Abstract
• An effective method for the diagnosis of tomato pests was proposed. • Improved FOA was proposed to optimize the parameter of ResNet50. • The improved FOA was validated on the benchmark functions against other peers. • Experimental results showed the proposed model has ability to diagnose pests. Tomato production is often threatened by the bites of several pests (mainly whiteflies and cotton bollworms). Pests exist throughout the tomato growing season, and it is necessary to detect and prevent these stubborn pests in time to reduce the economic losses caused by pests. Deep learning has been widely used to identify plant diseases and insect pests in recent years. The performance of the deep learning model is greatly affected by the network structure and hyperparameters, especially for hyperparameters, which often require manual participation in selection. To obtain suitable hyperparameters, this paper improves the fruit fly optimization algorithm and uses the improved algorithm to optimize the learning rate of the deep network. The experimental results show that the improved fruit fly optimization algorithm can search for a better learning rate. Among the 6 networks participating in the experiment, IResNet50 has an average diagnostic accuracy of 94.4% for seven tomato pests, which is better than other models.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.