Chrome Extension
WeChat Mini Program
Use on ChatGLM

Optimizing Crop Health: The Efficacy of a CNN-RF Hybrid Approach in Disease Identification

2024 IEEE 9th International Conference for Convergence in Technology (I2CT)(2024)

Cited 0|Views2
No score
Abstract
The purpose of this study is to investigate and evaluate the effectiveness of a one-of-a-kind CNN-RF hybrid model that was developed for the classification of plant diseases, with a particular emphasis on the scenario that is pertinent to rice production. The categorization of various plant diseases serves as the basis for the development of the model. The accuracy numbers, which range from 83.2% to 93.2%, demonstrate that the model is able to categorize occurrences that fall inside each category of unique diseases in a reliable way. This is shown by the fact that the accuracy values vary. The ability of a model to correctly identify occurrences that are really indicative of each disease class is contingent upon the model having recall values that are continuously high, ranging between 85.7% and 88.5%. This is evidence that the model is able to do the task in question. The F1 scores suggest a range that runs from 85.8% to 89.3% of the total, taking into account both the accuracy and the recall of the information. The tremendous capabilities of the model to provide accurate classifications over a wide range of illness categories are shown by the fact that it has achieved an impressive accuracy range of 94% to 96%.
More
Translated text
Key words
Diseases,Random Forest (RF),Agriculture,Convolutional Neural Network (CNN)
AI Read Science
Must-Reading Tree
Example
Generate MRT to find the research sequence of this paper
Chat Paper
Summary is being generated by the instructions you defined