Jul 2026· 2026 International Conference on Advanced Computing and Knowledge Engineering (ICACKE)· pp. 1-6· 0 citations· 25 references
Abstract
Precise identification of a disease in a crop is a critical step in protecting yields, optimizing inputs, and managing this sustainably. Decisions based on image-based deep learning models have achieved high diagnostic accuracy on controlled datasets, but in field variability, similar symptoms, nutrient stress and unfavorable environmental conditions, the decisions based on images could be uncertain. Study compares the performance of classical machine learning baselines, custom-trained convolutional neural networks (CNNs), and pretrained or transfer learning models on the challenging PlantVillage benchmark dataset with 54,305 RGB images of leaves across 38 crop-health classes and 14 plant species. The overall best classical methods was SVC using RBF kernel with high accuracy of 83.58% and F1 score of 82.96%. As depth and regularization increased, it was observed that the accuracy gradually increased and reached 95.71% for the functional CNN with dropout. The best results at the image level were obtained by the Transfer learning method: MobileNetV2 reached an accuracy of 99.30% and an F1-score of 99.30%. Based on these findings, the paper proposes an interpretable multimodal transfer learning decision-support architecture, comprising a MobileNetV2 image encoder, a residual MLP for soil attributes and dual LSTM encoders for a 48-hour and a 168-hour weather window. The evidence image, soil, full-weather and shortweather evidence are respectively assigned explicit weights of 0.80, 0.10, 0.05, and 0.05 in the proposed late-fusion mechanism. The framework is modular, explainable, and as desirable as possible in situations of decision support in the field where a diagnostic aspect is to be enhanced by the agronomic context.
Plant diseases have long been considered a major threat to global food production systems. Therefore, early diagnosis is vital to mitigate the risk of these diseases. This task can be challenging, as the number of harmful diseases is substantial. One technology that has gained widespread interest is artificial intelligence, specifically deep learning, which is used to identify plant diseases using leaf patterns. This paper presents two deep learning models, a custom CNN model and a transfer learning model based on the DenseNet-121 architecture. Experiments were carried out using the PlantCity dataset, which consists of twelve subsets of diverse crop species representing fruits, vegetables, and grains with variations among the subsets, including the number of classes, the subset sizes, class distribution, and visual complexity of disease symptoms. The two models were evaluated using multiple metrics, including accuracy, loss, precision, recall, and F1-score. Explainable AI using the LIME technique was deployed to better interpret the acquired results. Results showed that the developed transfer learning model based on DenseNet-121 had superior performance over the CNN model, with accuracies ranging from 86% to 99% across eleven experimented crops. In order to perform an independent experimental validation for the developed model, future work will focus on constructing a local crop dataset captured from Iraqi fields to evaluate the developed models based on the local environment.
H. Jeiad, S. Samaan, Omar Janeh et al.· Automation· 0 citations
Plant diseases greatly affect agricultural production, especially in developing countries, where prompt diagnosis can be quite challenging due to the limited availability of experts in real-time. Deep learning techniques for image analysis is gaining popularity and are increasingly considered an alternative to traditional manual inspection of plants. This research presents the evaluation of plant leaf disease detection system based on a convolutional neural network (CNN) optimized with different nature-inspired algorithms. The backbone model is based on the EfficientNet-B0 pretrained on ImageNet. Therefore, transfer learning is used to adapt the model to an updated PlantVillage dataset. Experiments have been conducted with multiple nature-inspired algorithms to improve generalisation and training efficiency of the prediction model. Different data preparation techniques have been carefully applied to the dataset, creating a unified approach to ensure consistency in the preprocessing pipeline for the training, validation, and testing phases. Our experiments indicate that application of the grey wolf optimizer (GWO) for tuning key hyperparameters of the model, including dropout, learning rates, and weight decay produced the best results, with and accuracy around 99.45%.
Plant diseases threaten global agriculture, causing 20–40% yield losses and food insecurity. Current diagnostic methods are costly and lack scalability. While deep learning advances plant disease detection, there remains a need for CNNs with simpler architectures, better generalizability, and lower computational cost. This study presents a novel CNN for multi-class classification of 38 diseases. Trained on a public dataset of over 87,000 RGB images, the architecture comprises five convolutional blocks (filters 32–512) with max pooling and dropout (0.25, 0.4), followed by a 1,500-unit dense layer and SoftMax output. Optimized with Adam (lr=0.0001) and categorical cross-entropy, the model achieved 98% training and 96% validation accuracy with approximately 28.7 million parameters significantly fewer than transfer learning architectures. These results demonstrate an effective balance between predictive performance and computational efficiency, positioning the model as a promising tool for real-world agricultural deployment.
Millet crops play a foremost role in ensuring food security and sustainable agriculture; however, their productivity is significantly affected by various leaf diseases such as Rust, Smut and Blast. Early and accurate detection of these diseases is key to effective crop management. In this study, a hybrid Transfer Learning–Convolutional Neural Network (TL–CNN) framework is designed for automated millet disease detection. The model uses pre-trained architectures such as MobileNetV2, Xception and EfficientNetB0V2, for feature extraction, followed by additional convolutional blocks to capture discriminative features. The novelty of this work lies in the development of a millet-specific deep learning framework, integrated with CNN-based feature optimization and a reliable evaluation strategy. Unlike classic approaches, the proposed model uses both single-run training and stratified 5-fold cross-validation to ensure reliable and unbiased performance assessment. A comprehensive comparative study is conducted across multiple transfer learning models within an integrated framework. Experimental data show that the proposed EfficientNetB0V2 + CNN model achieves superior performance, with higher accuracy and better precision, recall and F1 Score across all classes. Confusion matrix analysis additionally confirms minimal misclassification and strong class separability. The data highlight the effectiveness of the suggested approach in detecting complex disease patterns. Overall, the proposed TL–CNN framework delivers a reliable and efficient solution for millet disease detection. This solution provides a strong prospect for real-world agricultural applications and intelligent crop-monitoring systems.
Nisha Rani· International journal of com...· 0 citations
Plant diseases can reduce crop quality and productivity, making early detection an important aspect of modern agriculture. Recent advances in deep learning, particularly Convolutional Neural Networks (CNN), have shown promising performance in image-based plant disease classification. This study proposes an explainable deep learning approach for multi-class plant disease classification using ResNet50 and EfficientNetB0 combined with Grad-CAM visualization. The experiments were conducted using the PlantVillage dataset consisting of 15 classes of healthy and diseased plant leaves.The research process included image preprocessing, data augmentation, transfer learning, model training, performance evaluation, and explainability analysis. The dataset was divided into training and validation sets with a ratio of 80:20. Model performance was evaluated using accuracy, loss, confusion matrix, precision, recall, and f1-score metrics. Experimental results showed that ResNet50 achieved the best performance with an accuracy of 92% and a validation loss of 0.19, outperforming EfficientNetB0 which obtained 76% accuracy and 0.82 validation loss. The classification report demonstrated that ResNet50 provided more stable and consistent predictions across most disease classes. Furthermore, Grad-CAM visualization successfully highlighted disease-relevant regions such as lesions, discoloration, and damaged leaf areas, improving the interpretability of the CNN model. The findings indicate that the combination of ResNet50 and Grad-CAM is effective for plant disease classification and provides better explainability for deep learning-based agricultural applications.
W. Zalmi, Rahmi Putri Kurnia, Dyah Listianing Tyas· Informatik : Jurnal Ilmu Kom...· 0 citations
Cotton leaf diseases significantly affect crop productivity, fiber quality, and agricultural sustainability, making early and accurate disease diagnosis essential for effective crop management. Manual disease identification is time-consuming, subjective, and dependent on expert knowledge, highlighting the need for automated and intelligent diagnostic systems. This study proposes a CNN-based deep learning framework for automated multiclass classification of cotton leaf diseases using digital image analysis. The proposed framework is trained on a curated dataset comprising healthy and diseased cotton leaf images representing multiple disease categories. CNN architecture performs hierarchical feature extraction, automatically learning discriminative spatial representations from input images without manual feature engineering. The network is trained for 100 epochs using optimized hyperparameters to achieve robust feature learning while ensuring high generalization capability. Model performance is quantitatively evaluated using standard classification metrics, including accuracy, precision, recall, F1-score, and confusion matrix analysis, providing a comprehensive assessment of classification effectiveness. Experimental results demonstrate that the proposed framework achieves reliable disease recognition with high classification accuracy and minimal inter-class confusion, validating the effectiveness of CNN-based feature learning for agricultural image analysis. The automated system enables rapid and accurate disease diagnosis, supporting timely intervention, optimized crop protection strategies, and improved decision-making in precision agriculture. Future work will focus on improving model robustness through the integration of larger and more diverse datasets, advanced data augmentation techniques, transfer learning, and hybrid deep learning architectures. Furthermore, deployment of the proposed framework on mobile, edge, and web-based platforms, together with IoT technologies, can facilitate real-time field monitoring and disease surveillance. Overall, the proposed CNN framework provides a scalable, computationally efficient, and intelligent solution for automated cotton leaf disease classification, contributing to the advancement of AI-driven precision agriculture and sustainable crop management.
Sonali Kamra, Vijay Laxmi· International Journal of Res...· 0 citations