A Rapid Identification Method for Cottonseed Varieties Based on Near-Infrared Spectral and Generative Adversarial Networks

China is a major cotton-growing country with numerous cotton varieties, each exhibiting significant differences in yield and fiber quality. However, the current management of cottonseed varieties is disorganized, resulting in severe homogenization and the presence of counterfeit and mislabeled varie...

Full description

Saved in:
Bibliographic Details
Main Authors: Qingxu Li, Hao Li, Renhao Liu, Xiaofeng Dong, Hongzhou Zhang, Wanhuai Zhou
Format: Article
Language:English
Published: MDPI AG 2024-11-01
Series:Agriculture
Subjects:
Online Access:https://www.mdpi.com/2077-0472/14/12/2177
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850049563516207104
author Qingxu Li
Hao Li
Renhao Liu
Xiaofeng Dong
Hongzhou Zhang
Wanhuai Zhou
author_facet Qingxu Li
Hao Li
Renhao Liu
Xiaofeng Dong
Hongzhou Zhang
Wanhuai Zhou
author_sort Qingxu Li
collection DOAJ
description China is a major cotton-growing country with numerous cotton varieties, each exhibiting significant differences in yield and fiber quality. However, the current management of cottonseed varieties is disorganized, resulting in severe homogenization and the presence of counterfeit and mislabeled varieties. The detection of cottonseed variety information has become a critical issue for the Chinese cotton industry. In this study, we collected near-infrared (NIR) spectral data from six cottonseed varieties and constructed a GAN for cottonseed NIR data (GAN-CNIRD) model to generate additional cottonseed NIR data. The Euclidean distance method was used to label the generated NIR data according to the characteristics of the true NIR data. We then applied Standard Normal Variate (SNV), Multiplicative Scatter Correction (MSC), and Normalization algorithms to preprocess the combined dataset of generated and real cottonseed NIR data. Feature wavelengths were extracted using Bootstrap Soft Shrinkage (BOSS) and Competitive Adaptive Reweighted Sampling (CARS) algorithms. Subsequently, we developed Linear Discriminant Analysis (LDA), Random subspace method (RSM), and convolutional neural network (CNN) models to classify the cottonseed varieties. The results showed that for the LDA model, the use of feature wavelengths extracted after Normalization-BOSS processing achieved the best performance with an accuracy of 97.00%. For the RSM model, the use of feature wavelengths extracted after SNV-CARS processing achieved the best performance with an accuracy of 98.00%. For the CNN model, the use of feature wavelengths extracted after MSC-CARS processing achieved the best performance with an accuracy of 100.00%. Data augmentation using GAN-CNIRD-generated cottonseed data improved the accuracy of the three optimal models by 6%, 5%, and 6%, respectively. This study provides a crucial reference for the rapid detection of cottonseed variety information and has significant implications for the standardized management of cottonseed varieties.
format Article
id doaj-art-e1dc17511b694a6f93e9c9059feba57a
institution DOAJ
issn 2077-0472
language English
publishDate 2024-11-01
publisher MDPI AG
record_format Article
series Agriculture
spelling doaj-art-e1dc17511b694a6f93e9c9059feba57a2025-08-20T02:53:41ZengMDPI AGAgriculture2077-04722024-11-011412217710.3390/agriculture14122177A Rapid Identification Method for Cottonseed Varieties Based on Near-Infrared Spectral and Generative Adversarial NetworksQingxu Li0Hao Li1Renhao Liu2Xiaofeng Dong3Hongzhou Zhang4Wanhuai Zhou5College of Computer Science, Anhui University of Finance & Economics, Bengbu 233030, ChinaCollege of Computer Science, Anhui University of Finance & Economics, Bengbu 233030, ChinaCollege of Mechanical and Electrical Engineering, Tarim University, Alar 843300, ChinaCollege of Mechanical and Electrical Engineering, Tarim University, Alar 843300, ChinaCollege of Mechanical and Electrical Engineering, Tarim University, Alar 843300, ChinaCollege of Computer Science, Anhui University of Finance & Economics, Bengbu 233030, ChinaChina is a major cotton-growing country with numerous cotton varieties, each exhibiting significant differences in yield and fiber quality. However, the current management of cottonseed varieties is disorganized, resulting in severe homogenization and the presence of counterfeit and mislabeled varieties. The detection of cottonseed variety information has become a critical issue for the Chinese cotton industry. In this study, we collected near-infrared (NIR) spectral data from six cottonseed varieties and constructed a GAN for cottonseed NIR data (GAN-CNIRD) model to generate additional cottonseed NIR data. The Euclidean distance method was used to label the generated NIR data according to the characteristics of the true NIR data. We then applied Standard Normal Variate (SNV), Multiplicative Scatter Correction (MSC), and Normalization algorithms to preprocess the combined dataset of generated and real cottonseed NIR data. Feature wavelengths were extracted using Bootstrap Soft Shrinkage (BOSS) and Competitive Adaptive Reweighted Sampling (CARS) algorithms. Subsequently, we developed Linear Discriminant Analysis (LDA), Random subspace method (RSM), and convolutional neural network (CNN) models to classify the cottonseed varieties. The results showed that for the LDA model, the use of feature wavelengths extracted after Normalization-BOSS processing achieved the best performance with an accuracy of 97.00%. For the RSM model, the use of feature wavelengths extracted after SNV-CARS processing achieved the best performance with an accuracy of 98.00%. For the CNN model, the use of feature wavelengths extracted after MSC-CARS processing achieved the best performance with an accuracy of 100.00%. Data augmentation using GAN-CNIRD-generated cottonseed data improved the accuracy of the three optimal models by 6%, 5%, and 6%, respectively. This study provides a crucial reference for the rapid detection of cottonseed variety information and has significant implications for the standardized management of cottonseed varieties.https://www.mdpi.com/2077-0472/14/12/2177cottonseedscottonseed varietiesmachine learningnear-infrared spectroscopygenerative adversarial networks
spellingShingle Qingxu Li
Hao Li
Renhao Liu
Xiaofeng Dong
Hongzhou Zhang
Wanhuai Zhou
A Rapid Identification Method for Cottonseed Varieties Based on Near-Infrared Spectral and Generative Adversarial Networks
Agriculture
cottonseeds
cottonseed varieties
machine learning
near-infrared spectroscopy
generative adversarial networks
title A Rapid Identification Method for Cottonseed Varieties Based on Near-Infrared Spectral and Generative Adversarial Networks
title_full A Rapid Identification Method for Cottonseed Varieties Based on Near-Infrared Spectral and Generative Adversarial Networks
title_fullStr A Rapid Identification Method for Cottonseed Varieties Based on Near-Infrared Spectral and Generative Adversarial Networks
title_full_unstemmed A Rapid Identification Method for Cottonseed Varieties Based on Near-Infrared Spectral and Generative Adversarial Networks
title_short A Rapid Identification Method for Cottonseed Varieties Based on Near-Infrared Spectral and Generative Adversarial Networks
title_sort rapid identification method for cottonseed varieties based on near infrared spectral and generative adversarial networks
topic cottonseeds
cottonseed varieties
machine learning
near-infrared spectroscopy
generative adversarial networks
url https://www.mdpi.com/2077-0472/14/12/2177
work_keys_str_mv AT qingxuli arapididentificationmethodforcottonseedvarietiesbasedonnearinfraredspectralandgenerativeadversarialnetworks
AT haoli arapididentificationmethodforcottonseedvarietiesbasedonnearinfraredspectralandgenerativeadversarialnetworks
AT renhaoliu arapididentificationmethodforcottonseedvarietiesbasedonnearinfraredspectralandgenerativeadversarialnetworks
AT xiaofengdong arapididentificationmethodforcottonseedvarietiesbasedonnearinfraredspectralandgenerativeadversarialnetworks
AT hongzhouzhang arapididentificationmethodforcottonseedvarietiesbasedonnearinfraredspectralandgenerativeadversarialnetworks
AT wanhuaizhou arapididentificationmethodforcottonseedvarietiesbasedonnearinfraredspectralandgenerativeadversarialnetworks
AT qingxuli rapididentificationmethodforcottonseedvarietiesbasedonnearinfraredspectralandgenerativeadversarialnetworks
AT haoli rapididentificationmethodforcottonseedvarietiesbasedonnearinfraredspectralandgenerativeadversarialnetworks
AT renhaoliu rapididentificationmethodforcottonseedvarietiesbasedonnearinfraredspectralandgenerativeadversarialnetworks
AT xiaofengdong rapididentificationmethodforcottonseedvarietiesbasedonnearinfraredspectralandgenerativeadversarialnetworks
AT hongzhouzhang rapididentificationmethodforcottonseedvarietiesbasedonnearinfraredspectralandgenerativeadversarialnetworks
AT wanhuaizhou rapididentificationmethodforcottonseedvarietiesbasedonnearinfraredspectralandgenerativeadversarialnetworks