Detection and Classification of Citrus Fruit Infestation by Bactrocera dorsalis (Hendel) Using a Multi-Path Vis/NIR Spectroscopy System

Dapeng Li, Jiang Long, Ziye Tang, Longbo Han, Zhongliang Gong, Liang Wen, Hailong Peng and Tao Wen ()
Additional contact information
Dapeng Li: School of Mechanical and Electrical Engineering, Central South University of Forestry and Technology, Changsha 410004, China
Jiang Long: School of Mechanical and Electrical Engineering, Central South University of Forestry and Technology, Changsha 410004, China
Ziye Tang: School of Mechanical and Electrical Engineering, Central South University of Forestry and Technology, Changsha 410004, China
Longbo Han: School of Mechanical and Electrical Engineering, Central South University of Forestry and Technology, Changsha 410004, China
Zhongliang Gong: School of Mechanical and Electrical Engineering, Central South University of Forestry and Technology, Changsha 410004, China
Liang Wen: College of Life Sciences, South China Normal University, Guangzhou 510630, China
Hailong Peng: Department of Chemical and Pharmaceutical Engineering, Nanchang University, Nanchang 330031, China
Tao Wen: School of Mechanical and Electrical Engineering, Central South University of Forestry and Technology, Changsha 410004, China

Agriculture, 2023, vol. 13, issue 8, 1-18

Abstract: In this study, a multi-path Vis/NIR spectroscopy system was developed to detect the presence of Bactrocera dorsalis (Hendel) infestations of citrus fruit. Spectra were acquired for 252 citrus fruit, 126 of which were infested. Two hundred and fifty-two spectra were acquired for modeling in their un-infested stage, slightly infested stage, and seriously infested stage. The location of the infestation is unclear, and considering the impact of the light path on the location of the infestation, each citrus fruit was tested in three orientations (i.e., fruit stalks facing upward (A), fruit stalks facing horizontally (B), and fruit stalks facing downward (C)). Classification models based on joint X-Y distance, multiple transmittance calibration, competitive adaptive reweighted sampling, and partial least squares discriminant analysis (SPXY-MSC-CARS-PLS-DA) were developed on the spectra of each light path, and the average spectra of the four light paths was calculated, to compare their performance in infestation classification. The results show the classification result changed with the light path and fruit orientation. The average spectra for each fruit orientation consistently gave better classification results, with overall accuracies of 92.9%, 89.3%, and 90.5% for orientations A, B, and C, respectively. Moreover, the best model had a Kappa value of 0.89, and gave 95.2%, 80.1%, and 100.0% accuracy for un-infested, slightly infested, and seriously infested citrus fruit. Furthermore, the classification results for infested citrus fruits were better when using the average spectra than using the spectrum of each single light path. Therefore, the multi-path Vis/NIR spectroscopy system is conducive to the detection of B. dorsalis infestation in citrus fruits.

Keywords: multi-path spectra; citrus infestation; transmittance; Bactrocera dorsalis (Hendel); partial least squares; classification (search for similar items in EconPapers)
JEL-codes: Q1 Q10 Q11 Q12 Q13 Q14 Q15 Q16 Q17 Q18 (search for similar items in EconPapers)
Date: 2023
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2077-0472/13/8/1642/pdf (application/pdf)
https://www.mdpi.com/2077-0472/13/8/1642/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jagris:v:13:y:2023:i:8:p:1642-:d:1221567

Access Statistics for this article

Agriculture is currently edited by Ms. Leda Xuan

More articles in Agriculture from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().