International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
|
Volume 186 - Issue 31 |
Published: August 2024 |
Authors: R. Shivali, E. Elakiya, B. Surendiran |
![]() |
R. Shivali, E. Elakiya, B. Surendiran . Boosting Crop Yields: A Hybrid Approach to Intelligent Plant Disease Identification and Prediction. International Journal of Computer Applications. 186, 31 (August 2024), 55-62. DOI=10.5120/ijca2024923889
@article{ 10.5120/ijca2024923889, author = { R. Shivali,E. Elakiya,B. Surendiran }, title = { Boosting Crop Yields: A Hybrid Approach to Intelligent Plant Disease Identification and Prediction }, journal = { International Journal of Computer Applications }, year = { 2024 }, volume = { 186 }, number = { 31 }, pages = { 55-62 }, doi = { 10.5120/ijca2024923889 }, publisher = { Foundation of Computer Science (FCS), NY, USA } }
%0 Journal Article %D 2024 %A R. Shivali %A E. Elakiya %A B. Surendiran %T Boosting Crop Yields: A Hybrid Approach to Intelligent Plant Disease Identification and Prediction%T %J International Journal of Computer Applications %V 186 %N 31 %P 55-62 %R 10.5120/ijca2024923889 %I Foundation of Computer Science (FCS), NY, USA
Plant diseases are a major challenge for global food safety, and therefore it is impossible to underestimate the role of diagnostic methods. This paper promotes an integrated scheme that combines the capabilities of CNN and InceptionV3 models in order to diagnose plant disease. The proposed model integrates image processing algorithms, feature extraction techniques and ensemble learning in order to enhance accuracy and robustness. For evaluation purposes, we have used an all-inclusive dataset containing various ailments associated with corn maize rust, potato early blight, and tomato early blight. The dataset was divided into an 80-20 split ratio for training and testing respectively. Our findings are highly encouraging since the hybrid model recorded an accuracy level of 98.04%. Therefore, this research advances detection methodologies for plant ailments which could provide a dependable solution for use in agriculture. There is also future work that looks at tribrid models as well as comparison with existing literature to further enhance detection accuracy.