FL-ToLeD: An Improved Lightweight Attention Convolutional Neural Network Model for Tomato Leaf Diseases Classification for Low-End Devices
Mahmoud H. Alnamoly, Anar A. Hady, Sherine M. Abd El-Kader, Ibrahim El-Henawy
Abstract
The agricultural sector is still a major provider of many countries’ economies, but diseases that continuously infect plants represent continuous threats to agriculture and cause massive losses to the country’s economy. In this study, a lightweight convolutional neural network model called FL-ToLeD was proposed for tomato disease classification based on a soft attention mechanism with a depth-wise separable convolution layer. With a model size of 2.5 MB and 221,594 trainable parameters, FL-ToLeD achieved 99.5%, 99.10%, 99.04% for training, validation and testing accuracy respectively, and 99 % for each of precision, recall, and f1-score, it also achieved 99.90% for ROC-AUC with average inference time of 2.06924 μs. FL-ToLeD outperformed H. Ulutaş (2023) by 2.2% in terms of accuracy, precision, recall and f1-score. Additionally, it performed better than M. Agarwal (2023), Abbas (2021), and S. Verma (2020) in terms of accuracy, precision, recall, and f1-score by 8%, 2%, and 6%, respectively. It also outperformed Arshad (2023) by 4.77%, 8.92%, 35.18% and 5.11% in terms of accuracy, precision, recall and f1-score, respectively. Furthermore, FL-ToLeD is 90 times smaller than S. Verma (2020) and 2.5 times smaller than H. Ulutaş (2023) in terms of model size. All this makes FL-ToLeD more suitable for low-end devices in precision agriculture.