long recording of two ACP vibrating to each other using the RP2040 system shows that it would be useful in a live implementation.

Original languageEnglish (US)
Title of host publicationBioinspiration, Biomimetics, and Bioreplication XIV
EditorsRaul J. Martin-Palma, Mato Knez, Akhlesh Lakhtakia
PublisherSPIE
ISBN (Electronic)9781510671942
DOIs
StatePublished - 2024
EventBioinspiration, Biomimetics, and Bioreplication XIV 2024 - Long Beach, United States
Duration: Mar 25 2024Mar 26 2024

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume12944
ISSN (Print)0277-786X
ISSN (Electronic)1996-756X

Conference

ConferenceBioinspiration, Biomimetics, and Bioreplication XIV 2024
Country/TerritoryUnited States
CityLong Beach
Period3/25/243/26/24

All Science Journal Classification (ASJC) codes

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Computer Science Applications
  • Applied Mathematics
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Invasive insect pest monitoring using low-cost, field deployable, machine-learning-assisted sensor systems'. Together they form a unique fingerprint.

Cite this