2026-09-18T22:37:29Zhttps://ecommons.cornell.edu/server/oai/request

oai:ecommons.cornell.edu:1813/1116532026-05-15T19:43:38Zcom_1813_35col_1813_47

Siegel, Chloe Siobhan Nelson, Rebecca J. Bergstrom, Gary Carlton 2022-09-15T15:49:20Z 2022-09-15T15:49:20Z 2022-05 ProQuest Submission ID: 11459 ProQuest Publication ID: 29168023 https://hdl.handle.net/1813/111653 https://doi.org/10.7298/69xa-vr67 15530032 131 pages Current spectral models for detection of aflatoxin (AF) in maize kernels are limited by very low representation of kernels with AF levels above the models’ specified contamination thresholds. With the aim of improving prediction model sensitivity to AF-contaminated kernels, two methods were evaluated for artificially enriching the representation of kernels containing ≥150 ppb AF in a large spectral dataset: humid incubation and synthetic oversampling. The addition of synthetic training samples improved prediction accuracy of kernels containing ≥150 ppb AF from 51% to 80%. Humid incubation contributed additional kernels with intermediate levels of AF contamination (primarily 5 - 75 ppb), but generally did not change the overall distribution of AF contamination. Feature importance distributions overlapped among models at 329-345 nm, 380-385.5 nm, 415-425 nm, 639-668 nm, and 1,013.5-1,060 nm. These spectral ranges could be applicable to the development of limited wavelength grain sorting devices for low-resource settings. en SYNTHETIC OVERSAMPLING IMPROVES SPECTRAL DETECTION OF AFLATOXIN IN SINGLE MAIZE KERNELS dissertation or thesis https://newcatalog.library.cornell.edu/catalog/15530032 application/pdf Plant Pathology and Plant-Microbe Biology Cornell University Master of Science M.S., Plant Pathology and Plant-Microbe Biology https://hdl.handle.net/1813/59810.2 Publication Cornell Theses and Dissertations Siegel, Chloe Siobhan 5893a6ea-7af3-41d7-abc6-04bcd26ab5df open.access open.access <Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="0158c393-5961-43d4-887d-cb3990961d7d"> <Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843</Type> <Language>en</Language> <Title>SYNTHETIC OVERSAMPLING IMPROVES SPECTRAL DETECTION OF AFLATOXIN IN SINGLE MAIZE KERNELS</Title> <PublishedIn> <Publication> </Publication> </PublishedIn> <PublicationDate>2022-05</PublicationDate> <DOI>https://doi.org/10.7298/69xa-vr67</DOI> <Authors> <Author> <DisplayName>Siegel, Chloe Siobhan</DisplayName> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> </Authors> <Editors> </Editors> <Publishers> <Publisher> <OrgUnit /> </Publisher> </Publishers> <Abstract>Current spectral models for detection of aflatoxin (AF) in maize kernels are limited by very low representation of kernels with AF levels above the models’ specified contamination thresholds. With the aim of improving prediction model sensitivity to AF-contaminated kernels, two methods were evaluated for artificially enriching the representation of kernels containing ≥150 ppb AF in a large spectral dataset: humid incubation and synthetic oversampling. The addition of synthetic training samples improved prediction accuracy of kernels containing ≥150 ppb AF from 51% to 80%. Humid incubation contributed additional kernels with intermediate levels of AF contamination (primarily 5 - 75 ppb), but generally did not change the overall distribution of AF contamination. Feature importance distributions overlapped among models at 329-345 nm, 380-385.5 nm, 415-425 nm, 639-668 nm, and 1,013.5-1,060 nm. These spectral ranges could be applicable to the development of limited wavelength grain sorting devices for low-resource settings.</Abstract> <Access xmlns="http://purl.org/coar/access_right" > </Access> </Publication>