FL-ToLeD: An Improved Lightweight Attention Convolutional Neural Network Model for Tomato Leaf Diseases Classification for Low-End Devices DOI Creative Commons
Mahmoud H. Alnamoly, Abdelhady Mahmoud, Sherine M. Abd El-Kader

и другие.

IEEE Access, Год журнала: 2024, Номер 12, С. 73561 - 73580

Опубликована: Янв. 1, 2024

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 the country's economy. In this study, lightweight convolutional neural network model called FL-ToLeD was proposed for tomato disease classification based on soft attention mechanism with depth-wise separable convolution layer. With size 2.5 MB 221,594 trainable parameters, achieved 99.5%, 99.10%, 99.04% training, validation testing accuracy respectively, 99 % each precision, recall, f1-score, it also 99.90% ROC-AUC average inference time 2.06924 μs. outperformed H. Ulutaş (2023) by 2.2% in terms accuracy, recall f1-score. Additionally, performed better than M. Agarwal (2023), Abbas (2021), S. Verma (2020) f1-score 8%, 2%, 6%, respectively. It Arshad 4.77%, 8.92%, 35.18% 5.11% Furthermore, 90 times smaller size. All makes more suitable low-end devices precision agriculture.

Язык: Английский

XLTLDisNet: A Novel and Lightweight Approach to Identify Tomato Leaf Diseases with Transparency DOI Creative Commons
Aritra Das,

Fahad Pathan,

Jamin Rahman Jim

и другие.

Heliyon, Год журнала: 2025, Номер 11(4), С. e42575 - e42575

Опубликована: Фев. 1, 2025

Agricultural productivity is essential for global economic development by ensuring food security, boosting incomes and supporting employment. It enhances stability, reduces poverty promotes sustainable growth, creating a robust foundation overall progress improved quality of life worldwide. However, crop diseases can significantly affect agricultural output resources. The early detection these to minimize losses maximize production. In this study, novel Deep Learning (DL) model called Explainable Lightweight Tomato Leaf Disease Network (XLTLDisNet) has been proposed. proposed trained evaluated using publicly available PlantVillage tomato leaf disease dataset containing ten classes including healthy images. By leveraging different data augmentation techniques, the approach achieved an impressive accuracy 97.24%, precision 97.20%, recall 96.70% F1-score 97.10%. Additionally, explainable AI techniques such as Gradient-weighted Class Activation Mapping (GRAD-CAM) Local Interpretable Model-agnostic Explanations (LIME) have integrated into enhance explainability interpretability study.

Язык: Английский

Процитировано

0
CustomBottleneck-VGGNet: Advanced tomato leaf disease identification for sustainable agriculture DOI
Mohamed Zarboubi, Abdelaaziz Bellout, Samira Chabaa

и другие.

Computers and Electronics in Agriculture, Год журнала: 2025, Номер 232, С. 110066 - 110066

Опубликована: Фев. 11, 2025

Язык: Английский

Процитировано

0
Deep learning-based classification, detection, and segmentation of tomato leaf diseases: A state-of-the-art review DOI Creative Commons
Aritra Das,

Fahad Pathan,

Jamin Rahman Jim

и другие.

Artificial Intelligence in Agriculture, Год журнала: 2025, Номер 15(2), С. 192 - 220

Опубликована: Фев. 20, 2025

Язык: Английский

Процитировано

0
On construction of data preprocessing for real-life SoyLeaf dataset & disease identification using Deep Learning Models DOI

Sujata Gudge,

Aruna Tiwari, Milind B. Ratnaparkhe

и другие.

Computational Biology and Chemistry, Год журнала: 2025, Номер 117, С. 108417 - 108417

Опубликована: Март 8, 2025

Язык: Английский

Процитировано

0
DWTFormer: a frequency-spatial features fusion model for tomato leaf disease identification DOI Creative Commons
Yuyun Xiang, Shuang Gao, Xiaopeng Li

и другие.

Plant Methods, Год журнала: 2025, Номер 21(1)

Опубликована: Март 11, 2025

Remarkable inter-class similarity and intra-class variability of tomato leaf diseases seriously affect the accuracy identification models. A novel disease model, DWTFormer, based on frequency-spatial feature fusion, was proposed to address this issue. Firstly, a Bneck-DSM module designed extract shallow features, laying groundwork for deep extraction. Then, dual-branch mapping network (DFMM) multi-scale features from frequency spatial domain information. In branch, 2D discrete wavelet transform decomposition effectively captured rich information in image, compensating convolution PVT (Pyramid Vision Transformer)-based developed global local enabling comprehensive representation. Finally, dual-domain fusion model dynamic cross-attention fuse features. Experimental results dataset demonstrated that DWTFormer achieved 99.28% accuracy, outperforming most existing mainstream Furthermore, 96.18% 99.89% accuracies have been obtained AI Challenger 2018 PlantVillage datasets. In-field experiments an 97.22% average inference time 0.028 seconds real plant environments. This work has reduced impact identification. It provides scalable reference fast accurate

Язык: Английский

Процитировано

0
TrioConvTomatoNet-BiLSTM: An Efficient Framework for the Classification of Tomato Leaf Diseases in Real Time Complex Background Images DOI Creative Commons
S. Ledbin Vini,

P. Rathika

International Journal of Computational Intelligence Systems, Год журнала: 2025, Номер 18(1)

Опубликована: Апрель 10, 2025

Язык: Английский

Процитировано

0
Enhancing crop disease recognition via prompt learning-based progressive Mixup and Contrastive Language-Image Pre-training dynamic calibration DOI
Hao Chen, Haidong Li, Jinling Zhao

и другие.

Engineering Applications of Artificial Intelligence, Год журнала: 2025, Номер 152, С. 110805 - 110805

Опубликована: Апрель 14, 2025

Язык: Английский

Процитировано

0
Identify Subtle Fall Hazards Using Transfer Learning DOI Creative Commons
Wen-Ta Hsiao, Wen‐der Yu, Chao‐Hsiun Tang

и другие.

Опубликована: Апрель 22, 2025

Язык: Английский

Процитировано

0
Smart Plant Disease Diagnosis Using Multiple Deep Learning and Web Application Integration DOI Creative Commons

Ahmed M. S. Kheir,

Anis Koubâa,

Vinothkumar Kolluru

и другие.

Journal of Agriculture and Food Research, Год журнала: 2025, Номер 21, С. 101948 - 101948

Опубликована: Апрель 23, 2025

Язык: Английский

Процитировано

0
TomaFDNet: A multiscale focused diffusion-based model for tomato disease detection DOI Creative Commons
Rijun Wang, Yesheng Chen, Fulong Liang

и другие.

Frontiers in Plant Science, Год журнала: 2025, Номер 16

Опубликована: Апрель 24, 2025

Tomatoes are one of the most economically significant crops worldwide, with their yield and quality heavily impacted by foliar diseases. Effective detection these diseases is essential for enhancing agricultural productivity mitigating economic losses. Current tomato leaf disease methods, however, encounter challenges in extracting multi-scale features, identifying small targets, complex background interference. The model Tomato Focus-Diffusion Network (TomaFDNet) was proposed to solve above problems. utilizes a focus-diffusion network (MSFDNet) alongside an efficient parallel convolutional module (EPMSC) significantly enhance extraction features. This combination particularly strengthens model's capability detect targets amidst backgrounds. Experimental results show that TomaFDNet reaches mean average precision (mAP) 83.1% detecting Early_blight, Late_blight, Leaf_Mold on leaves, outperforming classical object algorithms, including Faster R-CNN (mAP = 68.2%) You Only Look Once (YOLO) series (v5: mAP 75.5%, v7: 78.3%, v8: 78.9%, v9: 79%, v10: 77.5%, v11: 79.2%). Compared baseline YOLOv8 model, achieves 4.2% improvement mAP, which statistically (P < 0.01). These findings indicate offers valid solution precise

Язык: Английский

Процитировано

0