Accuracy improvement in disease identification of guava leaf using random forest algorithm compared with fuzzy algorithm

The aim of this work is to calculate the accuracy in the identification of Guava leaf disease using Random Forest Compared with the Fuzzy logic framework. The data set contains 20 images collected from the seed buzz website and these images are used for training and testing the predictive model in M...

Full description

Saved in:
Bibliographic Details
Main Authors: Chowdary, M. Sivaram, Puviarasi, R.
Format: Conference Proceeding
Language:English
Subjects:
Accuracy
Algorithms
Fuzzy logic
Guava
Plant diseases
Prediction models
Statistical analysis
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The aim of this work is to calculate the accuracy in the identification of Guava leaf disease using Random Forest Compared with the Fuzzy logic framework. The data set contains 20 images collected from the seed buzz website and these images are used for training and testing the predictive model in MATLAB. Statistical analysis is done using SPSS software. The sample size of the two groups is calculated using the G power tool with a pretest power of 0.8. The propo sed system using Random Forest (RF) achieved a better mean accuracy of 94.88±0.161 and the sensitivity of 93.10±0.305 followed by the Fuzzy model produces 89.12±0.496 accuracy and the sensitivity of 87.61±0.111. The significance value for accuracy is 0.037 and for sensitivity 0.073 which are obtained from statistical analysis in SPSS. The outcome of the study shows that the Random Forest based model appears to better result in enhancing the accuracy of disease identification in Guava leaves.
ISSN:0094-243X
1551-7616
DOI:10.1063/5.0159397