Exploring multiple optimization algorithms in transfer learning with EfficientNet models for agricultural insect classification
Dangerous insects are a significant risk to the global agricultural industry, threatening food security, economic stability, and crop quality. This study investigates the impact of multiple optimization algorithms within transfer learning, employing EfficientNet models for the classification of agr...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Can Tho University Publisher
2024-10-01
|
| Series: | CTU Journal of Innovation and Sustainable Development |
| Subjects: | |
| Online Access: | http://web2010.thanhtoan/index.php/ctujs/article/view/1136 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849694825597632512 |
|---|---|
| author | Hoang-Tu Vo Nhon Nguyen Thien Kheo Chau Mui Huan Lam Le Phuc Pham Tien |
| author_facet | Hoang-Tu Vo Nhon Nguyen Thien Kheo Chau Mui Huan Lam Le Phuc Pham Tien |
| author_sort | Hoang-Tu Vo |
| collection | DOAJ |
| description |
Dangerous insects are a significant risk to the global agricultural industry, threatening food security, economic stability, and crop quality. This study investigates the impact of multiple optimization algorithms within transfer learning, employing EfficientNet models for the classification of agricultural insects. The explored optimization algorithms include Adam, Adamax, AdamW, RMSprop, and SGD, while utilizing the EfficientNetB0, EfficientNetB3, EfficientNetB5, and EfficientNetB7 architectures. Experimental results show notable performance differences between optimization algorithms across all EfficiencyNet models in the study. Among the measured metrics are precision, recall, f1-score, accuracy, and loss, the AdamW optimizer consistently demonstrates superior performance compared to other algorithms. The findings underscore the critical influence of optimization algorithms in enhancing classification accuracy and convergence within transfer learning scenarios. Additionally, the study employs various visualization techniques, such as Gradient-weighted Class Activation Mapping (Grad-CAM) to enhance the interpretation of the image classification model’s results. By focusing on these methodologies, this research aims to improve the model’s performance, optimize its capabilities, and ultimately contribute to effective pest management strategies in agriculture, safeguarding crop yields, farmer livelihoods, and global food security.
|
| format | Article |
| id | doaj-art-00d8faca2cc44809b0d3bfb5b4e50192 |
| institution | DOAJ |
| issn | 2588-1418 2815-6412 |
| language | English |
| publishDate | 2024-10-01 |
| publisher | Can Tho University Publisher |
| record_format | Article |
| series | CTU Journal of Innovation and Sustainable Development |
| spelling | doaj-art-00d8faca2cc44809b0d3bfb5b4e501922025-08-20T03:19:57ZengCan Tho University PublisherCTU Journal of Innovation and Sustainable Development2588-14182815-64122024-10-0116Special issue: ISDSExploring multiple optimization algorithms in transfer learning with EfficientNet models for agricultural insect classificationHoang-Tu Vo0Nhon Nguyen ThienKheo Chau MuiHuan Lam LePhuc Pham Tiena:1:{s:5:"en_US";s:73:"Information Technology Department, FPT University, Can Tho 94000, Vietnam";} Dangerous insects are a significant risk to the global agricultural industry, threatening food security, economic stability, and crop quality. This study investigates the impact of multiple optimization algorithms within transfer learning, employing EfficientNet models for the classification of agricultural insects. The explored optimization algorithms include Adam, Adamax, AdamW, RMSprop, and SGD, while utilizing the EfficientNetB0, EfficientNetB3, EfficientNetB5, and EfficientNetB7 architectures. Experimental results show notable performance differences between optimization algorithms across all EfficiencyNet models in the study. Among the measured metrics are precision, recall, f1-score, accuracy, and loss, the AdamW optimizer consistently demonstrates superior performance compared to other algorithms. The findings underscore the critical influence of optimization algorithms in enhancing classification accuracy and convergence within transfer learning scenarios. Additionally, the study employs various visualization techniques, such as Gradient-weighted Class Activation Mapping (Grad-CAM) to enhance the interpretation of the image classification model’s results. By focusing on these methodologies, this research aims to improve the model’s performance, optimize its capabilities, and ultimately contribute to effective pest management strategies in agriculture, safeguarding crop yields, farmer livelihoods, and global food security. http://web2010.thanhtoan/index.php/ctujs/article/view/1136Deep learning, explainable AI, grad-cam, insect identification, optimization algorithm, transfer learning |
| spellingShingle | Hoang-Tu Vo Nhon Nguyen Thien Kheo Chau Mui Huan Lam Le Phuc Pham Tien Exploring multiple optimization algorithms in transfer learning with EfficientNet models for agricultural insect classification CTU Journal of Innovation and Sustainable Development Deep learning, explainable AI, grad-cam, insect identification, optimization algorithm, transfer learning |
| title | Exploring multiple optimization algorithms in transfer learning with EfficientNet models for agricultural insect classification |
| title_full | Exploring multiple optimization algorithms in transfer learning with EfficientNet models for agricultural insect classification |
| title_fullStr | Exploring multiple optimization algorithms in transfer learning with EfficientNet models for agricultural insect classification |
| title_full_unstemmed | Exploring multiple optimization algorithms in transfer learning with EfficientNet models for agricultural insect classification |
| title_short | Exploring multiple optimization algorithms in transfer learning with EfficientNet models for agricultural insect classification |
| title_sort | exploring multiple optimization algorithms in transfer learning with efficientnet models for agricultural insect classification |
| topic | Deep learning, explainable AI, grad-cam, insect identification, optimization algorithm, transfer learning |
| url | http://web2010.thanhtoan/index.php/ctujs/article/view/1136 |
| work_keys_str_mv | AT hoangtuvo exploringmultipleoptimizationalgorithmsintransferlearningwithefficientnetmodelsforagriculturalinsectclassification AT nhonnguyenthien exploringmultipleoptimizationalgorithmsintransferlearningwithefficientnetmodelsforagriculturalinsectclassification AT kheochaumui exploringmultipleoptimizationalgorithmsintransferlearningwithefficientnetmodelsforagriculturalinsectclassification AT huanlamle exploringmultipleoptimizationalgorithmsintransferlearningwithefficientnetmodelsforagriculturalinsectclassification AT phucphamtien exploringmultipleoptimizationalgorithmsintransferlearningwithefficientnetmodelsforagriculturalinsectclassification |