IoT Agricultural Pest Identification Based on Multiple Convolutional Models

3Citations
Citations of this article
12Readers
Mendeley users who have this article in their library.

Abstract

This topic focuses on the corresponding research and simulation of multiple convolutional models for the detection methods of leaf pests and disease identification. Currently, crop pest identification in China mainly relies on field observation by farmers or experts, which is less accurate, time-consuming and extremely expensive, and not feasible for millions of small and medium-sized farms. To improve the recognition accuracy, crop pest recognition is performed by a convolutional neural network (CNN) after combining the plant leaf collection dataset, which has the features of automatic image feature extraction, strong generalization ability, and high recognition rate, and combined with the advantage of similarity by transfer learning, a crop pest recognition algorithm based on the comparison of multiple convolutional neural networks is implemented. After comparison experiments, the algorithm has 99.8% accuracy in the test set and can accurately distinguish seven health states of apples and grapes. This algorithm can help agricultural workers to conduct agricultural activities more scientifically, which is important for improving crop yield and agricultural intelligence.

Cite

CITATION STYLE

APA

Zhang, Y. (2023). IoT Agricultural Pest Identification Based on Multiple Convolutional Models. Journal of Internet Technology, 24(4), 905–913. https://doi.org/10.53106/160792642023072404008

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Save time finding and organizing research with Mendeley

Sign up for free