Abstract
Codling moth (CM) larva is one of the most problematic insect pest species that plague the apple industry in the United States, especially with regards to international export. As the apple industry continues to grow, there is an evergrowing need for faster and more precise non-destructive techniques for detecting insect infestations. Vibro-acoustic emission sensing has proven to be an effective method for non-invasive detection. However, internal CM larvae infestation detection in apples can be difficult because their activity pattern is not stationary, resulting in a nontrivial chance of the larvae being dormant during the sample's evaluation period. One solution to this is to attempt to stimulate the larvae, encouraging it to be active during a known evaluation period. Our proposed method is heat stimulation, where the apple (and larvae, if present) are placed in an environment that slightly elevates its temperature (30°C) above the room temperature for a period before data are acquired. For heat stimulation to be meaningful, the temperature must be high enough to stimulate the larvae, but low enough to where it does not cause chemical property changes in the fruit or lessen the potential usable life of the fruit. The proposed work describes an experimental study where both control and CM larvae infested apples had vibro-acoustic data collected, with and without heat stimulation. The results show that heat stimulation does increase the accuracy of detection at the longer signal time (120 s, 60 s, and 10 s). Different classifier models were applied to recognize vibro-acoustic signals from CM infested apples, and the Ensemble model illustrated the highest performance, with overall test accuracy of 96.64%. This suggests that there is merit in heat stimulation, and industrial potential as the heat stimulation applied does not appear to damage the fruit.
Original language | English |
---|---|
Title of host publication | American Society of Agricultural and Biological Engineers Annual International Meeting, ASABE 2021 |
Pages | 210-218 |
Number of pages | 9 |
ISBN (Electronic) | 9781713833536 |
DOIs | |
State | Published - 2021 |
Event | 2021 American Society of Agricultural and Biological Engineers Annual International Meeting, ASABE 2021 - Virtual, Online Duration: Jul 12 2021 → Jul 16 2021 |
Publication series
Name | American Society of Agricultural and Biological Engineers Annual International Meeting, ASABE 2021 |
---|---|
Volume | 1 |
Conference
Conference | 2021 American Society of Agricultural and Biological Engineers Annual International Meeting, ASABE 2021 |
---|---|
City | Virtual, Online |
Period | 7/12/21 → 7/16/21 |
Bibliographical note
Funding Information:This work was supported by the Kentucky Agricultural Experiment Station (KAES), and the National Institute of Food and Agriculture (NIFA), U.S. Department of Agriculture, Hatch-Multistate project #: 1007893.
Publisher Copyright:
© ASABE 2021.All right reserved.
Funding
This work was supported by the Kentucky Agricultural Experiment Station (KAES), and the National Institute of Food and Agriculture (NIFA), U.S. Department of Agriculture, Hatch-Multistate project #: 1007893.
Funders | Funder number |
---|---|
U.S. Department of Agriculture | 1007893 |
National Institute of Food and Agriculture | |
Kentucky Agricultural Experiment Station |
Keywords
- Apples
- Codling moth
- Heat stimulation
- Machine learning
- Vibro-acoustic emission
ASJC Scopus subject areas
- Bioengineering
- Agronomy and Crop Science