Considering its wide application in the food industry, near-infrared hyperspectral imaging (NIR HSI) was explored for animal feed applications. Its ability to provide chemical composition of the sample at the pixel level provides an advantage over the typical NIR spectroscopy. In this dissertation, a literature review was presented that highlights the applications of NIR HSI on grains, oilseeds, and animal feed ingredients. In our first study, a Corning NIR HSI instrument was used to predict protein and oil content in soybean meal and visualize predicted protein distribution over the entire soybean meal sample. Preprocessing by standard normal variate and Savitzky-Golay derivative was effective in improving calibration model performance. The NIR HSI instrument was also compared with two commercially available single-point NIR spectrometers which are typically used in the grain and feed industry. Absorbance spectra from the NIR HSI instrument were relatively close to those from the two NIR instruments in most of the wavelengths. Regression coefficients from soybean meal protein model calibration highlighted the similarities in the contributing variables of the three instruments. In our second study, lysine concentration was determined in soybean meal and dried distillers’ grains with solubles (DDGS) using NIR HSI in combination with partial least squares regression or spectral angle mapper (SAM) classification. Score plots from principal component analysis separated pure lysine spectra from soybean meal and DDGS. Increasing the SAM maximum angle also increased the model calibration performance. Overall, both PLS regression and SAM classification obtained promising results thereby indicating the potential of this technology to be used in evaluating amino acid concentration in animal feeds.
","abstract_html":"<p>Considering its wide application in the food industry, near-infrared hyperspectral imaging (NIR HSI) was explored for animal feed applications. Its ability to provide chemical composition of the sample at the pixel level provides an advantage over the typical NIR spectroscopy. In this dissertation, a literature review was presented that highlights the applications of NIR HSI on grains, oilseeds, and animal feed ingredients. In our first study, a Corning NIR HSI instrument was used to predict protein and oil content in soybean meal and visualize predicted protein distribution over the entire soybean meal sample. Preprocessing by standard normal variate and Savitzky-Golay derivative was effective in improving calibration model performance. The NIR HSI instrument was also compared with two commercially available single-point NIR spectrometers which are typically used in the grain and feed industry. Absorbance spectra from the NIR HSI instrument were relatively close to those from the two NIR instruments in most of the wavelengths. Regression coefficients from soybean meal protein model calibration highlighted the similarities in the contributing variables of the three instruments. In our second study, lysine concentration was determined in soybean meal and dried distillers’ grains with solubles (DDGS) using NIR HSI in combination with partial least squares regression or spectral angle mapper (SAM) classification. Score plots from principal component analysis separated pure lysine spectra from soybean meal and DDGS. Increasing the SAM maximum angle also increased the model calibration performance. Overall, both PLS regression and SAM classification obtained promising results thereby indicating the potential of this technology to be used in evaluating amino acid concentration in animal feeds.</p>","abstract_has_math":false,"creators":["Dantes, Princess Tiffany"],"institution":null,"degree_name":"Doctor of Philosophy","degree_level":"dissertation","degree_discipline":"Agricultural and Biosystems Engineering","degree_department":"Department of Agricultural and Biosystems Engineering (ENG)","school":null,"contributors":[],"advisors":["Charles R Hurburgh"],"committee_chairs":[],"committee_members":[],"year":2020,"date_issued":"2020-01-01","date_published":"2020-01-01","updated_at":"2026-07-24T02:38:01Z","subjects":[],"languages":["en"],"rights":[],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier.doi","label":"DOI","values":["https://doi.org/10.31274/etd-20200902-32"],"render_values":[{"text":"https://doi.org/10.31274/etd-20200902-32","href":"https://doi.org/10.31274/etd-20200902-32","code":true}]},{"key":"dc:identifier","label":"Identifier","values":["archive/lib.dr.iastate.edu/etd/18113/"],"render_values":[{"text":"archive/lib.dr.iastate.edu/etd/18113/","href":null,"code":true}]}]},"links":{"outbound_url":"https://dr.lib.iastate.edu/handle/20.500.12876/94265","outbound_label":"Repository record","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Charles R Hurburgh"]},{"key":"dc:contributor.department","label":"Department","values":["Department of Agricultural and Biosystems Engineering (ENG)"]},{"key":"dc:creator","label":"Author","values":["Dantes, Princess Tiffany"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2020-09-23T19:12:52.000"]},{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2021-02-25T21:33:25Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2021-02-25T21:33:25Z"]},{"key":"dc:date.issued","label":"Date","values":["2020-01-01"]},{"key":"dc:type","label":"Dc Type","values":["dissertation"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Agricultural and Biosystems Engineering"]},{"key":"thesis:degree_level","label":"Degree Level","values":["dissertation"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Doctor of Philosophy"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["en"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["archive/lib.dr.iastate.edu/etd/18113/"]},{"key":"dc:identifier.doi","label":"DOI","values":["https://doi.org/10.31274/etd-20200902-32"]},{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://dr.lib.iastate.edu/handle/20.500.12876/94265"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Considering its wide application in the food industry, near-infrared hyperspectral imaging (NIR HSI) was explored for animal feed applications. Its ability to provide chemical composition of the sample at the pixel level provides an advantage over the typical NIR spectroscopy. In this dissertation, a literature review was presented that highlights the applications of NIR HSI on grains, oilseeds, and animal feed ingredients. In our first study, a Corning NIR HSI instrument was used to predict protein and oil content in soybean meal and visualize predicted protein distribution over the entire soybean meal sample. Preprocessing by standard normal variate and Savitzky-Golay derivative was effective in improving calibration model performance. The NIR HSI instrument was also compared with two commercially available single-point NIR spectrometers which are typically used in the grain and feed industry. Absorbance spectra from the NIR HSI instrument were relatively close to those from the two NIR instruments in most of the wavelengths. Regression coefficients from soybean meal protein model calibration highlighted the similarities in the contributing variables of the three instruments. In our second study, lysine concentration was determined in soybean meal and dried distillers’ grains with solubles (DDGS) using NIR HSI in combination with partial least squares regression or spectral angle mapper (SAM) classification. Score plots from principal component analysis separated pure lysine spectra from soybean meal and DDGS. Increasing the SAM maximum angle also increased the model calibration performance. Overall, both PLS regression and SAM classification obtained promising results thereby indicating the potential of this technology to be used in evaluating amino acid concentration in animal feeds.
"]},{"key":"dc:format.mimetype","label":"Dc Format Mimetype","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["NIR hyperspectral imaging for animal feed ingredient applications"]}]}],"canonical_facts":{"dc:contributor.advisor":["Charles R Hurburgh"],"dc:contributor.department":["Department of Agricultural and Biosystems Engineering (ENG)"],"dc:creator":["Dantes, Princess Tiffany"],"dc:date":["2020-09-23T19:12:52.000"],"dc:date.accessioned":["2021-02-25T21:33:25Z"],"dc:date.available":["2021-02-25T21:33:25Z"],"dc:date.issued":["2020-01-01"],"dc:description.abstract":["Considering its wide application in the food industry, near-infrared hyperspectral imaging (NIR HSI) was explored for animal feed applications. Its ability to provide chemical composition of the sample at the pixel level provides an advantage over the typical NIR spectroscopy. In this dissertation, a literature review was presented that highlights the applications of NIR HSI on grains, oilseeds, and animal feed ingredients. In our first study, a Corning NIR HSI instrument was used to predict protein and oil content in soybean meal and visualize predicted protein distribution over the entire soybean meal sample. Preprocessing by standard normal variate and Savitzky-Golay derivative was effective in improving calibration model performance. The NIR HSI instrument was also compared with two commercially available single-point NIR spectrometers which are typically used in the grain and feed industry. Absorbance spectra from the NIR HSI instrument were relatively close to those from the two NIR instruments in most of the wavelengths. Regression coefficients from soybean meal protein model calibration highlighted the similarities in the contributing variables of the three instruments. In our second study, lysine concentration was determined in soybean meal and dried distillers’ grains with solubles (DDGS) using NIR HSI in combination with partial least squares regression or spectral angle mapper (SAM) classification. Score plots from principal component analysis separated pure lysine spectra from soybean meal and DDGS. Increasing the SAM maximum angle also increased the model calibration performance. Overall, both PLS regression and SAM classification obtained promising results thereby indicating the potential of this technology to be used in evaluating amino acid concentration in animal feeds.
"],"dc:format.mimetype":["application/pdf"],"dc:identifier":["archive/lib.dr.iastate.edu/etd/18113/"],"dc:identifier.doi":["https://doi.org/10.31274/etd-20200902-32"],"dc:identifier.uri":["https://dr.lib.iastate.edu/handle/20.500.12876/94265"],"dc:language.iso":["en"],"dc:title":["NIR hyperspectral imaging for animal feed ingredient applications"],"dc:type":["dissertation"],"thesis:degree_discipline":["Agricultural and Biosystems Engineering"],"thesis:degree_level":["dissertation"],"thesis:degree_name":["Doctor of Philosophy"]},"updated_at":"2026-07-24T02:38:01Z"}