• 대한임베디드공학회논문지
• /
• 제18권6호
• /
• pp.285-292
• /
• 2023

With the wide spread of smart farms and the advancements in IoT technology, it is easy to obtain additional data in addition to crop images. Consequently, deep learning-based crop disease diagnosis research utilizing multimodal data has become important. This study proposes a crop disease diagnosis method using multimodal supervised contrastive learning by expanding upon the multimodal self-supervised learning. RandAugment method was used to augment crop image and time series of environment data. These augmented data passed through encoder and projection head for each modality, yielding low-dimensional features. Subsequently, the proposed multimodal supervised contrastive loss helped features from the same class get closer while pushing apart those from different classes. Following this, the pretrained model was fine-tuned for crop disease diagnosis. The visualization of t-SNE result and comparative assessments of crop disease diagnosis performance substantiate that the proposed method has superior performance than multimodal self-supervised learning.

• Journal of Forest and Environmental Science
• /
• 제40권1호
• /
• pp.1-8
• /
• 2024

Recently, intensive research has been conducted to develop innovative methods for diagnosing plant diseases based on hyperspectral technologies. Hyperspectral analysis is a new subject that combines optical spectroscopy and image analysis methods, which makes it possible to simultaneously evaluate both physiological and morphological parameters. Among the physiological and morphological parameters are classifying healthy and diseased plants, assessing the severity of the disease, differentiating the types of pathogens, and identifying the symptoms of biotic stresses at early stages, including during the incubation period, when the symptoms are not visible to the human eye. Plant diseases cause significant economic losses in agriculture around the world as the symptoms of diseases usually appear when the plants are infected severely. Early detection, quantification, and identification of plant diseases are crucial for the targeted application of plant protection measures in crop production. Hence, this can be done by possible applications of hyperspectral sensors and platforms on different scales for disease diagnosis. Further, the main areas of application of hyperspectral sensors in the diagnosis of plant diseases are considered, such as detection, differentiation, and identification of diseases, estimation of disease severity, and phenotyping of disease resistance of genotypes. This review provides a deeper understanding, of basic principles and implementation of hyperspectral sensors that can measure pathogen-induced changes in plant physiology. Hence, it brings together critically assessed reports and evaluations of researchers who have adopted the use of this application. This review concluded with an overview that hyperspectral sensors, as a non-invasive system of measurement can be adopted in early detection, identification, and possible solutions to farmers as it would empower prior intervention to help moderate against decrease in yield and/or total crop loss.

• 식물병연구
• /
• 제30권1호
• /
• pp.99-102
• /
• 2024

Integrated pest management is essential for controlling plant diseases that reduce crop yields. Rapid diagnosis is crucial for effective management in the event of an outbreak to identify the cause and minimize damage. Diagnosis methods range from indirect visual observation, which can be subjective and inaccurate, to machine learning and deep learning predictions that may suffer from biased data. Direct molecular-based methods, while accurate, are complex and time-consuming. However, the development of large multimodal models, like GPT-4, combines image recognition with natural language processing for more accurate diagnostic information. This study introduces GPT-4-based system for diagnosing plant diseases utilizing a detailed knowledge base with 1,420 host plants, 2,462 pathogens, and 37,467 pesticide instances from the official plant disease and pesticide registries of Korea. The AI plant doctor offers interactive advice on diagnosis, control methods, and pesticide use for diseases in Korea and is accessible at https://pdoc.scnu.ac.kr/.

• The Plant Pathology Journal
• /
• 제34권4호
• /
• pp.327-334
• /
• 2018

Northern corn leaf spot and southern corn leaf blight caused by Cochliobolus carbonum (anamorph, Bipolaris zeicola) and Cochliobolus heterostrophus (anamorph, Bipolaris maydis), respectively, are common maize diseases in Korea. Accurate detection of plant pathogens is necessary for effective disease management. Based on the polyketide synthase gene (PKS) of Cochliobolus carbonum and the nonribosomal peptide synthetase gene (NRPS) of Cochliobolus heterostrophus, primer pairs were designed for PCR to simultaneously detect the two fungal pathogens and were specific and sensitive enough to be used for duplex PCR analysis. This duplex PCR-based method was found to be effective for diagnosing simultaneous infections from the two Cochliobolus species that display similar morphological and mycological characteristics. With this method, it is possible to prevent infections in maize by detecting infected seeds or maize and discarding them. Besides saving time and effort, early diagnosis can help to prevent infections, establish comprehensive management systems, and secure healthy seeds.

• 한국작물학회지
• /
• 제58권2호
• /
• pp.142-148
• /
• 2013

국내 콩에서 발생하는 세균병해인 불마름병, 들불병, 세균점무늬병, 세균갈색점무늬병의 다중 진단을 위한 PCR 방법을 요약하면 다음과 같다. 1. 콩에 발생하는 각각의 세균들은 서로 다른 박테리오신(bacteriocin) 이나 파이토톡신(phytotoxin)을 생산하는데 이와 관련한 유전자를 목적으로 하여 진단프라이머를 설계하였다. 2. 불마름병은 glycinecin A, 들불병은 tabtoxin, 세균점무늬병은 coronatine과 세균갈색점무늬병은 syringopeptin을 목적유전자로 하여 다중 진단프라이머 조합을 설계하였다. 3. 1차 선발로 각각의 균주에 대한 단일 진단 프라이머를 선발하였으며, 여기선 선발된 21개의 프라이머들을 조합하여 4종 다중진단프라이머 선발을 위한 2차 선발에 이용하였다. 최종적으로 280 bp의 불마름병, 355 bp의 세균갈색점무늬병, 563 bp의 들불병과 815 bp의 세균점무늬병으로 구성된 다중진단 프라이머 조합이 개발되었다. 4. 선발된 4종 다중 진단 프라이머 조합의 경우 다른 세균들과의 비특이적 반응이 있는지 확인하기 위한 3차 선발을 거쳐 그 특이성을 검증하였다.

• 한국식물병리학회지
• /
• 제10권2호
• /
• pp.99-104
• /
• 1994

A computer-based diagnosing system for diseases of grasses, ornamental plant and fruit trees was developed using a 16 bit personal computer (Model Acer 900) and BASIC was used as a programing language. the developed advisory system was named as Korean Plant Disease Advisory System (KOPDAS). The diagraming system files were composed of a system operation file and several database files. The knowledge-base files are composed of text files, code files and implement program files. The knowledge-base of text files are composed of 79 files of grasses diseases, 122 files of ornamental plant diseases and 67 files of fruit tree diseases. The information of each text file include disease names, causal agents, diseased parts, symptoms, morphological characteristics of causal organisms and control methods for the diagnosing of crop diseases.

• 식물병연구
• /
• 제21권4호
• /
• pp.321-325
• /
• 2015

다공성 세라믹 큐브를 이용한 RT-PCR 진단법은 별도의 핵산 추출 과정이나 용액 처리 없이, 식물체에 접촉시켜 큐브의 공극에 바이러스 입자나 핵산 등의 분자가 신속하게 흡수되면 이를 바로 RT-PCR 반응에 넣어 유전자를 증폭시키는 방법으로, 식물체로부터 빠르고 정확하게 바이러스를 진단하는 방법이다. 본 연구에서는 다공성 세라믹 큐브를 이용하여 벼에 발생하는 주요 바이러스인 벼줄무늬잎마름바이러스(RSV)를 진단하는 RT-PCR 진단법을 확립하였다. 벼의 잎, 잎집, 또는 줄기를 대상으로 큐브 1개 또는 3개를 사용하여 즙액을 흡수시킨 후, 이를 RT-PCR 주형으로 사용하였고, 그 결과 변성처리에 큰 차이 없이 증폭 효율이 나타났다. 또한 즙액을 흡수한 큐브는 9주차까지 상온에서 보관한 후 RT-PCR을 실시하여도 안정적으로 증폭 효율을 나타내었다.

• 한국빅데이터학회지
• /
• 제1권1호
• /
• pp.19-22
• /
• 2016

최근 IT 기술을 활용하여 농작물의 병충해 조기 진단에 관한 연구가 활발히 진행되고 있다. 본 논문은 카메라 센서를 통해 받아온 작물의 잎사귀 이미지를 분석하여 병충해를 조기에 감지할 수 있는 이미지 프로세싱 기법에 대해 논한다. 본 논문은 개선된 K 평균 클러스터링 방법을 활용하여 잎사귀 질병 감염 여부를 진단하는 알고리즘을 제안한다. 잎사귀 감염 분류 실험을 통해, 제안한 알고리즘이 정성적인 평가에서 더 좋은 성능을 나타낸 것으로 분석되었다.

• 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.

• 식물병연구
• /
• 제26권4호
• /
• pp.222-228
• /
• 2020

과수 화상병을 일으키는 Erwinia amylovora는 국내에서 금지병원균으로 지정되어 화상병 발생 시, 중앙 정부의 진단을 근거로 기주를 매몰하는 공적 방제가 실시되고 있다. 국내 과수 화상병은 2015년 안성, 천안 및 제천의 43농가에서 발생하여 42.9 ha를 매몰한 것을 시작으로, 2019년 발생 지역이 11개 시군으로 확산되었으며, 총 348농가 260.4 ha가 매몰되었다. 배나무 화상병은 주로 경기남부와 충남에서 발생되었고, 발생 건수가 연평균 29±9.2건으로 매년 비교적 고르게 발생되었으며 20-30년생 과수에서 발병 비율이 가장 높았다. 반면, 사과나무 화상병은 주로 경기북부, 강원, 충북에서 발생되었고, 발생 건수가 연평균 41±57.6건으로 2018-2019년 발생건수가 크게 증가하였으며, 20년 이하의 과수의 발병 비율이 높았다. 국내 과수 화상병은 어린 사과나무에서 병의 확산이 빠르므로, 특히 미성숙 과수가 식재된 과원에서는 화상병이 발병하지 않도록 약제를 적기에 살포하는 등 예방을 철저히 하고, 발병 시 신속히 방제해야 한다.