Template-Type: ReDIF-Article 1.0
Author-Name:MuhammadTariq,  Inam  Ullah,  Muhammad  Afzal  Shah,  Muhammad  Suleman  Soomro, Chudary Akbar Ali
Author-Email:tariqmalik29055@gmail.com
Author-Workplace-Name:School of Computer Science and Technology (Taiyuan University of Science and Technology, Taiyuan, Shanxi, China), University   Institute   of   Information   Technology (PMAS   Arid   Agriculture   University, Rawalpindi, Punjab, Pakistan, School   of   Electronics   Information   Engineering (Taiyuan   University   of   Science   and Technology, Taiyuan, Shanxi, China), School  of  Computer  Science  and  Technology (Wuhan  Textile  University,  Wuhan,  Hubei, China)
Title:Automated Detection and Classification of Tomato Leaf Diseases Using EfficientNetB0 and Deep Learning Techniques
Abstract:Tomato   leaf   diseases   significantly   impact   agricultural   productivity   worldwide, necessitating accurate and timely detection methods. This research proposes a robust and efficient deep learning framework leveraging the “EfficientNetB0”architecture for the  detection  and  classification  of  multiple  tomato  leaf  diseases.  Utilizing  transfer  learning alongside advanced data augmentation techniques, the model was trained on a comprehensive dataset  comprising  six  disease  categories  and  healthy  samples,  sourced from  Kaggle.  The proposed approach achieved an overall accuracy of 88.4%, outperforming traditional methods such as CNN, AlexNet, and S-V-M by a notable margin across all disease classes. Evaluation metrics,including  precision,  recall,  and  F1-score,further  validate  the  model’s  ability  to accurately   distinguish   subtle   disease   symptoms   despite   class   imbalance   challenges. Additionally,   the   lightweight   design   of “EfficientNetB0”enables   potential   real-time applications  in  mobile  and  edge  computing  environments.  These  findings  highlight  the model’s  promise  as  an  effective  tool  for  precision  agriculture,  facilitating  early  disease intervention and reducing crop loss. Future work will focus on expanding the dataset diversity and  deploying  the  system  in  real-world  agricultural  settings  through  mobile  and  drone platforms.
Keywords:EfficientNetB0;  Deep  Learning;  Tomato  Plant  Diseases;  Image  Classification; Transfer Learning
Journal: International Journal of Innovations in Science and Technology
Pages:2212-2224
Volume:7
Issue:3
Year: 2025
Month:September
File-URL:https://journal.50sea.com/index.php/IJIST/article/view/1574/2374
File-Format: Application/pdf
File-URL:https://journal.50sea.com/index.php/IJIST/article/view/1574
File-Format: text/html
Handle: RePEc:abq:IJIST:v:7:y:2025:i:3:p:2212-2224