International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
|
Volume 186 - Issue 45 |
Published: October 2024 |
Authors: Ali Raza, Muhammad Subhan |
![]() |
Ali Raza, Muhammad Subhan . Enhancing Tea Plant Health Through Machine Learning: EfficientNet-B0 for Tea Sickness Detection. International Journal of Computer Applications. 186, 45 (October 2024), 32-43. DOI=10.5120/ijca2024924092
@article{ 10.5120/ijca2024924092, author = { Ali Raza,Muhammad Subhan }, title = { Enhancing Tea Plant Health Through Machine Learning: EfficientNet-B0 for Tea Sickness Detection }, journal = { International Journal of Computer Applications }, year = { 2024 }, volume = { 186 }, number = { 45 }, pages = { 32-43 }, doi = { 10.5120/ijca2024924092 }, publisher = { Foundation of Computer Science (FCS), NY, USA } }
%0 Journal Article %D 2024 %A Ali Raza %A Muhammad Subhan %T Enhancing Tea Plant Health Through Machine Learning: EfficientNet-B0 for Tea Sickness Detection%T %J International Journal of Computer Applications %V 186 %N 45 %P 32-43 %R 10.5120/ijca2024924092 %I Foundation of Computer Science (FCS), NY, USA
Tea is a globally important crop that is prone to numerous diseases that can significantly affect its quality and production. This study proposes a novel work of improving the health of tea plants through Machine Learning (ML) for tea sickness detection from the EfficientNet-B0 convolutional neural network (CNN). By training the model on a comprehensive dataset of tea leaf images, significant improvements in disease detection accuracy were achieved. The architecture of the EfficientNet-B0 was well optimized explicitly for the use of this study and its test accuracy is 94.64%. This performance highlights the ability of the model as a classifier of the healthy and diseased tea leaves. EfficientNet-B0 is a promising solution to better manage and detect diseases in the initial stages, which confirmed the effectiveness when applied in this context. This stays in contrast to the traditional disease diagnosing approach in agriculture. This approach is an improvement by combining Deep Learning (DL) with real-life applications in farming.