Cotton Fusarium wilt diagnosis based on generative adversarial networks in small samples
This study aimed to explore the feasibility of applying Generative Adversarial Networks (GANs) for the diagnosis of Verticillium wilt disease in cotton and compared it with traditional data augmentation methods and transfer learning. By designing a model based on small-sample learning, we proposed a...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-12-01
|
| Series: | Frontiers in Plant Science |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fpls.2023.1290774/full |
| _version_ | 1827589689703399424 |
|---|---|
| author | Zhenghang Zhang Zhenghang Zhang Lulu Ma Lulu Ma Chunyue Wei Mi Yang Mi Yang Shizhe Qin Shizhe Qin Xin Lv Xin Lv Ze Zhang Ze Zhang |
| author_facet | Zhenghang Zhang Zhenghang Zhang Lulu Ma Lulu Ma Chunyue Wei Mi Yang Mi Yang Shizhe Qin Shizhe Qin Xin Lv Xin Lv Ze Zhang Ze Zhang |
| author_sort | Zhenghang Zhang |
| collection | DOAJ |
| description | This study aimed to explore the feasibility of applying Generative Adversarial Networks (GANs) for the diagnosis of Verticillium wilt disease in cotton and compared it with traditional data augmentation methods and transfer learning. By designing a model based on small-sample learning, we proposed an innovative cotton Verticillium wilt disease diagnosis system. The system uses Convolutional Neural Networks (CNNs) as feature extractors and applies trained GAN models for sample augmentation to improve classification accuracy. This study collected and processed a dataset of cotton Verticillium wilt disease images, including samples from normal and infected plants. Data augmentation techniques were used to expand the dataset and train the CNNs. Transfer learning using InceptionV3 was applied to train the CNNs on the dataset. The dataset was augmented using GAN algorithms and used to train CNNs. The performances of the data augmentation, transfer learning, and GANs were compared and analyzed. The results have demonstrated that augmenting the cotton Verticillium wilt disease image dataset using GAN algorithms enhanced the diagnostic accuracy and recall rate of the CNNs. Compared to traditional data augmentation methods, GANs exhibit better performance and generated more representative and diverse samples. Unlike transfer learning, GANs ensured an adequate sample size. By visualizing the images generated, GANs were found to generate realistic cotton images of Verticillium wilt disease, highlighting their potential applications in agricultural disease diagnosis. This study has demonstrated the potential of GANs in the diagnosis of cotton Verticillium wilt disease diagnosis, offering an effective approach for agricultural disease detection and providing insights into disease detection in other crops. |
| first_indexed | 2024-03-09T01:05:30Z |
| format | Article |
| id | doaj.art-32c3e01083474e25bd69680d28c34974 |
| institution | Directory Open Access Journal |
| issn | 1664-462X |
| language | English |
| last_indexed | 2024-03-09T01:05:30Z |
| publishDate | 2023-12-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Plant Science |
| spelling | doaj.art-32c3e01083474e25bd69680d28c349742023-12-11T09:20:12ZengFrontiers Media S.A.Frontiers in Plant Science1664-462X2023-12-011410.3389/fpls.2023.12907741290774Cotton Fusarium wilt diagnosis based on generative adversarial networks in small samplesZhenghang Zhang0Zhenghang Zhang1Lulu Ma2Lulu Ma3Chunyue Wei4Mi Yang5Mi Yang6Shizhe Qin7Shizhe Qin8Xin Lv9Xin Lv10Ze Zhang11Ze Zhang12Xinjiang Production and Construction Crops Oasis Eco-Agriculture Key Laboratory, Shihezi University College of Agriculture, Shihezi, ChinaNatiobal-Local Joint Engineering Research Center of Xinjiang Production and Construction Corps XPCC's Agricultural Big Data, Shihezi, ChinaXinjiang Production and Construction Crops Oasis Eco-Agriculture Key Laboratory, Shihezi University College of Agriculture, Shihezi, ChinaNatiobal-Local Joint Engineering Research Center of Xinjiang Production and Construction Corps XPCC's Agricultural Big Data, Shihezi, ChinaAgricultural Development Service Center, Fifty-first Mission, Third Division, Tumushuke, ChinaXinjiang Production and Construction Crops Oasis Eco-Agriculture Key Laboratory, Shihezi University College of Agriculture, Shihezi, ChinaNatiobal-Local Joint Engineering Research Center of Xinjiang Production and Construction Corps XPCC's Agricultural Big Data, Shihezi, ChinaXinjiang Production and Construction Crops Oasis Eco-Agriculture Key Laboratory, Shihezi University College of Agriculture, Shihezi, ChinaNatiobal-Local Joint Engineering Research Center of Xinjiang Production and Construction Corps XPCC's Agricultural Big Data, Shihezi, ChinaXinjiang Production and Construction Crops Oasis Eco-Agriculture Key Laboratory, Shihezi University College of Agriculture, Shihezi, ChinaNatiobal-Local Joint Engineering Research Center of Xinjiang Production and Construction Corps XPCC's Agricultural Big Data, Shihezi, ChinaXinjiang Production and Construction Crops Oasis Eco-Agriculture Key Laboratory, Shihezi University College of Agriculture, Shihezi, ChinaNatiobal-Local Joint Engineering Research Center of Xinjiang Production and Construction Corps XPCC's Agricultural Big Data, Shihezi, ChinaThis study aimed to explore the feasibility of applying Generative Adversarial Networks (GANs) for the diagnosis of Verticillium wilt disease in cotton and compared it with traditional data augmentation methods and transfer learning. By designing a model based on small-sample learning, we proposed an innovative cotton Verticillium wilt disease diagnosis system. The system uses Convolutional Neural Networks (CNNs) as feature extractors and applies trained GAN models for sample augmentation to improve classification accuracy. This study collected and processed a dataset of cotton Verticillium wilt disease images, including samples from normal and infected plants. Data augmentation techniques were used to expand the dataset and train the CNNs. Transfer learning using InceptionV3 was applied to train the CNNs on the dataset. The dataset was augmented using GAN algorithms and used to train CNNs. The performances of the data augmentation, transfer learning, and GANs were compared and analyzed. The results have demonstrated that augmenting the cotton Verticillium wilt disease image dataset using GAN algorithms enhanced the diagnostic accuracy and recall rate of the CNNs. Compared to traditional data augmentation methods, GANs exhibit better performance and generated more representative and diverse samples. Unlike transfer learning, GANs ensured an adequate sample size. By visualizing the images generated, GANs were found to generate realistic cotton images of Verticillium wilt disease, highlighting their potential applications in agricultural disease diagnosis. This study has demonstrated the potential of GANs in the diagnosis of cotton Verticillium wilt disease diagnosis, offering an effective approach for agricultural disease detection and providing insights into disease detection in other crops.https://www.frontiersin.org/articles/10.3389/fpls.2023.1290774/fullcotton diseasesdata augmentationtransfer learninggenerative adversarial networksconvolutional networks |
| spellingShingle | Zhenghang Zhang Zhenghang Zhang Lulu Ma Lulu Ma Chunyue Wei Mi Yang Mi Yang Shizhe Qin Shizhe Qin Xin Lv Xin Lv Ze Zhang Ze Zhang Cotton Fusarium wilt diagnosis based on generative adversarial networks in small samples Frontiers in Plant Science cotton diseases data augmentation transfer learning generative adversarial networks convolutional networks |
| title | Cotton Fusarium wilt diagnosis based on generative adversarial networks in small samples |
| title_full | Cotton Fusarium wilt diagnosis based on generative adversarial networks in small samples |
| title_fullStr | Cotton Fusarium wilt diagnosis based on generative adversarial networks in small samples |
| title_full_unstemmed | Cotton Fusarium wilt diagnosis based on generative adversarial networks in small samples |
| title_short | Cotton Fusarium wilt diagnosis based on generative adversarial networks in small samples |
| title_sort | cotton fusarium wilt diagnosis based on generative adversarial networks in small samples |
| topic | cotton diseases data augmentation transfer learning generative adversarial networks convolutional networks |
| url | https://www.frontiersin.org/articles/10.3389/fpls.2023.1290774/full |
| work_keys_str_mv | AT zhenghangzhang cottonfusariumwiltdiagnosisbasedongenerativeadversarialnetworksinsmallsamples AT zhenghangzhang cottonfusariumwiltdiagnosisbasedongenerativeadversarialnetworksinsmallsamples AT luluma cottonfusariumwiltdiagnosisbasedongenerativeadversarialnetworksinsmallsamples AT luluma cottonfusariumwiltdiagnosisbasedongenerativeadversarialnetworksinsmallsamples AT chunyuewei cottonfusariumwiltdiagnosisbasedongenerativeadversarialnetworksinsmallsamples AT miyang cottonfusariumwiltdiagnosisbasedongenerativeadversarialnetworksinsmallsamples AT miyang cottonfusariumwiltdiagnosisbasedongenerativeadversarialnetworksinsmallsamples AT shizheqin cottonfusariumwiltdiagnosisbasedongenerativeadversarialnetworksinsmallsamples AT shizheqin cottonfusariumwiltdiagnosisbasedongenerativeadversarialnetworksinsmallsamples AT xinlv cottonfusariumwiltdiagnosisbasedongenerativeadversarialnetworksinsmallsamples AT xinlv cottonfusariumwiltdiagnosisbasedongenerativeadversarialnetworksinsmallsamples AT zezhang cottonfusariumwiltdiagnosisbasedongenerativeadversarialnetworksinsmallsamples AT zezhang cottonfusariumwiltdiagnosisbasedongenerativeadversarialnetworksinsmallsamples |