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

doi:10.1117/12.3010873

9 May 2024 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

Proceedings Volume 12944, Bioinspiration, Biomimetics, and Bioreplication XIV; 129440B (2024) https://doi.org/10.1117/12.3010873
Event: SPIE Smart Structures + Nondestructive Evaluation, 2024, Long Beach, California, United States

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.

Conference Presentation

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Seth A. McNeill, Aviad Golan, Heeirthan Shanthan, Richard W. Mankin, and Yabin Liao "Invasive insect pest monitoring using low-cost, field deployable, machine-learning-assisted sensor systems", Proc. SPIE 12944, Bioinspiration, Biomimetics, and Bioreplication XIV, 129440B (9 May 2024); https://doi.org/10.1117/12.3010873

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available