Summary of Advancing Green Ai: Efficient and Accurate Lightweight Cnns For Rice Leaf Disease Identification, by Khairun Saddami et al.
Advancing Green AI: Efficient and Accurate Lightweight CNNs for Rice Leaf Disease Identification
by Khairun Saddami, Yudha Nurdin, Mutia Zahramita, Muhammad Shahreeza Safiruz
First submitted to arxiv on: 3 Aug 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper explores three mobile-compatible CNN architectures (ShuffleNet, MobileNetV2, and EfficientNet-B0) for classifying rice leaf diseases. The models are chosen due to their compatibility with mobile devices, which require less computational power and memory compared to other CNN models. To enhance the performance of these models, two fully connected layers separated by a dropout layer were added. Early stopping was implemented to prevent overfitting. The results show that EfficientNet-B0 achieved an accuracy of 99.8%, outperforming MobileNetV2 (84.21%) and ShuffleNet (66.51%). This study highlights the potential of combining EfficientNet-B0 with proposed layers and early stopping for high-accuracy rice leaf disease classification. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This research helps farmers detect rice diseases earlier, reducing crop losses and improving food security. The scientists tested three special computer models on mobile devices to see which one worked best at identifying rice leaf diseases. They added extra features to the models and stopped them from getting too good (overfitting). The results show that one model, EfficientNet-B0, is really accurate, with an accuracy of 99.8%. This study can help develop a tool for farmers to use on their mobile devices, making it easier to detect rice diseases and grow more food. |
Keywords
» Artificial intelligence » Classification » Cnn » Dropout » Early stopping » Overfitting
