Research on Automatic Diagnostic Technology of Soybean Leaf Diseases Based on Improved Transfer Learning

Soybean diseases and insect pests are important factors that affect the output and quality of the soybean,thus,it is necessary to do correct inspection and diagnosis on them.For this reason,based on improved transfer learning,a classification method of the soybean leaf diseases was proposed in this paper.In detail,this method first removed the complicated background in images and cut apart leaves from the entire image;second,the data-augmented method was applied to amplify the separated leaf disease image dataset to reduce overfitting;at last,the automatically fine-tuning convolutional neural network(AutoTun)was adopted to classify the soybean leaf diseases.The proposed method respectively reached 94.23%,93.51%and 94.91%of validation accuracy rates on VGG-16,ResNet-34 and DenseNet-121,and it was compared with the traditional fine-tuning method of transfer learning.The results indicated that the proposed method had superior to the traditional transfer learning method.

A LAMP-assay-based specific microbiota analysis reveals community dynamics and potential interactions of 13 major soybean root pathogens

Soybean root diseases are associated with numerous fungal and oomycete pathogens;however,the community dynamics and interactions of these pathogens are largely unknown.We performed 13 loop-mediated isothermal amplification(LAMP)assays that targeted specific soybean root pathogens,and traditional isolation assays.A total of 159 samples were collected from three locations in the Huang-Huai-Hai region of China at three soybean growth stages(30,60,and 90 days after planting)in 2016.In LAMP results,we found that pathogen communities differed slightly among locations,but changed dramatically between soybean growth stages.Phytophthora sojae,Rhizoctonia solani,and Fusarium oxysporum were most frequently detected at the early stage,whereas Phomopsis longicolla,Fusarium equiseti,and Fusarium virguliforme were most common in the later stages.Most samples(86%)contained two to six pathogen species.Interestingly,the less detectable species tended to exist in the samples containing more detected species,and some pathogens preferentially co-occurred in diseased tissue,including P.sojae–R.solani–F.oxysporum and F.virguliforme–Calonectria ilicicola,implying potential interactions during infection.The LAMP detection results were confirmed by traditional isolation methods.The isolated strains exhibited different virulence to soybean,further implying a beneficial interaction among some pathogens.

Grading method of soybean mosaic disease based on hyperspectral imaging technology

Soybean is a crop with a long cultivation history that occupies an important position in agricultural production.Soybean mosaic virus disease(SMV)has caused a rapid decline in soybean yields,causing huge losses to the soybean industry,wherefrom its early detec-tion is particularly important.This study proposes a new classification method for the early SMV,dividing its severity into grades 0,1 and 2.In the case of a small number of experi-mental samples of soybeans,this study proposes a combined convolutional neural network and support vector machine(CNN-SVM)method for the early detection of SMV.Experimen-tal results showed that the accuracy of the training set of the CNN-SVM model reached 96.67%,and the accuracy rate of the test set reached 94.17%.The experiment proved the feasibility of using the proposed CNN-SVM model to classify early SMV under the new clas-sification method,and provided a new direction for early SMV detection based on hyper-spectral images.