IoT-RiceMobileNet: An improved lightweight MobileNetV2 Model for real-time multi-class rice disease detection using IoT
- 1Department of Computer Science and Engineering, Dhaka University of Engineering & Technology, Gazipur, Bangladesh
- 2AI and Big Data Department, Endicott College, Woosong University, Daejeon, South Korea
- 3Anuradha and Vikas Sinha Department of Data Science, University of North Texas, Denton, Texas, United States of America
Abstract
Early and real-time detection of rice leaf diseases (RLD) poses a significant challenge for farmers, especially in rural regions with limited access to advanced technology. Conventional deep learning models often require substantial computational resources, rendering them impractical for deployment on mobile or edge devices commonly used in agricultural environments. Although models such as ResNet50, VGG16, and InceptionV3 can achieve high accuracy, they are computationally expensive and may be less suitable for real-time deployment in smart agricultural systems. Furthermore, many existing studies rely on limited datasets, which can restrict model generalizability under diverse real-world conditions. Although transfer learning can improve classification performance, developing lightweight models suitable for real-time IoT deployment remains challenging. To address these limitations, we curated a hybrid dataset of 7,092 rice leaf images by combining self-collected and Kaggle samples and proposed IoT-RiceMobileNet, a lightweight improved MobileNetV2-based model that can be effectively integrated into our developed IoT system. The proposed model outperformed transfer learning and deep learning baseline models, achieving 99.19% test accuracy and 99.20% precision while maintaining low computational complexity. We further confirmed model stability using stratified 5-fold and 10-fold cross-validation on both the constructed RLD and multi-source datasets, achieving mean accuracies of 98.04% and 98.13% on the constructed RLD dataset and 98.11% and 98.58% on the multi-source dataset, respectively. Moreover, our models compact size and 85.17 FPS inference speed support real-time deployment. Finally, the model was integrated into an IoT-enabled mobile, web, and cloud-based inference framework, demonstrating its practical potential for scalable rice disease detection in smart agriculture.
Related
- Deep learning-based detection of construction waste in complex scenarios with an improved lightweight algorithm
- LeafXNet: A Lightweight Explainable Model With Integrated Attention Mechanism for Fruit Leaf Disease Detection
- Cross-level attention and lightweight feature extraction for improved tomato ripeness detection in complex greenhouse environments
- HECA-MobileNet: an explainable lightweight attention-based deep learning framework for custard apple disease detection
- Efficient-tomato: a high-precision and lightweight method for cherry tomato ripeness and disease detection
BibTeX
@article{masud2026iotricemobilenet,
title = {{IoT-RiceMobileNet: An improved lightweight MobileNetV2 Model for real-time multi-class rice disease detection using IoT}},
author = {Khawja Imran Masud and Md Yasin Zihad and Mehedi Hasan Shuvo and Mst Raonik Jannat and Jia Uddin and Sahara Ali},
journal = {PLOS One},
year = {2026},
month = sep,
doi = {10.1371/journal.pone.0356383},
url = {https://doi.org/10.1371/journal.pone.0356383},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - IoT-RiceMobileNet: An improved lightweight MobileNetV2 Model for real-time multi-class rice disease detection using IoT
AU - Khawja Imran Masud
AU - Md Yasin Zihad
AU - Mehedi Hasan Shuvo
AU - Mst Raonik Jannat
AU - Jia Uddin
AU - Sahara Ali
PY - 2026
DA - 2026/09/15
JO - PLOS One
DO - 10.1371/journal.pone.0356383
UR - https://doi.org/10.1371/journal.pone.0356383
AB - Early and real-time detection of rice leaf diseases (RLD) poses a significant challenge for farmers, especially in rural regions with limited access to advanced technology. Conventional deep learning models often require substantial computational resources, rendering them impractical for deployment on mobile or edge devices commonly used in agricultural environments. Although models such as ResNet50, VGG16, and InceptionV3 can achieve high accuracy, they are computationally expensive and may be less suitable for real-time deployment in smart agricultural systems. Furthermore, many existing studies rely on limited datasets, which can restrict model generalizability under diverse real-world conditions. Although transfer learning can improve classification performance, developing lightweight models suitable for real-time IoT deployment remains challenging. To address these limitations, we curated a hybrid dataset of 7,092 rice leaf images by combining self-collected and Kaggle samples and proposed IoT-RiceMobileNet, a lightweight improved MobileNetV2-based model that can be effectively integrated into our developed IoT system. The proposed model outperformed transfer learning and deep learning baseline models, achieving 99.19% test accuracy and 99.20% precision while maintaining low computational complexity. We further confirmed model stability using stratified 5-fold and 10-fold cross-validation on both the constructed RLD and multi-source datasets, achieving mean accuracies of 98.04% and 98.13% on the constructed RLD dataset and 98.11% and 98.58% on the multi-source dataset, respectively. Moreover, our models compact size and 85.17 FPS inference speed support real-time deployment. Finally, the model was integrated into an IoT-enabled mobile, web, and cloud-based inference framework, demonstrating its practical potential for scalable rice disease detection in smart agriculture.
SN - 1932-6203
ER -