• The Plant Pathology Journal
• /
• 제34권3호
• /
• pp.191-198
• /
• 2018

Fast and accurate diagnosis is needed to eradicate and manage economically important and invasive diseases like fire blight. Loop-mediated isothermal amplification (LAMP) is known as the best on-site diagnostic, because it is fast, highly specific to a target, and less sensitive to inhibitors in samples. In this study, LAMP assay that gives more consistent results for on-site diagnosis of fire blight than the previous developed LAMP assays was developed. Primers for new LAMP assay (named as DS-LAMP) were designed from a histidine-tRNA ligase gene (EAMY_RS32025) of E. amylovora CFBP1430 genome. The DS-LAMP amplified DNA (positive detection) only from genomic DNA of E. amylovora strains, not from either E. pyrifoliae (causing black shoot blight) or from Pseudomonas syringae pv. syringae (causing shoot blight on apple trees). The detection limit of DS-LAMP was 10 cells per LAMP reaction, equivalent to $10^4$ cells per ml of the sample extract. DS-LAMP successfully diagnosed the pathogens on four fire-blight infected apple and pear orchards. In addition, it could distinguish black shoot blight from fire blight. The $B{\ddot{u}}hlmann$-LAMP, developed previously for on-site diagnosis of fire blight, did not give consistent results for specificity to E. amylovora and on-site diagnosis; it gave positive reactions to three strains of E. pyrifoliae and two strains of P. syringae pv. syringae. It also, gave positive reactions to some healthy sample extracts. DS-LAMP, developed in this study, would give more accurate on-site diagnosis of fire blight, especially in the Republic of Korea, where fire blight and black shoot blight coexist.

• 한국시뮬레이션학회논문지
• /
• 제29권4호
• /
• pp.1-7
• /
• 2020

농작물 질병에 대한 조기 진단은 질병의 확산을 억제하고 농업 생산성을 증대하는 데에 있어 중요한 역할을 하고 있다. 최근 합성곱신경망(convolutional neural network, CNN)과 같은 딥러닝 기법을 활용하여 농작물 잎사귀 이미지 데이터세트를 분석하여 농작물 질병을 진단하는 다수의 연구가 진행되었다. 이와 같은 연구를 통해 농작물 질병을 90% 이상의 정확도로 분류할 수 있지만, 사전 학습된 농작물 질병 외에는 진단할 수 없다는 한계를 갖는다. 본 연구에서는 미학습 농작물에 대해 효율적으로 질병 여부를 진단하는 모델을 제안한다. 이를 위해, 먼저 VGG16을 활용한 농작물 질병 분류기(CDC)를 구축하고 PlantVillage 데이터세트을 통해 학습하였다. 이어 미학습 농작물의 질병 진단이 가능하도록 수정된 질병 분류기(mCDC)의 구축방안을 제안하였다. 실험을 통해 본 연구에서 제안한 수정된 질병 분류기(mCDC)가 미학습 농작물의 질병진단에 대해 기존 질병 분류기(CDC)보다 높은 성능을 보임을 확인하였다.

• The Plant Pathology Journal
• /
• 제38권3호
• /
• pp.194-202
• /
• 2022

Erwinia amylovora and Erwinia pyrifoliae cause fire blight and black-shoot blight, respectively, in apples and pears. E. pyrifoliae is less pathogenic and has a narrower host range than that of E. amylovora. Fire blight and black-shoot blight exhibit similar symptoms, making it difficult to distinguish one bacterial disease from the other. Molecular tools that differentiate fire blight from black-shoot blight could guide in the implementation of appropriate management strategies to control both diseases. In this study, a primer set was developed to detect and distinguish E. amylovora from E. pyrifoliae by conventional polymerase chain reaction (PCR). The primers produced amplicons of different sizes that were specific to each bacterial species. PCR products from E. amylovora and E. pyrifoliae cells at concentrations of 10⁴ cfu/ml and 10⁷ cfu/ml, respectively, were amplified, which demonstrated sufficient primer detection sensitivity. This primer set provides a simple molecular tool to distinguish between two types of bacterial diseases with similar symptoms.

• The Plant Pathology Journal
• /
• 제34권6호
• /
• pp.459-469
• /
• 2018

Plants and microorganisms (microbes) use information from chemicals such as volatile compounds to understand their environments. Proficiency in sensing and responding to these infochemicals increases an organism's ecological competence and ability to survive in competitive environments, particularly with regard to plant-pathogen interactions. Plants and microbes acquired the ability to sense and respond to biogenic volatiles during their evolutionary history. However, these signals can only be interpreted by humans through the use of state-of the-art technologies. Newly-developed tools allow microbe-induced plant volatiles to be detected in a rapid, precise, and non-invasive manner to diagnose plant diseases. Beside disease diagnosis, volatile compounds may also be valuable in improving crop productivity in sustainable agriculture. Bacterial volatile compounds (BVCs) have potential for use as a novel plant growth stimulant or as improver of fertilizer efficiency. BVCs can also elicit plant innate immunity against insect pests and microbial pathogens. Research is needed to expand our knowledge of BVCs and to produce BVC-based formulations that can be used practically in the field. Formulation possibilities include encapsulation and sol-gel matrices, which can be used in attract and kill formulations, chemigation, and seed priming. Exploitation of biogenic volatiles will facilitate the development of smart integrated plant management systems for disease control and productivity improvement.

• 한국동물위생학회지
• /
• 제44권1호
• /
• pp.15-19
• /
• 2021

Senecavirus A (SVA), previously known as Seneca Valley virus, can cause vesicular disease and neonatal losses in pigs that is clinically indistinguishable from foot-and-mouth disease virus (FMDV). After the first case report in Canada in 2007, it had been restrictively identified in North America including United States. But, since 2015, SVA emerged outside North America in Brazil, and also in several the Asian countries including China, Thailand, and Vietnam. Considering the SVA occurrence in neighboring countries, there has been a high risk that Korea can be introduced at any time. In particular, it is very important in terms of differential diagnosis in the suspected case of vesicular diseases in countries where FMD is occurring. So far, several different molecular detection methods for SVV have been published but not validated as the reference method, yet. In this study, seven different molecular methods for detecting SVA were evaluated. Among them, the method by Flowler et al, (2017) targeted to 3D gene region with the highest sensitivity and no cross reaction with other vesicular disease agents including FMDV, VSV and SVD, was selected and applied further to antigen surveillance of SVA. A total of 245 samples of 157 pigs from 61 farms submitted for animal disease diagnose nationwide during 2018 were tested all negative. In 2018, no sign of SVA occurrence have been confirmed in Korea, but the results of the surveillance for SVA needs to be continued and accumulated at a high risk of SVA in neighboring countries.

• 식물병연구
• /
• 제13권3호
• /
• pp.145-151
• /
• 2007

Xanthomonas axonopodis pv. glycines에 의해 발병되는 콩 불마름병은 한국에서 콩에 가장 많이 발생하는 중요한 세균성 병해 중 하나이다. 본 연구에서는 Xanthomonas axonopodis pv. glycines를 종자에서 검출하기 위해 PCR기법을 이용하였으며, 한국의 36개 주요 콩 품종의 종자 오염을 조사하였다. 그리고 병원균 검출과 동정을 위한 PCR assay와 dilution plating assay를 비교하였다. PCR assay를 이용하여 인공접종에 의한 이병종자와 자연감염된 이병종자로부터 병원균 검출을 확인하였다. PCR assay를 통한 이런 결과는 dilution plating assay와 비슷한 결과를 보여 주었으며 종자에서 병원균을 검출하는 다른 전통적인 방법보다 더 효과적인 방법으로 증명되었다. 36개 주요 콩 품종의 X. axonopodis pv. glycines에 의한 종자 전염을 확인한 결과 풍산나물콩, 만리콩, 태광콩, 대망콩, 아주까리콩에서 병원균이 검출되었다. 그러므로 PCR assay는 콩 종자에서 신속하고, 민감하게 X. axonopodis pv. glycines 특이적으로 검출할 수 있는 효과적인 방법으로 활용될 수 있을 것이다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권8호
• /
• pp.3312-3327
• /
• 2020

Plant diseases are a significant yield and quality constraint for farmers around the world due to their severe impact on agricultural productivity. Such losses can have a substantial impact on the economy which causes a reduction in farmer's income and higher prices for consumers. Further, it may also result in a severe shortage of food ensuing violent hunger and starvation, especially, in less-developed countries where access to disease prevention methods is limited. This research presents an investigation of Directional Local Quinary Patterns (DLQP) as a feature descriptor for plants leaf disease detection and Support Vector Machine (SVM) as a classifier. The DLQP as a feature descriptor is specifically the first time being used for disease detection in horticulture. DLQP provides directional edge information attending the reference pixel with its neighboring pixel value by involving computation of their grey-level difference based on quinary value (-2, -1, 0, 1, 2) in 0°, 45°, 90°, and 135° directions of selected window of plant leaf image. To assess the robustness of DLQP as a texture descriptor we used a research-oriented Plant Village dataset of Tomato plant (3,900 leaf images) comprising of 6 diseased classes, Potato plant (1,526 leaf images) and Apple plant (2,600 leaf images) comprising of 3 diseased classes. The accuracies of 95.6%, 96.2% and 97.8% for the above-mentioned crops, respectively, were achieved which are higher in comparison with classification on the same dataset using other standard feature descriptors like Local Binary Pattern (LBP) and Local Ternary Patterns (LTP). Further, the effectiveness of the proposed method is proven by comparing it with existing algorithms for plant disease phenotyping.

• 스마트미디어저널
• /
• 제12권7호
• /
• pp.9-17
• /
• 2023

작물의 병충해는 다양한 작물의 성장에 영향을 미치기 때문에 초기에 병충해를 식별하는 것이 매우 중요하다. 이미 많은 머신러닝(ML) 모델이 작물 병충해의 검사와 분류에 사용되었지만, 머신러닝의 부분 집합인 딥러닝(DL)이 발전을 이루면서 이 연구 분야에서 많은 진보가 있었다. 본 연구에서는 YOLOX 검출기와 MobileNet 분류기를 사용하여 비정상 작물의 병충해 검사 및 정상 작물에 대해서는 성숙도 분류를 진행하였다. 이 방법을 통해 다양한 작물 병충해 특징을 효과적으로 추출할 수 있으며, 실험을 위해 딸기, 고추, 토마토와 관련된 다양한 해상도의 이미지 데이터 셋을 준비하여 작물 병충해 분류에 사용하였다. 실험 결과에 따르면 복잡한 배경 조건을 가진 영상에서 평균 테스트 정확도가 84%, 성숙도 분류 정확도가 83.91% 임을 확인할 수 있었다. 이 모델은 자연 상태에서 3가지 작물에 대한 6가지 질병 검출 및 각 작물의 성숙도 분류를 효과적으로 진행할 수 있었다.

• 산업경영시스템학회지
• /
• 제44권3호
• /
• pp.33-38
• /
• 2021

Recently, transfer learning techniques with a base convolutional neural network (CNN) model have widely gained acceptance in early detection and classification of crop diseases to increase agricultural productivity with reducing disease spread. The transfer learning techniques based classifiers generally achieve over 90% of classification accuracy for crop diseases using dataset of crop leaf images (e.g., PlantVillage dataset), but they have ability to classify only the pre-trained diseases. This paper provides with an evaluation scheme on selecting an effective base CNN model for crop disease transfer learning with regard to the accuracy of trained target crops as well as of untrained target crops. First, we present transfer learning models called CDC (crop disease classification) architecture including widely used base (pre-trained) CNN models. We evaluate each performance of seven base CNN models for four untrained crops. The results of performance evaluation show that the DenseNet201 is one of the best base CNN models.

• The Plant Pathology Journal
• /
• 제33권3호
• /
• pp.307-317
• /
• 2017

Satsuma dwarf virus (SDV) or Citrus mosaic sadwavirus (CiMV) were not consistently detected in RTPCR assay with the primer sets based on gene of Japan isolates. SDV and CiMV isolates were distinctively divided into two groups based on phylogenetic analysis of PP2 gene cloned from 22 Korean isolates, and the Korean CiMV and SDV isolates shared 95.5-96.2% and 97.1-97.7% sequence identity with Japanese isolate, respectively. We developed PP2-1 primer set based on the PP2 gene sequence of Korean isolates to simultaneously and effectively detect SDV and CiMV. And CTLV-2013 and CTV-po primer sets were newly designed for detection of Citrus tatter leaf virus (CTLV) and Citrus tristeza virus (CTV), respectively. Using these primer sets, a new multiplex PCR assay was developed as a means to simultaneously detect 4 citrus viruses, CTV, CTLV, SDV, and CiMV. The degree of detection by the multiplex PCR were consistent with those of uniplex RT-PCR for detection of each of the viruses. Therefore, the new multiplex PCR provides an efficient method for detecting 4 citrus viruses, which will help diagnose many citrus plants at the same time. We verified that 35.2% and 72.1% of 775 trees in 155 orchards were infected with SDV or CiMV (SDV/CiMV) and CTV by the multiplex-PCR assay, respectively, and CTLV was not detected in any of the trees tested.