Integration of Hyperspectral Imaging and Deep Learning for Discrimination of Fumigated Lilies and Prediction of Quality Indicator Contents

The lily, valued for its edibility and medicinal properties, is rich in essential nutrients. However, storage conditions and sulfur fumigation during processing can degrade key nutrients like polysaccharides, phenols, and sulfur dioxide. To address this, we applied a deep learning model combined wit...

Full description

Saved in:
Bibliographic Details
Main Authors: Pengfei Zhang, Youyou Wang, Binbin Yan, Xiufu Wang, Zihua Zhang, Sheng Wang, Jian Yang
Format: Article
Language:English
Published: MDPI AG 2025-02-01
Series:Foods
Subjects:
Online Access:https://www.mdpi.com/2304-8158/14/5/825
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850030378892394496
author Pengfei Zhang
Youyou Wang
Binbin Yan
Xiufu Wang
Zihua Zhang
Sheng Wang
Jian Yang
author_facet Pengfei Zhang
Youyou Wang
Binbin Yan
Xiufu Wang
Zihua Zhang
Sheng Wang
Jian Yang
author_sort Pengfei Zhang
collection DOAJ
description The lily, valued for its edibility and medicinal properties, is rich in essential nutrients. However, storage conditions and sulfur fumigation during processing can degrade key nutrients like polysaccharides, phenols, and sulfur dioxide. To address this, we applied a deep learning model combined with hyperspectral imaging for the rapid prediction of nutrient quality. The CLSTM (convolutional neural network–long short-term memory) model, utilizing variable combination population analysis (VCPA) for wavelength selection, effectively differentiated sulfur fumigation patterns in lilies. In terms of nutrient content prediction, the CLSTM model combined with full-wavelength data demonstrated superior performance, achieving an R<sup>2</sup> value of 0.769 for polysaccharides and 0.699 for total phenols. Additionally, the CLSTM model combined with IRF-selected characteristic wavelengths exhibited remarkable performance in predicting sulfur dioxide content, with an R<sup>2</sup> value of 0.755. These findings highlight the potential of hyperspectral imaging and the CLSTM model in enhancing the quality assessment and ensuring the nutritional integrity of lily products.
format Article
id doaj-art-e24c5ed0084f4c7aa8380ee459915f2c
institution DOAJ
issn 2304-8158
language English
publishDate 2025-02-01
publisher MDPI AG
record_format Article
series Foods
spelling doaj-art-e24c5ed0084f4c7aa8380ee459915f2c2025-08-20T02:59:14ZengMDPI AGFoods2304-81582025-02-0114582510.3390/foods14050825Integration of Hyperspectral Imaging and Deep Learning for Discrimination of Fumigated Lilies and Prediction of Quality Indicator ContentsPengfei Zhang0Youyou Wang1Binbin Yan2Xiufu Wang3Zihua Zhang4Sheng Wang5Jian Yang6Dexing Research and Training Center of Chinese Medical Sciences, Dexing 334220, ChinaState Key Laboratory for Quality Ensurance and Sustainable Use of Dao-di Herbs, National Resource Center for Chinese Materia Medica, China Academy of Chinese Medical Sciences, Beijing 100700, ChinaDexing Research and Training Center of Chinese Medical Sciences, Dexing 334220, ChinaDexing Research and Training Center of Chinese Medical Sciences, Dexing 334220, ChinaDexing Traditional Chinese Medicine Industry Development Service Center, Dexing 334220, ChinaDexing Research and Training Center of Chinese Medical Sciences, Dexing 334220, ChinaJiangxi Province Key Laboratory of Sustainable Utilization of Traditional Chinese Medicine Resources, Institute of Traditional Chinese Medicine Health Industry, China Academy of Chinese Medical Sciences, Nanchang 330115, ChinaThe lily, valued for its edibility and medicinal properties, is rich in essential nutrients. However, storage conditions and sulfur fumigation during processing can degrade key nutrients like polysaccharides, phenols, and sulfur dioxide. To address this, we applied a deep learning model combined with hyperspectral imaging for the rapid prediction of nutrient quality. The CLSTM (convolutional neural network–long short-term memory) model, utilizing variable combination population analysis (VCPA) for wavelength selection, effectively differentiated sulfur fumigation patterns in lilies. In terms of nutrient content prediction, the CLSTM model combined with full-wavelength data demonstrated superior performance, achieving an R<sup>2</sup> value of 0.769 for polysaccharides and 0.699 for total phenols. Additionally, the CLSTM model combined with IRF-selected characteristic wavelengths exhibited remarkable performance in predicting sulfur dioxide content, with an R<sup>2</sup> value of 0.755. These findings highlight the potential of hyperspectral imaging and the CLSTM model in enhancing the quality assessment and ensuring the nutritional integrity of lily products.https://www.mdpi.com/2304-8158/14/5/825lilyhyperspectral imagingnutrient contentdeep learning
spellingShingle Pengfei Zhang
Youyou Wang
Binbin Yan
Xiufu Wang
Zihua Zhang
Sheng Wang
Jian Yang
Integration of Hyperspectral Imaging and Deep Learning for Discrimination of Fumigated Lilies and Prediction of Quality Indicator Contents
Foods
lily
hyperspectral imaging
nutrient content
deep learning
title Integration of Hyperspectral Imaging and Deep Learning for Discrimination of Fumigated Lilies and Prediction of Quality Indicator Contents
title_full Integration of Hyperspectral Imaging and Deep Learning for Discrimination of Fumigated Lilies and Prediction of Quality Indicator Contents
title_fullStr Integration of Hyperspectral Imaging and Deep Learning for Discrimination of Fumigated Lilies and Prediction of Quality Indicator Contents
title_full_unstemmed Integration of Hyperspectral Imaging and Deep Learning for Discrimination of Fumigated Lilies and Prediction of Quality Indicator Contents
title_short Integration of Hyperspectral Imaging and Deep Learning for Discrimination of Fumigated Lilies and Prediction of Quality Indicator Contents
title_sort integration of hyperspectral imaging and deep learning for discrimination of fumigated lilies and prediction of quality indicator contents
topic lily
hyperspectral imaging
nutrient content
deep learning
url https://www.mdpi.com/2304-8158/14/5/825
work_keys_str_mv AT pengfeizhang integrationofhyperspectralimaginganddeeplearningfordiscriminationoffumigatedliliesandpredictionofqualityindicatorcontents
AT youyouwang integrationofhyperspectralimaginganddeeplearningfordiscriminationoffumigatedliliesandpredictionofqualityindicatorcontents
AT binbinyan integrationofhyperspectralimaginganddeeplearningfordiscriminationoffumigatedliliesandpredictionofqualityindicatorcontents
AT xiufuwang integrationofhyperspectralimaginganddeeplearningfordiscriminationoffumigatedliliesandpredictionofqualityindicatorcontents
AT zihuazhang integrationofhyperspectralimaginganddeeplearningfordiscriminationoffumigatedliliesandpredictionofqualityindicatorcontents
AT shengwang integrationofhyperspectralimaginganddeeplearningfordiscriminationoffumigatedliliesandpredictionofqualityindicatorcontents
AT jianyang integrationofhyperspectralimaginganddeeplearningfordiscriminationoffumigatedliliesandpredictionofqualityindicatorcontents