Intelligent Cotton Pest and Disease Detection: Edge Computing Solutions with Transformer Technology and Knowledge Graphs
In this study, a deep-learning-based intelligent detection model was designed and implemented to rapidly detect cotton pests and diseases. The model integrates cutting-edge Transformer technology and knowledge graphs, effectively enhancing pest and disease feature recognition precision. With the app...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-02-01
|
| Series: | Agriculture |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2077-0472/14/2/247 |
| _version_ | 1827344398729347072 |
|---|---|
| author | Ruicheng Gao Zhancai Dong Yuqi Wang Zhuowen Cui Muyang Ye Bowen Dong Yuchun Lu Xuaner Wang Yihong Song Shuo Yan |
| author_facet | Ruicheng Gao Zhancai Dong Yuqi Wang Zhuowen Cui Muyang Ye Bowen Dong Yuchun Lu Xuaner Wang Yihong Song Shuo Yan |
| author_sort | Ruicheng Gao |
| collection | DOAJ |
| description | In this study, a deep-learning-based intelligent detection model was designed and implemented to rapidly detect cotton pests and diseases. The model integrates cutting-edge Transformer technology and knowledge graphs, effectively enhancing pest and disease feature recognition precision. With the application of edge computing technology, efficient data processing and inference analysis on mobile platforms are facilitated. Experimental results indicate that the proposed method achieved an accuracy rate of 0.94, a mean average precision (mAP) of 0.95, and frames per second (FPS) of 49.7. Compared with existing advanced models such as YOLOv8 and RetinaNet, improvements in accuracy range from 3% to 13% and in mAP from 4% to 14%, and a significant increase in processing speed was noted, ensuring rapid response capability in practical applications. Future research directions are committed to expanding the diversity and scale of datasets, optimizing the efficiency of computing resource utilization and enhancing the inference speed of the model across various devices. Furthermore, integrating environmental sensor data, such as temperature and humidity, is being considered to construct a more comprehensive and precise intelligent pest and disease detection system. |
| first_indexed | 2024-03-07T22:46:40Z |
| format | Article |
| id | doaj.art-79ca2adc0c5f495795b93c8d6a2a0eef |
| institution | Directory Open Access Journal |
| issn | 2077-0472 |
| language | English |
| last_indexed | 2024-03-07T22:46:40Z |
| publishDate | 2024-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Agriculture |
| spelling | doaj.art-79ca2adc0c5f495795b93c8d6a2a0eef2024-02-23T15:03:43ZengMDPI AGAgriculture2077-04722024-02-0114224710.3390/agriculture14020247Intelligent Cotton Pest and Disease Detection: Edge Computing Solutions with Transformer Technology and Knowledge GraphsRuicheng Gao0Zhancai Dong1Yuqi Wang2Zhuowen Cui3Muyang Ye4Bowen Dong5Yuchun Lu6Xuaner Wang7Yihong Song8Shuo Yan9China Agricultural University, Beijing 100083, ChinaChina Agricultural University, Beijing 100083, ChinaChina Agricultural University, Beijing 100083, ChinaChina Agricultural University, Beijing 100083, ChinaChina Agricultural University, Beijing 100083, ChinaChina Agricultural University, Beijing 100083, ChinaChina Agricultural University, Beijing 100083, ChinaChina Agricultural University, Beijing 100083, ChinaChina Agricultural University, Beijing 100083, ChinaChina Agricultural University, Beijing 100083, ChinaIn this study, a deep-learning-based intelligent detection model was designed and implemented to rapidly detect cotton pests and diseases. The model integrates cutting-edge Transformer technology and knowledge graphs, effectively enhancing pest and disease feature recognition precision. With the application of edge computing technology, efficient data processing and inference analysis on mobile platforms are facilitated. Experimental results indicate that the proposed method achieved an accuracy rate of 0.94, a mean average precision (mAP) of 0.95, and frames per second (FPS) of 49.7. Compared with existing advanced models such as YOLOv8 and RetinaNet, improvements in accuracy range from 3% to 13% and in mAP from 4% to 14%, and a significant increase in processing speed was noted, ensuring rapid response capability in practical applications. Future research directions are committed to expanding the diversity and scale of datasets, optimizing the efficiency of computing resource utilization and enhancing the inference speed of the model across various devices. Furthermore, integrating environmental sensor data, such as temperature and humidity, is being considered to construct a more comprehensive and precise intelligent pest and disease detection system.https://www.mdpi.com/2077-0472/14/2/247cotton pest detectionedge computing in farmingobject detectionmobile applicationdataset augmentation |
| spellingShingle | Ruicheng Gao Zhancai Dong Yuqi Wang Zhuowen Cui Muyang Ye Bowen Dong Yuchun Lu Xuaner Wang Yihong Song Shuo Yan Intelligent Cotton Pest and Disease Detection: Edge Computing Solutions with Transformer Technology and Knowledge Graphs Agriculture cotton pest detection edge computing in farming object detection mobile application dataset augmentation |
| title | Intelligent Cotton Pest and Disease Detection: Edge Computing Solutions with Transformer Technology and Knowledge Graphs |
| title_full | Intelligent Cotton Pest and Disease Detection: Edge Computing Solutions with Transformer Technology and Knowledge Graphs |
| title_fullStr | Intelligent Cotton Pest and Disease Detection: Edge Computing Solutions with Transformer Technology and Knowledge Graphs |
| title_full_unstemmed | Intelligent Cotton Pest and Disease Detection: Edge Computing Solutions with Transformer Technology and Knowledge Graphs |
| title_short | Intelligent Cotton Pest and Disease Detection: Edge Computing Solutions with Transformer Technology and Knowledge Graphs |
| title_sort | intelligent cotton pest and disease detection edge computing solutions with transformer technology and knowledge graphs |
| topic | cotton pest detection edge computing in farming object detection mobile application dataset augmentation |
| url | https://www.mdpi.com/2077-0472/14/2/247 |
| work_keys_str_mv | AT ruichenggao intelligentcottonpestanddiseasedetectionedgecomputingsolutionswithtransformertechnologyandknowledgegraphs AT zhancaidong intelligentcottonpestanddiseasedetectionedgecomputingsolutionswithtransformertechnologyandknowledgegraphs AT yuqiwang intelligentcottonpestanddiseasedetectionedgecomputingsolutionswithtransformertechnologyandknowledgegraphs AT zhuowencui intelligentcottonpestanddiseasedetectionedgecomputingsolutionswithtransformertechnologyandknowledgegraphs AT muyangye intelligentcottonpestanddiseasedetectionedgecomputingsolutionswithtransformertechnologyandknowledgegraphs AT bowendong intelligentcottonpestanddiseasedetectionedgecomputingsolutionswithtransformertechnologyandknowledgegraphs AT yuchunlu intelligentcottonpestanddiseasedetectionedgecomputingsolutionswithtransformertechnologyandknowledgegraphs AT xuanerwang intelligentcottonpestanddiseasedetectionedgecomputingsolutionswithtransformertechnologyandknowledgegraphs AT yihongsong intelligentcottonpestanddiseasedetectionedgecomputingsolutionswithtransformertechnologyandknowledgegraphs AT shuoyan intelligentcottonpestanddiseasedetectionedgecomputingsolutionswithtransformertechnologyandknowledgegraphs |