Using a Resnet50 with a Kernel Attention Mechanism for Rice Disease Diagnosis
The domestication of animals and the cultivation of crops have been essential to human development throughout history, with the agricultural sector playing a pivotal role. Insufficient nutrition often leads to plant diseases, such as those affecting rice crops, resulting in yield losses of 20–40% of...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-05-01
|
| Series: | Life |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-1729/13/6/1277 |
| _version_ | 1797593836470403072 |
|---|---|
| author | Mehdhar S. A. M. Al-Gaashani Nagwan Abdel Samee Rana Alnashwan Mashael Khayyat Mohammed Saleh Ali Muthanna |
| author_facet | Mehdhar S. A. M. Al-Gaashani Nagwan Abdel Samee Rana Alnashwan Mashael Khayyat Mohammed Saleh Ali Muthanna |
| author_sort | Mehdhar S. A. M. Al-Gaashani |
| collection | DOAJ |
| description | The domestication of animals and the cultivation of crops have been essential to human development throughout history, with the agricultural sector playing a pivotal role. Insufficient nutrition often leads to plant diseases, such as those affecting rice crops, resulting in yield losses of 20–40% of total production. These losses carry significant global economic consequences. Timely disease diagnosis is critical for implementing effective treatments and mitigating financial losses. However, despite technological advancements, rice disease diagnosis primarily depends on manual methods. In this study, we present a novel self-attention network (SANET) based on the ResNet50 architecture, incorporating a kernel attention mechanism for accurate AI-assisted rice disease classification. We employ attention modules to extract contextual dependencies within images, focusing on essential features for disease identification. Using a publicly available rice disease dataset comprising four classes (three disease types and healthy leaves), we conducted cross-validated classification experiments to evaluate our proposed model. The results reveal that the attention-based mechanism effectively guides the convolutional neural network (CNN) in learning valuable features, resulting in accurate image classification and reduced performance variation compared to state-of-the-art methods. Our SANET model achieved a test set accuracy of 98.71%, surpassing that of current leading models. These findings highlight the potential for widespread AI adoption in agricultural disease diagnosis and management, ultimately enhancing efficiency and effectiveness within the sector. |
| first_indexed | 2024-03-11T02:14:52Z |
| format | Article |
| id | doaj.art-d3daca9531b54c01879416f43899023c |
| institution | Directory Open Access Journal |
| issn | 2075-1729 |
| language | English |
| last_indexed | 2024-03-11T02:14:52Z |
| publishDate | 2023-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Life |
| spelling | doaj.art-d3daca9531b54c01879416f43899023c2023-11-18T11:17:04ZengMDPI AGLife2075-17292023-05-01136127710.3390/life13061277Using a Resnet50 with a Kernel Attention Mechanism for Rice Disease DiagnosisMehdhar S. A. M. Al-Gaashani0Nagwan Abdel Samee1Rana Alnashwan2Mashael Khayyat3Mohammed Saleh Ali Muthanna4College of Computer Science and Technology, Chongqing University of Posts and Telecommunications, Chongqing 400065, ChinaDepartment of Information Technology, College of Computer and Information Sciences, Princess Nourah bint Abdulrahman University, P.O. Box 84428, Riyadh 11671, Saudi ArabiaDepartment of Information Technology, College of Computer and Information Sciences, Princess Nourah bint Abdulrahman University, P.O. Box 84428, Riyadh 11671, Saudi ArabiaDepartment of Information Systems and Technology, College of Computer Science and Engineering, University of Jeddah, Jeddah 23218, Saudi ArabiaInstitute of Computer Technologies and Information Security, Southern Federal University, 347922 Taganrog, RussiaThe domestication of animals and the cultivation of crops have been essential to human development throughout history, with the agricultural sector playing a pivotal role. Insufficient nutrition often leads to plant diseases, such as those affecting rice crops, resulting in yield losses of 20–40% of total production. These losses carry significant global economic consequences. Timely disease diagnosis is critical for implementing effective treatments and mitigating financial losses. However, despite technological advancements, rice disease diagnosis primarily depends on manual methods. In this study, we present a novel self-attention network (SANET) based on the ResNet50 architecture, incorporating a kernel attention mechanism for accurate AI-assisted rice disease classification. We employ attention modules to extract contextual dependencies within images, focusing on essential features for disease identification. Using a publicly available rice disease dataset comprising four classes (three disease types and healthy leaves), we conducted cross-validated classification experiments to evaluate our proposed model. The results reveal that the attention-based mechanism effectively guides the convolutional neural network (CNN) in learning valuable features, resulting in accurate image classification and reduced performance variation compared to state-of-the-art methods. Our SANET model achieved a test set accuracy of 98.71%, surpassing that of current leading models. These findings highlight the potential for widespread AI adoption in agricultural disease diagnosis and management, ultimately enhancing efficiency and effectiveness within the sector.https://www.mdpi.com/2075-1729/13/6/1277rice disease classificationself-attention mechanismagriculture imaging |
| spellingShingle | Mehdhar S. A. M. Al-Gaashani Nagwan Abdel Samee Rana Alnashwan Mashael Khayyat Mohammed Saleh Ali Muthanna Using a Resnet50 with a Kernel Attention Mechanism for Rice Disease Diagnosis Life rice disease classification self-attention mechanism agriculture imaging |
| title | Using a Resnet50 with a Kernel Attention Mechanism for Rice Disease Diagnosis |
| title_full | Using a Resnet50 with a Kernel Attention Mechanism for Rice Disease Diagnosis |
| title_fullStr | Using a Resnet50 with a Kernel Attention Mechanism for Rice Disease Diagnosis |
| title_full_unstemmed | Using a Resnet50 with a Kernel Attention Mechanism for Rice Disease Diagnosis |
| title_short | Using a Resnet50 with a Kernel Attention Mechanism for Rice Disease Diagnosis |
| title_sort | using a resnet50 with a kernel attention mechanism for rice disease diagnosis |
| topic | rice disease classification self-attention mechanism agriculture imaging |
| url | https://www.mdpi.com/2075-1729/13/6/1277 |
| work_keys_str_mv | AT mehdharsamalgaashani usingaresnet50withakernelattentionmechanismforricediseasediagnosis AT nagwanabdelsamee usingaresnet50withakernelattentionmechanismforricediseasediagnosis AT ranaalnashwan usingaresnet50withakernelattentionmechanismforricediseasediagnosis AT mashaelkhayyat usingaresnet50withakernelattentionmechanismforricediseasediagnosis AT mohammedsalehalimuthanna usingaresnet50withakernelattentionmechanismforricediseasediagnosis |