Non-Destructive Detection of Soybean Pest Based on Hyperspectral Image and Attention-ResNet Meta-Learning Model

Abstract

Soybean plays an important role in food, medicine, and industry. The quality inspection of soybean is essential for soybean yield and the agricultural economy. However, soybean pest is an important factor that seriously affects soybean yield, among which leguminivora glycinivorella matsumura is the most frequent pest. Aiming at the problem that the traditional detection methods have low accuracy and need a large number of samples to train the model, this paper proposed a detection method for leguminivora glycinivorella matsumura based on an A-ResNet (Attention-ResNet) meta-learning model. In this model, the ResNet network was combined with Attention to obtain the feature vectors that can better express the samples, so as to improve the performance of the model. As well, the classifier was designed as a multi-class support vector machine (SVM) to reduce over-fitting. Furthermore, in order to improve the training stability of the model and the prediction performance on the testing set, the traditional Batch Normalization was replaced by the Layer Normalization, and the Label Smooth method was used to punish the original loss. The experimental results showed that the accuracy of the A-ResNet meta-learning model reached 94.57 ± 0.19%, which can realize rapid and accurate nondestructive detection, and provides theoretical support for the intelligent detection of soybean pests.

An Advancing GCT-Inception-ResNet-V3 Model for Arboreal Pest Identification

“…In this research, we adopted the ResNet-18 model as the baseline for pest identification studies due to its prominence in previous research [15,16]. The hyperparameters for the ResNet-18 were meticulously adjusted to suit the IP102 dataset's requirements, implementing a grid search for the optimal set.…”

“…Automated systems using machine learning offer a promising solution, yet they require vast amounts of data and computational resources, often lacking in field conditions [14]. The ResNet architecture, with its deep residual learning framework [15,16], offers a potential improvement in learning complex features for accurate pest identification, yet like other advanced CNN (Convolutional Neural Network) architectures (e.g., VGG16 [17,18], DenseNet [19], and Inception-V3 [20][21][22]), it faces challenges in deployment on resource-constrained mobile devices, thus restricting their accessibility. Additionally, memory-efficient CNN architectures [23,24], although apt for mobile environments, typically sacrifice classification precision.…”

“…These models were compared against the traditional ResNet-18 model, which was selected as the control group. The selection of ResNet-18 as the baseline model is due to its widespread adoption in previous research on pest and disease identification [15][16][17], alongside SE-RegNet, SE-SE-RegNet, SE-RegNetY, and GCT-Inception-ResNet-V3. The GCT-Inception-ResNet-V3 model significantly outperforms the baseline model group.…”

Integrative Analyses of Transcriptomics and Metabolomics in Immune Response of Leguminivora glycinivorella Mats to Beauveria bassiana Infection

“…The degree of damage varies depending on the year, with a general insect feeding rate of 10% to 15%. In more severe years, the insect feeding rate can reach 50% to 70%, resulting in a 20% to 40% reduction in soybean production [6][7][8].…”

Identification and Classification of Coix seed Storage Years Based on Hyperspectral Imaging Technology Combined with Deep Learning

“…Kong et al developed a rapid detection method HSI combined with a CNN for the qualitative and quantitative identification of marine fishmeal adulteration [20]. However, as the depth of the network increases, CNNs may encounter the issue of gradient vanishing [21]. A modified CNN structure called ResNet, proposed by He et al [22], introduces a shortcut mechanism where residual modules are connected through shortcut connections.…”