Ensemble Learning of Lightweight Deep Convolutional Neural Networks for Crop Disease Image Detection

Abstract

The application of convolutional neural networks (CNNs) to plant disease recognition is widely considered to enhance the effectiveness of such networks significantly. However, these models are nonlinear and have a high bias. To address the high bias of the single CNN model, the authors proposed an ensemble method of three lightweight CNNs models (MobileNetv2, NasNetMobile and a simple CNN model from scratch) based on a stacking generalization approach. This method has two-stage training, first, we fine-tuned and trained the base models (level-0) to make predictions, then we passed these predictions to XGBoost (level-1 or meta-learner) for training and making the final prediction. Furthermore, a search grid algorithm was used for the hyperparameter tuning of the XGBoost. The proposed method is compared to the majority voting approach and all base learner models (MobileNetv2, NasNetMobile and simple CNN model from scratch). The proposed ensemble method significantly improved the performance of plant disease classification. Experiments show that the ensemble approach achieves higher prediction accuracy (98% for majority voting and 99% for staking method) than a single CNN learner. Furthermore, the proposed ensemble method has a lightweight size (e.g., 10[Formula: see text] smaller than VGG16), allowing farmers to deploy it on devices with limited resources such as cell phones, internet of things (IoT) devices, unmanned aerial vehicles (UAVs) and so on.

Deep transfer learning with gravitational search algorithm for enhanced plant disease classification

“…Our method, based on the MLR model, exhibits a superior exemplary level of efficacy with an average accuracy of 99.8%. This outperforms the results from the study [ 15 ] with an average of 83.4% and the study [ 6 ] with averages of 98.02% and 96.621% for Meta learner (XGBoost) and Majority voting, respectively. Our method also shows better performance compared to the EfficientNetB5 (99.91%) and EfficientNetB4 (99.96%) models of the study [ 42 ].…”

“…Table 3 presents a comparison of our method's disease detection results with those from other studies, specifically from Refs. [ 6 , 15 ], and [ 42 ]. The diseases analyzed include Peach Bacterial spot, Peach healthy, Strawberry healthy, Strawberry Leaf scorch, Tomato Bacterial spot, Tomato Early blight, Tomato healthy, Tomato Late blight, Tomato Leaf Mold, and Tomato Septoria leaf spot.…”

“…With this modern technology, agriculturalists have the potential to automate the process of identifying plant ailments, therefore saving time and cost, especially in regions where the visual examination is challenging to perform, such as extensive farmland [ 4 ]. Computer Vision (CV) technology is one of the most advanced technologies that have been utilized for plant disease recognition in the last decade [ 5 , 6 ]. K-nearest neighbors algorithm (k-NN), artificial neural networks, random forests, and Support Vector Machines (SVM) are some of the computer vision-based technologies used for the automated detection and classification of crop diseases [ 7 ].…”