Using transfer learning-based plant disease classification and detection for sustainable agriculture

Subsistence farmers and global food security depend on sufficient food production, which aligns with the UN's "Zero Hunger," "Climate Action," and "Responsible Consumption and Production" sustainable development goals. In addition to already available methods for early disease detection and classification facing overfitting and fine feature extraction complexities during the training process, how early signs of green attacks can be identified or classified remains uncertain. Most pests and disease symptoms are seen in plant leaves and fruits, yet their diagnosis by experts in the laboratory is expensive, tedious, labor-intensive, and time-consuming. Notably, how plant pests and diseases can be appropriately detected and timely prevented is a hotspot paradigm in smart, sustainable agriculture remains unknown. In recent years, deep transfer learning has demonstrated tremendous advances in the recognition accuracy of object detection and image classification systems since these frameworks utilize previously acquired knowledge to solve similar problems more effectively and quickly. Therefore, in this research, we introduce two plant disease detection (PDDNet) models of early fusion (AE) and the lead voting ensemble (LVE) integrated with nine pre-trained convolutional neural networks (CNNs) and fine-tuned by deep feature extraction for efficient plant disease identification and classification. The experiments were carried out on 15 classes of the popular PlantVillage dataset, which has 54,305 image samples of different plant disease species in 38 categories. Hyperparameter fine-tuning was done with popular pre-trained models, including DenseNet201, ResNet101, ResNet50, GoogleNet, AlexNet, ResNet18, EfficientNetB7, NASNetMobile, and ConvNeXtSmall. We test these CNNs on the stated plant disease detection and classification problem, both independently and as part of an ensemble. In the final phase, a logistic regression (LR) classifier is utilized to determine the performance of various CNN model combinations. A comparative analysis was also performed on classifiers, deep learning, the proposed model, and similar state-of-the-art studies. The experiments demonstrated that PDDNet-AE and PDDNet-LVE achieved 96.74% and 97.79%, respectively, compared to current CNNs when tested on several plant diseases, depicting its exceptional robustness and generalization capabilities and mitigating current concerns in plant disease detection and classification.

Using a Novel Convolutional Neural Network for Plant Pests Detection and Disease Classification

BACKGROUND

Early plant diseases and pests identification reduces social, economic, and environmental deficiencies entailing toxic chemical utilization on agricultural farms, thus posing a threat to global food security.

METHODOLOGY

An enhanced convolutional neural network (CNN) along with long short-term memory (LSTM) using a majority voting (MVE) ensemble classifier has been proposed to tackle plant pest and disease identification and classification. Within pre-trained models, deep feature extractions have been obtained from connected layers. Deep features have been extracted and are sent to the LSTM layer to build a robust, enhanced LSTM-CNN model for detecting plant pests and diseases. Experiments were carried out using Turkey Dataset, with 4,447 apple pests and diseases categorized into 15 different classes.

RESULTS

The study has been evaluated in different CNNs using logistic regression (LR), LSTM, and extreme learning machine (ELM), focusing on plant disease detection problems. The ensemble majority voting (EMV) classifier was used at the LSTM layer to detect and classify plant disease labels. Furthermore, an autonomous selection of the optimal LSTM layer network parameters was applied. Finally, the performance was validated based on sensitivity, F1-score, accuracy, and specificity using LSTM, ELM, and LR classifiers.

CONCLUSION

The presented model attained 99.2% accuracy in comparison to the cutting-edge models on different classifiers like LSTM, LR, and ELM, and performed better in comparison to transfer learning (TL). Pre-trained models, like VGG-19, VGG-18, and AlexNet, demonstrated better accuracy when the fc6 layer was compared to other layers. This article is protected by copyright. All rights reserved.