Development of a handheld GPU-assisted DSC-TransNet model for the real-time classification of plant leaf disease using deep learning approach
Abstract In agriculture, promptly and accurately identifying leaf diseases is crucial for sustainable crop production. To address this requirement, this research introduces a hybrid deep learning model that combines the visual geometric group version 19 (VGG19) architecture features with the transfo...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-01-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-024-82629-8 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832571792678453248 |
|---|---|
| author | Midhun P. Mathew Sudheep Elayidom V. P. Jagathy Raj K. M. Abubeker |
| author_facet | Midhun P. Mathew Sudheep Elayidom V. P. Jagathy Raj K. M. Abubeker |
| author_sort | Midhun P. Mathew |
| collection | DOAJ |
| description | Abstract In agriculture, promptly and accurately identifying leaf diseases is crucial for sustainable crop production. To address this requirement, this research introduces a hybrid deep learning model that combines the visual geometric group version 19 (VGG19) architecture features with the transformer encoder blocks. This fusion enables the accurate and précised real-time classification of leaf diseases affecting grape, bell pepper, and tomato plants. Incorporating transformer encoder blocks offers enhanced capability in capturing intricate spatial dependencies within leaf images, promising agricultural sustainability and food security. By providing farmers and farming stakeholders with a reliable tool for rapid disease detection, our model facilitates timely intervention and management practices, ultimately leading to improved crop yields and mitigated economic losses. Through extensive comparative analyses on various datasets and filed tests, the proposed depth wise separable convolutional-TransNet (DSC-TransNet) architecture has demonstrated higher performance in terms of accuracy (99.97%), precision (99.94%), recall (99.94), sensitivity (99.94%), F1-score (99.94%), AUC (0.98) for Grpae leaves across different datasets including bell pepper and tomato. Furthermore, including DSC layers enhances the computational efficiency of the model while maintaining expressive power, making it well-suited for real-time agricultural applications. The developed DSC-TransNet model is deployed in NVIDIA Jetson Nano single board computer. This research contributes to advancing the field of automated plant disease classification, addressing critical challenges in modern agriculture and promoting more efficient and sustainable farming practices. |
| format | Article |
| id | doaj-art-69b88c34ce2b4b35b8ece408e03ff587 |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-69b88c34ce2b4b35b8ece408e03ff5872025-02-02T12:18:25ZengNature PortfolioScientific Reports2045-23222025-01-0115111910.1038/s41598-024-82629-8Development of a handheld GPU-assisted DSC-TransNet model for the real-time classification of plant leaf disease using deep learning approachMidhun P. Mathew0Sudheep Elayidom1V. P. Jagathy Raj2K. M. Abubeker3CS Division, SOE-Cochin University of Science and TechnologyCS Division, SOE-Cochin University of Science and TechnologySMS-Cochin University of Science and TechnologyAmal Jyothi College of Engineering (Autonomous)Abstract In agriculture, promptly and accurately identifying leaf diseases is crucial for sustainable crop production. To address this requirement, this research introduces a hybrid deep learning model that combines the visual geometric group version 19 (VGG19) architecture features with the transformer encoder blocks. This fusion enables the accurate and précised real-time classification of leaf diseases affecting grape, bell pepper, and tomato plants. Incorporating transformer encoder blocks offers enhanced capability in capturing intricate spatial dependencies within leaf images, promising agricultural sustainability and food security. By providing farmers and farming stakeholders with a reliable tool for rapid disease detection, our model facilitates timely intervention and management practices, ultimately leading to improved crop yields and mitigated economic losses. Through extensive comparative analyses on various datasets and filed tests, the proposed depth wise separable convolutional-TransNet (DSC-TransNet) architecture has demonstrated higher performance in terms of accuracy (99.97%), precision (99.94%), recall (99.94), sensitivity (99.94%), F1-score (99.94%), AUC (0.98) for Grpae leaves across different datasets including bell pepper and tomato. Furthermore, including DSC layers enhances the computational efficiency of the model while maintaining expressive power, making it well-suited for real-time agricultural applications. The developed DSC-TransNet model is deployed in NVIDIA Jetson Nano single board computer. This research contributes to advancing the field of automated plant disease classification, addressing critical challenges in modern agriculture and promoting more efficient and sustainable farming practices.https://doi.org/10.1038/s41598-024-82629-8AgricultureLeaf diseasesTransformer encoderDepthwise separable convolutionDeep learningGPU |
| spellingShingle | Midhun P. Mathew Sudheep Elayidom V. P. Jagathy Raj K. M. Abubeker Development of a handheld GPU-assisted DSC-TransNet model for the real-time classification of plant leaf disease using deep learning approach Scientific Reports Agriculture Leaf diseases Transformer encoder Depthwise separable convolution Deep learning GPU |
| title | Development of a handheld GPU-assisted DSC-TransNet model for the real-time classification of plant leaf disease using deep learning approach |
| title_full | Development of a handheld GPU-assisted DSC-TransNet model for the real-time classification of plant leaf disease using deep learning approach |
| title_fullStr | Development of a handheld GPU-assisted DSC-TransNet model for the real-time classification of plant leaf disease using deep learning approach |
| title_full_unstemmed | Development of a handheld GPU-assisted DSC-TransNet model for the real-time classification of plant leaf disease using deep learning approach |
| title_short | Development of a handheld GPU-assisted DSC-TransNet model for the real-time classification of plant leaf disease using deep learning approach |
| title_sort | development of a handheld gpu assisted dsc transnet model for the real time classification of plant leaf disease using deep learning approach |
| topic | Agriculture Leaf diseases Transformer encoder Depthwise separable convolution Deep learning GPU |
| url | https://doi.org/10.1038/s41598-024-82629-8 |
| work_keys_str_mv | AT midhunpmathew developmentofahandheldgpuassisteddsctransnetmodelfortherealtimeclassificationofplantleafdiseaseusingdeeplearningapproach AT sudheepelayidom developmentofahandheldgpuassisteddsctransnetmodelfortherealtimeclassificationofplantleafdiseaseusingdeeplearningapproach AT vpjagathyraj developmentofahandheldgpuassisteddsctransnetmodelfortherealtimeclassificationofplantleafdiseaseusingdeeplearningapproach AT kmabubeker developmentofahandheldgpuassisteddsctransnetmodelfortherealtimeclassificationofplantleafdiseaseusingdeeplearningapproach |