Image Classification of Wheat Rust Based on Ensemble Learning
Rust is a common disease in wheat that significantly impacts its growth and yield. Stem rust and leaf rust of wheat are difficult to distinguish, and manual detection is time-consuming. With the aim of improving this situation, this study proposes a method for identifying wheat rust based on ensembl...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-08-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/16/6047 |
| _version_ | 1797408060846637056 |
|---|---|
| author | Qian Pan Maofang Gao Pingbo Wu Jingwen Yan Mohamed A. E. AbdelRahman |
| author_facet | Qian Pan Maofang Gao Pingbo Wu Jingwen Yan Mohamed A. E. AbdelRahman |
| author_sort | Qian Pan |
| collection | DOAJ |
| description | Rust is a common disease in wheat that significantly impacts its growth and yield. Stem rust and leaf rust of wheat are difficult to distinguish, and manual detection is time-consuming. With the aim of improving this situation, this study proposes a method for identifying wheat rust based on ensemble learning (WR-EL). The WR-EL method extracts and integrates multiple convolutional neural network (CNN) models, namely VGG, ResNet 101, ResNet 152, DenseNet 169, and DenseNet 201, based on bagging, snapshot ensembling, and the stochastic gradient descent with warm restarts (SGDR) algorithm. The identification results of the WR-EL method were compared to those of five individual CNN models. The results show that the identification accuracy increases by 32%, 19%, 15%, 11%, and 8%. Additionally, we proposed the SGDR-S algorithm, which improved the f1 scores of healthy wheat, stem rust wheat and leaf rust wheat by 2%, 3% and 2% compared to the SGDR algorithm, respectively. This method can more accurately identify wheat rust disease and can be implemented as a timely prevention and control measure, which can not only prevent economic losses caused by the disease, but also improve the yield and quality of wheat. |
| first_indexed | 2024-03-09T03:52:52Z |
| format | Article |
| id | doaj.art-d10053592ef841e590c9407e9b33952d |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T03:52:52Z |
| publishDate | 2022-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-d10053592ef841e590c9407e9b33952d2023-12-03T14:25:57ZengMDPI AGSensors1424-82202022-08-012216604710.3390/s22166047Image Classification of Wheat Rust Based on Ensemble LearningQian Pan0Maofang Gao1Pingbo Wu2Jingwen Yan3Mohamed A. E. AbdelRahman4Key Laboratory of Agricultural Remote Sensing, Ministry of Agriculture and Rural Affairs/Institute of Agricultural Resources and Regional Planning, Chinese Academy of Agricultural Sciences, Beijing 100081, ChinaKey Laboratory of Agricultural Remote Sensing, Ministry of Agriculture and Rural Affairs/Institute of Agricultural Resources and Regional Planning, Chinese Academy of Agricultural Sciences, Beijing 100081, ChinaKey Laboratory of Digital Signal and Image Processing of Guangdong Province, Shantou University, Shantou 515063, ChinaKey Laboratory of Digital Signal and Image Processing of Guangdong Province, Shantou University, Shantou 515063, ChinaDivision of Environmental Studies and Land Use, National Authority for Remote Sensing and Space Sciences (NARSS), Cairo 11769, EgyptRust is a common disease in wheat that significantly impacts its growth and yield. Stem rust and leaf rust of wheat are difficult to distinguish, and manual detection is time-consuming. With the aim of improving this situation, this study proposes a method for identifying wheat rust based on ensemble learning (WR-EL). The WR-EL method extracts and integrates multiple convolutional neural network (CNN) models, namely VGG, ResNet 101, ResNet 152, DenseNet 169, and DenseNet 201, based on bagging, snapshot ensembling, and the stochastic gradient descent with warm restarts (SGDR) algorithm. The identification results of the WR-EL method were compared to those of five individual CNN models. The results show that the identification accuracy increases by 32%, 19%, 15%, 11%, and 8%. Additionally, we proposed the SGDR-S algorithm, which improved the f1 scores of healthy wheat, stem rust wheat and leaf rust wheat by 2%, 3% and 2% compared to the SGDR algorithm, respectively. This method can more accurately identify wheat rust disease and can be implemented as a timely prevention and control measure, which can not only prevent economic losses caused by the disease, but also improve the yield and quality of wheat.https://www.mdpi.com/1424-8220/22/16/6047wheat rustensemble learningCNNsnapshot ensemblingSGDR-S |
| spellingShingle | Qian Pan Maofang Gao Pingbo Wu Jingwen Yan Mohamed A. E. AbdelRahman Image Classification of Wheat Rust Based on Ensemble Learning Sensors wheat rust ensemble learning CNN snapshot ensembling SGDR-S |
| title | Image Classification of Wheat Rust Based on Ensemble Learning |
| title_full | Image Classification of Wheat Rust Based on Ensemble Learning |
| title_fullStr | Image Classification of Wheat Rust Based on Ensemble Learning |
| title_full_unstemmed | Image Classification of Wheat Rust Based on Ensemble Learning |
| title_short | Image Classification of Wheat Rust Based on Ensemble Learning |
| title_sort | image classification of wheat rust based on ensemble learning |
| topic | wheat rust ensemble learning CNN snapshot ensembling SGDR-S |
| url | https://www.mdpi.com/1424-8220/22/16/6047 |
| work_keys_str_mv | AT qianpan imageclassificationofwheatrustbasedonensemblelearning AT maofanggao imageclassificationofwheatrustbasedonensemblelearning AT pingbowu imageclassificationofwheatrustbasedonensemblelearning AT jingwenyan imageclassificationofwheatrustbasedonensemblelearning AT mohamedaeabdelrahman imageclassificationofwheatrustbasedonensemblelearning |