• 한국멀티미디어학회논문지
• /
• 제23권10호
• /
• pp.1250-1257
• /
• 2020

The early detection of diseases is important in agriculture because diseases are major threats of reducing crop yield for farmers. The shape and color of plant leaf are changed differently according to the disease. So we can detect and estimate the disease by inspecting the visual feature in leaf. This study presents a vision-based leaf classification method for detecting the diseases of tomato crop. ResNet-50 model was used to extract the visual feature in leaf and classify the disease of tomato crop, since the model showed the higher accuracy than the other ResNet models with different depths. We propose a new ensemble approach using several DCNN classifiers that have the same structure but have been trained at different ranges in the DCNN layers. Experimental result achieved accuracy of 97.19% for PlantVillage dataset. It validates that the proposed method effectively classify the disease of tomato crop.

• 한국소성가공학회:학술대회논문집
• /
• 한국소성가공학회 1999년도 제3회 압연심포지엄 논문집 압연기술의 미래개척 (Exploitation of Future Rolling Technologies)
• /
• pp.438-446
• /
• 1999

Crop minimization of the top and bottom ends of hot rolled plate, in a plate, in a plate mill, has been investigated. The existing model to determine the edging pattern at the finishing rolling pass was not reasonable to get high width accuracy and rolling yields. New models including width prediction have been formulated by using neural network model of back propagation learning algorithm and statistical analysis based on the actual production rolling data to give the optimal pattern for minimizing trimming loss. Using these models, at a given rolling condition of broadside pass and finishing pass and the permissible condition of width variation, it was possible to minimize crip at the top and bottom ends according to optimum procedure in plate mill. An application to improve the plan view pattern reduced width variation by 23% and crop length by 30% on average with an effective fishtail crop shape.

• 한국작물학회지
• /
• 제60권1호
• /
• pp.29-32
• /
• 2015

Two-dimensional electrophoresis (2-DE) was executed to separate the seed storage proteins from the buckwheat. The proteins extracted from the whole seed proteins were better separated and observed in the use of lysis buffer. Using this method, the highly reproducible isoelectric focusing (IEF) can be obtained from polyacrylamide gels, and IEF from the polyacrylamide gel at all the possible pH range (5.0-8.0) was more easily separated than IPG (immobilized pH gradient) gels. The polyacrylamide gels in the first dimension in 2-DE was used to separate and identify a number of whole seed proteins in the proteome analysis. In this new apparatus using 2-DE, 27cm in length of plate coated with polyacrylamide gel was used and the experiment was further investigated under the various conditions.

• 한국작물학회:학술대회논문집
• /
• 한국작물학회 2004년도 춘계 학술대회지
• /
• pp.102-103
• /
• 2004

[ $\bigcirc$ ] In the growth simulation without changing of module with ORYZA2000, dry matter, LAI and leaf nitrogen content(FNLV) were estimated well under high nitrogen applicated condition, but overestimated under low nitrogen applicated condition. $\bigcirc$ Nitrogen stress factor on the SLA was introduced into ORYZA2000 because especially overestimated LAI under low nitrogen applicated condition was originated from SLA decrease with leaf nitrogen(FNLV) decrease. $\bigcirc$ In the growth simulation with modified SLA modified module, LAI was estimated well under even low nitrogen applicated condition, but dry matter was hardly changed compared with default. $\bigcirc$ Simulated plant nitrogen content and dry matter have no clear difference between modules, but compared with observed values, panicle weight(WSO) and rough rice yield(WRR14) were overestimated under high nitrogen applicated because of lodging, pest, disease and low nitrogen use efficiency.

• 한국농업기계학회:학술대회논문집
• /
• 한국농업기계학회 1993년도 Proceedings of International Conference for Agricultural Machinery and Process Engineering
• /
• pp.353-362
• /
• 1993

The purpose of this study is to develop a crop-row detector which can be applied to an automatic row following control for cultivators or thinning machines. In this report, a possibility of new crop-row detecting method was discussed. This detecting method consists of two principal means. One is the hardware means to convert the two dimensional crop-row vision to the compacted one dimensional information. The conversion is achieved by a color line sensor and a rotating mirror. In order to extract crop-row , R and G signals of RGB color system are used. The locations of two different points on the target row are detected by this means. Another is the software means to estimate the offset value and the heading angle between the detector and the target row which can be assumed as a straight line. As a result of discussion, it was concluded that this detecting method would be accurate enough for practical use.

• 원예과학기술지
• /
• 제35권4호
• /
• pp.499-509
• /
• 2017

Recently, there has been increased attention to the development of new plant cultivars with enhanced resistance to biotic and abiotic stress. To develop ginseng cultivars with such traits, systematic breeding programs and comprehensive field studies are prerequisites. In this study, we applied a pure-line selection method to identify a ginseng cultivar with enhanced stress resistance. Phenotypic and agronomic characteristics, seed yield, and physiological responses to biotic and abiotic stresses were investigated according to the guidelines of the International Union for the Protection of New Varieties of Plants (UPOV). In the newly developed 'Kowon' cultivar, the time of emergence, flowering, and berry maturity were intermediate between those of the controls, 'Yunpoong' and 'Chunpoong'. The stem length of 'Kowon' was intermediate, whereas the root length was shorter and the main root diameter was greater than those of 'Chunpoong'. In local adaptability tests conducted in three regions, the yield of 'Kowon' was $666kg{\cdot}10a^{-1}$; 27% and 4% higher than that of 'Chunpoong' and 'Yunpoong'. Diseases such as Alternaria blight, Phytophthora blight, mulberry mealybug, and nematode infestation did not occur in 'Kowon'; and it also exhibited moderate resistance to damping-off and anthracnose. In these cases, yellow spots occurred on aerial parts and the rusty skin of the root, and it exhibited moderate resistance at high temperatures. Our study demonstrates that 'Kowon', which has a high root weight and enhanced biotic/abiotic stress resistance, is a superior cultivar that could increase farmers' income.

• 한국작물학회:학술대회논문집
• /
• 한국작물학회 2017년도 9th Asian Crop Science Association conference
• /
• pp.14-14
• /
• 2017

The discipline of plant breeding is experiencing a renaissance impacting crop improvement as a result of new technologies, however fundamental questions remain for predicting the phenotype and how the environment and genetics shape it. Inexpensive DNA sequencing, genotyping, new statistical methods, high throughput phenotyping and gene-editing are revolutionizing breeding methods and strategies for improving both quantitative and qualitative traits. Genomic selection (GS) models use genome-wide markers to predict performance for both phenotyped and non-phenotyped individuals. Aerial and ground imaging systems generate data on correlated traits such as canopy temperature and normalized difference vegetative index that can be combined with genotypes in multivariate models to further increase prediction accuracy and reduce the cost of advanced trials with limited replication in time and space. Design of a GS training population is crucial to the accuracy of prediction models and can be affected by many factors including population structure and composition. Prediction models can incorporate performance over multiple environments and assess GxE effects to identify a highly predictive subset of environments. We have developed a methodology for analyzing unbalanced datasets using genome-wide marker effects to group environments and identify outlier environments. Environmental covariates can be identified using a crop model and used in a GS model to predict GxE in unobserved environments and to predict performance in climate change scenarios. These new tools and knowledge challenge the plant breeder to ask the right questions and choose the tools that are appropriate for their crop and target traits. Contemporary plant breeding requires teams of people with expertise in genetics, phenotyping and statistics to improve efficiency and increase prediction accuracy in terms of genotypes, experimental design and environment sampling.

• 한국자원식물학회지
• /
• 제31권6호
• /
• pp.714-718
• /
• 2018

A new Gomchwi cultivar 'Sammany' was developed by a cross between Gomchwi (Ligularia fischeri (Ledeb.) Turcz.) and Handaeri-gomchwi (Ligularia fischeri var. spiciformis Nakai). Gomchwi is a common Korean name referring wild edible plant species within Ligularia genus. 'Sammany' has purple colored petiole ears and petiole trichome is absent. It has 2nd degree leaf vein density. Plant height, leaf length, leaf width and petiole length were 46.2, 19.1, 19.5 and 32.1 cm, respectively. Plant height was higher than 'Gondalbi'. Bolting occurred in mid. July and it flowered from late August to early September. 'Gondalbi' bolted and flowered 26 days earlier than 'Sammany', and consequently has earlier flowering time more than 26 day. Leaf number of 'Sammany' was 156 per plant but 'Gondalbi' had 130. 'Sammany' had thicker leaves (0.61 mm) compared to 'Gondalbi' (0.46 mm). As a result, yield was higher in 'Sammany (1,077 g/plant)' than 'Gondalbi (798 g/plant)' and leaf hardness was lower in 'Sammany ($20.8kg/cm^2$)' compared to 'Gondalbi ($23.0kg/cm^2$)'. In addition, 'Sammany' was found to be moderately resistant to powdery mildew. With enhanced agronomic and pathology traits, 'Sammany' was newly registered as a new Gomchwi cultivar (variety protection no. 131 on May 2017).

• 한국작물학회:학술대회논문집
• /
• 한국작물학회 2022년도 추계학술대회
• /
• pp.186-186
• /
• 2022

Phytophthora root and stem rot (PRSR) and wildfire disease (WFD) of soybean are frequently observed in the field of South Korea. The most environmentally friendly way to control PRSR and WFD is to use soybean varieties with resistance to Phytophthora sojae (P. sojae) and Pseudomonas amygdali pv. tabaci. Plant germplasm is an important gene pool for soybean breeding and improvement. In this study, hundreds of soybean accessions were evaluated for the two pathogens, and genome-wide association analyses were conducted using 104,955 SNPs to identify resistance loci for the two pathogens. Of 193 accessions, 46 genotypes showed resistance reaction, while 143 did susceptibility for PRSP. Twenty SNPs were significantly associated with resistance to P. sojae on chromosomes (Chr.) 3 and 4. Significant SNPs on Chr.3 were located within the known Rps gene region. A region on Chr. 4 is considered as a new candidate resistance loci. For evalation of resistance to WFD, 18, 31,74,36 and 34 genotypes were counted by a scale of 1-5, respectively. Five SNP markers on Chrs 9,11,12,17 and 18 were significantly associated with resistance to P. amygdali pv. tabaci. The identified SNPs and genomic regions will provide a useful information for further researches and breeding for resistance to P. sojae and P. amygdali pv. tabaci.

• Journal of Information Processing Systems
• /
• 제20권2호
• /
• pp.149-158
• /
• 2024

Traditional manual identification of crop leaf diseases is challenging. Owing to the limitations in manpower and resources, it is challenging to explore crop diseases on a large scale. The emergence of artificial intelligence technologies, particularly the extensive application of deep learning technologies, is expected to overcome these challenges and greatly improve the accuracy and efficiency of crop disease identification. Crop leaf disease identification models have been designed and trained using large-scale training data, enabling them to predict different categories of diseases from unlabeled crop leaves. However, these models, which possess strong feature representation capabilities, require substantial training data, and there is often a shortage of such datasets in practical farming scenarios. To address this issue and improve the feature learning abilities of models, this study proposes a deep transfer learning adaptation strategy. The novel proposed method aims to transfer the weights and parameters from pre-trained models in similar large-scale training datasets, such as ImageNet. ImageNet pre-trained weights are adopted and fine-tuned with the features of crop leaf diseases to improve prediction ability. In this study, we collected 16,060 crop leaf disease images, spanning 12 categories, for training. The experimental results demonstrate that an impressive accuracy of 98% is achieved using the proposed method on the transferred ResNet-50 model, thereby confirming the effectiveness of our transfer learning approach.