A Multi-Source Data Fusion Decision-Making Method for Disease and Pest Detection of Grape Foliage Based on ShuffleNet V2

Abstract

Disease and pest detection of grape foliage is essential for grape yield and quality. RGB image (RGBI), multispectral image (MSI), and thermal infrared image (TIRI) are widely used in the health detection of plants. In this study, we collected three types of grape foliage images with six common classes (anthracnose, downy mildew, leafhopper, mites, viral disease, and healthy) in the field. ShuffleNet V2 was used to build up detection models. According to the accuracy of RGBI, MSI, TIRI, and multi-source data concatenation (MDC) models, and a multi-source data fusion (MDF) decision-making method was proposed for improving the detection performance for grape foliage, aiming to enhance the decision-making for RGBI of grape foliage by fusing the MSI and TIRI. The results showed that 40% of the incorrect detection outputs were rectified using the MDF decision-making method. The overall accuracy of MDF model was 96.05%, which had improvements of 2.64%, 13.65%, and 27.79%, compared with the RGBI, MSI, and TIRI models using label smoothing, respectively. In addition, the MDF model was based on the lightweight network with 3.785 M total parameters and 0.362 G multiply-accumulate operations, which could be highly portable and easy to be applied.

Urban Landscaping Landscape Design and Maintenance Management Method Based on Multisource Big Data Fusion

“…And using the support vector machine method, combined with the Alzheimer's disease dataset, the classification problem of the fused dataset is considered. Due to the particularity of some diseases, the number of patients is relatively small, and the amount of related data is also small [ 11 ]. Dana Lahat et al proposed a multimodal data fusion method to fuse datasets obtained by different means [ 12 ].…”

Harnessing transfer learning for Alzheimer's disease prediction

“…ShuffleNet is also used in migration learning image recognition and classification due to its lightweight network and high portability. Yang et al [16] used ShuffleNet V2 for disease and pest detection of grape foliage. They provide a new multisource data fusion decision-making method and apply it in improving the detection performance of grape leaves.…”

A Lightweight Crop Pest Detection Method Based on Convolutional Neural Networks

“…This is mainly due to the deeper structure of the MLP, which can learn more complex mapping relationships. Pest detection methods based on machine learning techniques rely on the artificial selection and extraction of visual features, which limits the generalization ability of feature representation, resulting in such methods being susceptible to interference from background changes, morphological changes, and other factors, as well as the instability of detection precision [7].…”