TY  - JOUR
AU  - Farooq, Fahad
AU  - Muneer, Muhammad Haris
AU  - Babar, Muhammad
AU  - Zahid, Faizan
PY  - 2025
DA  - 2025/04/15
TI  - Smart Ground Robot for Real-Time Detection of Tomato Diseases Using Deep Learning and IoT Technologies
JO  - ICCK Transactions on Sensing, Communication, and Control
T2  - ICCK Transactions on Sensing, Communication, and Control
JF  - ICCK Transactions on Sensing, Communication, and Control
VL  - 2
IS  - 2
SP  - 66
EP  - 74
DO  - 10.62762/TSCC.2024.593301
UR  - https://www.icck.org/article/abs/TSCC.2024.593301
KW  - automated systems
KW  - agricultural robotics
KW  - internet of things (IoT)
KW  - deep learning
KW  - tomato disease detection
KW  - raspberry Pi 4
AB  - This study presents an intelligent automated system for real-time detection and classification of tomato diseases using a Convolutional Neural Network (CNN) integrated within an Internet of Things (IoT) based unmanned ground vehicle (UGV). The CNN was trained and evaluated using a dataset comprising over 20,000 images of tomato leaves categorized into ten distinct diseases—Late Blight, Early Blight, Septoria Leaf Spot, Tomato Yellow Leaf Curl Virus, Bacterial Spot, Target Spot, Tomato Mosaic Virus, Leaf Mold, Spider Mites Two-Spotted Spider Mite, Powdery Mildew—and healthy leaves. The developed CNN architecture, optimized for lightweight deployment on edge devices like Raspberry Pi 4, achieved an overall accuracy of approximately 83%, with notable variations across classes in precision, recall, and F1-score. Specifically, high precision scores (above 80%) were obtained for diseases such as Bacterial Spot, Late Blight, and Tomato Yellow Leaf Curl Virus, while moderate scores in diseases exhibiting subtle visual symptoms underscored areas for future refinement. The UGV autonomously navigates tomato fields, captures high-resolution images of leaves, and conducts on-site real-time disease classification, significantly reducing the labor, human error, and time associated with traditional manual inspections. Comprehensive quantitative analyses, including confusion matrices and visual assessments of classified samples, validate the practical viability and robustness of the proposed system, although certain misclassifications highlight opportunities to enhance training data diversity and model generalizability in future work. The integration of deep learning and IoT technologies demonstrated in this study substantially advances precision agriculture, improving disease management practices and promoting sustainable agricultural productivity.
SN  - 3068-9287
PB  - Institute of Central Computation and Knowledge
LA  - English
ER  - 

@article{Farooq2025Smart,
  author = {Fahad Farooq and Muhammad Haris Muneer and Muhammad Babar and Faizan Zahid},
  title = {Smart Ground Robot for Real-Time Detection of Tomato Diseases Using Deep Learning and IoT Technologies},
  journal = {ICCK Transactions on Sensing, Communication, and Control},
  year = {2025},
  volume = {2},
  number = {2},
  pages = {66-74},
  doi = {10.62762/TSCC.2024.593301},
  url = {https://www.icck.org/article/abs/TSCC.2024.593301},
  abstract = {This study presents an intelligent automated system for real-time detection and classification of tomato diseases using a Convolutional Neural Network (CNN) integrated within an Internet of Things (IoT) based unmanned ground vehicle (UGV). The CNN was trained and evaluated using a dataset comprising over 20,000 images of tomato leaves categorized into ten distinct diseases—Late Blight, Early Blight, Septoria Leaf Spot, Tomato Yellow Leaf Curl Virus, Bacterial Spot, Target Spot, Tomato Mosaic Virus, Leaf Mold, Spider Mites Two-Spotted Spider Mite, Powdery Mildew—and healthy leaves. The developed CNN architecture, optimized for lightweight deployment on edge devices like Raspberry Pi 4, achieved an overall accuracy of approximately 83\%, with notable variations across classes in precision, recall, and F1-score. Specifically, high precision scores (above 80\%) were obtained for diseases such as Bacterial Spot, Late Blight, and Tomato Yellow Leaf Curl Virus, while moderate scores in diseases exhibiting subtle visual symptoms underscored areas for future refinement. The UGV autonomously navigates tomato fields, captures high-resolution images of leaves, and conducts on-site real-time disease classification, significantly reducing the labor, human error, and time associated with traditional manual inspections. Comprehensive quantitative analyses, including confusion matrices and visual assessments of classified samples, validate the practical viability and robustness of the proposed system, although certain misclassifications highlight opportunities to enhance training data diversity and model generalizability in future work. The integration of deep learning and IoT technologies demonstrated in this study substantially advances precision agriculture, improving disease management practices and promoting sustainable agricultural productivity.},
  keywords = {automated systems, agricultural robotics, internet of things (IoT), deep learning, tomato disease detection, raspberry Pi 4},
  issn = {3068-9287},
  publisher = {Institute of Central Computation and Knowledge}
}