• Korean Journal of Remote Sensing
• /
• v.38 no.6_1
• /
• pp.1101-1107
• /
• 2022

The leaf temperature is principally regulated by the opening and closing of stomata that is sensitive to various kinds of plant physiological stress. Thus, the analysis of thermal imagery, one of remote sensing technique, will be useful to detect crop physiological condition on smart farm system and phenomics platform. However, there are few case studies using a thermal imaging camera on the agricultural application. In this study, three cases are presented: the effect of lime fertilizer on the rice, the different physiological properties of soybean under shading condition, and the screening of soybean breeds for salinity tolerance characteristic. The leaf temperature measured by thermal imaging camera on the three cases was used effectively to the physiological change and characteristics. However, the thermal imagery analysis requires considering the accuracy of measured temperature and the weather conditions that affects to the leaf temperature.

• Journal of Broadcast Engineering
• /
• v.27 no.6
• /
• pp.923-935
• /
• 2022

This paper deals with detection and classification of leaf diseases for phenomics systems. As the smart farm systems of plants are increased, It is important to determine quickly the abnormal growth of plants without supervisors. This paper considers the color distribution and shape information of leaf diseases, and designs two deep leaning networks in training the leaf diseases. In the first step, color distribution of input image is analyzed for possible diseases. In the second step, the image is first partitioned into small segments using mean shift clustering, and the color information of each segment is inspected by the proposed Color Network. When a segment is determined as disease, the shape parameters of the segment are extracted and inspected by proposed Shape Network to classify the leaf disease types in the third step. According to the experiments with two types of diseases (frogeye/rust and tipburn) for apple leaves and iceberg, the leaf diseases are detected with 92.3% recall for a segment and with 99.3% recall for an input image where there are usually more than two disease segments. The proposed method is useful for detecting leaf diseases quickly in the smart farm environment, and is extendible to various types of new plants and leaf diseases without additional learning.

• Journal of Bio-Environment Control
• /
• v.31 no.3
• /
• pp.255-260
• /
• 2022

This study aimed to develop a service model that uses a deep learning algorithm for detecting diseases and pests in strawberries through image data. In addition, the pest detection performance of deep learning models was further improved by proposing segmented image data sets specialized in disease and pest symptoms. The CNN-based YOLO deep learning model was selected to enhance the existing R-CNN-based model's slow learning speed and inference speed. A general image data set and a proposed segmented image dataset was prepared to train the pest and disease detection model. When the deep learning model was trained with the general training data set, the pest detection rate was 81.35%, and the pest detection reliability was 73.35%. On the other hand, when the deep learning model was trained with the segmented image dataset, the pest detection rate increased to 91.93%, and detection reliability was increased to 83.41%. This study concludes with the possibility of improving the performance of the deep learning model by using a segmented image dataset instead of a general image dataset.

• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.67 no.3
• /
• pp.164-171
• /
• 2022

We studied the influence of Hanwoo (Korean native cattle) manure compost soil application on the growth and yield of maize (Zea mays L.). We compared the soil application of chemical fertilizer (CF), commercial manure (CM), Hanwoo manure (HM), and the mixed Hanwoo manure and chemical fertilizer (HM + CF). CF application showed faster tasseling and silking dates compared to the other treatments. During the early plant growth stage of maize, CF application resulted in taller plant height, However, during later growth stages (55 days after transplanting). HM (226.0 cm) and HM + CF (230.0 cm) treatment resulted in taller plant height compared to CF (216.2 cm). Post-harvest measurement results showed that, the ear length was longer in HM (22.13 cm) and HM + CF (22.70 cm) compared to others, while ear diameter, ear weight, and 100-grains weight showed no significant difference among CF, HM, and HM + CF groups. The use of HM resulted in delayed growth during the early stages of plant development compared to CF. However, crop productivity markers of ear weight and ear diameter showed no significant difference compared to CF. Thus, HM treatment was comparable to CF treatment in maize cultivation.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.3
• /
• pp.125-132
• /
• 2023

In this study, we compared the performance of machine learning models for predicting Vapor Pressure Deficits (VPD) in greenhouses that affect pore function and photosynthesis as well as plant growth due to nutrient absorption of plants. For VPD prediction, the correlation between the environmental elements in and outside the greenhouse and the temporal elements of the time series data was confirmed, and how the highly correlated elements affect VPD was confirmed. Before analyzing the performance of the prediction model, the amount and interval of analysis time series data (1 day, 3 days, 7 days) and interval (20 minutes, 1 hour) were checked to adjust the amount and interval of data. Finally, four machine learning prediction models (XGB Regressor, LGBM Regressor, Random Forest Regressor, etc.) were applied to compare the prediction performance by model. As a result of the prediction of the model, when data of 1 day at 20 minute intervals were used, the highest prediction performance was 0.008 for MAE and 0.011 for RMSE in LGBM. In addition, it was confirmed that the factor that most influences VPD prediction after 20 minutes was VPD (VPD_y__71) from the past 20 minutes rather than environmental factors. Using the results of this study, it is possible to increase crop productivity through VPD prediction, condensation of greenhouses, and prevention of disease occurrence. In the future, it can be used not only in predicting environmental data of greenhouses, but also in various fields such as production prediction and smart farm control models.

• Journal of Food Hygiene and Safety
• /
• v.38 no.4
• /
• pp.228-235
• /
• 2023

Peanut is a well-known food allergen that causes adverse reactions ranging from mild urticaria to life-threatening anaphylaxis. Consumers suffering from peanut allergies should thus avoid consuming undeclared peanuts in processed foods. Therefore, effective cleaning methods are needed to remove food allergens from manufacturing facilities. To address this, wet cleaning methods with washing water at different temperatures, abstergents (peracetic acid, sodium bicarbonate, dilute sodium hypochlorite, detergent), and cleaning tools (brush, sponge, paper towel, and cotton) were investigated to remove peanuts from materials used in food manufacture, including plastics, wood, glass, and stainless steel. Peanut butter was coated on the surface of the glass, wood, stainless steel, and plastic for 30 min and cleaned using wet cleaning. The peanut residue on the cleaned surfaces was swabbed and determined using an optimized enzyme-linked immunosorbent assay (ELISA). Cleaning using a brush and hot water above 50℃ showed an effective reduction of peanut residue from the surface. However, removing peanuts from wooden surfaces was complicated. These results provide information for selecting appropriate materials in food manufacturing facilities and cleaning methods to remove food allergens. Additionally, the cleaning methods developed in this study can be applied to further research on removing other food allergens.

• Journal of the Korea Convergence Society
• /
• v.13 no.1
• /
• pp.149-160
• /
• 2022

In this study, the physical quality and microbial changes of ginseng sprout according to the pretreatment process and packaging container were evaluated to improve the storage properties of ginseng sprout produced in smart farm. Quality change during storage (10 days) according to pretreatment method (ascorbic acid, citric acid, peroxyacetic acid) and packaging container (expanded polystyrene (EP), polypropylene (PP), polyethylene (PE), polypropylene + polyethylene + cast polypropylene (PP+PE+CPP)) was evaluated in terms of texture, viable cell count, water content, and color. As a result of comparison according to the type of pretreatment, the citric acid treatment group showed the lowest texture change and the effect on inhibition of bacterial growth. On the other hand, citric acid, which was most effective among pretreatments, was treated in all samples and then stored in 4 types of containers. Specially, the ginseng sprout in PP packaging container was not observed significant softening or color changes after 10 days storage, and the lowest changes in viable cell number. Therefore, this study was shown that citric acid treatment and use of PP packaging container are effective in increasing the shelf life of ginseng sprout.

• Journal of Bio-Environment Control
• /
• v.32 no.3
• /
• pp.190-196
• /
• 2023

This study was carried out to collect gas emitted from agricultural heaters using kerosene and to identify the emission concentration of carbon dioxide according to the age of agricultural heating machine. As a result of the linear regression analysis, the carbon dioxide emissions according to the year of agricultural heating machine are R² = 0.84, which follows y = 26.99x+721.98. Distributed analysis was classified into three groups according to the age of agricultural heating machine. As a result of the distributed analysis, it was 2.196×10^-13, which was smaller than the 0.05 probability set for the analysis, which means that there is a difference in at least one group. As a result, the age of the agriculture machine was divided into three groups and the difference between groups was tested. A statistical analysis result was derived that there was a difference in the emission concentration of carbon dioxide according to the age of agricultural heating machine. It is thought that it can be used to investigate greenhouse gas emissions by investigating the amount of carbon dioxide generated by agricultural heaters in the agricultural field of Korea.

• Journal of Bio-Environment Control
• /
• v.32 no.3
• /
• pp.197-204
• /
• 2023

Heat stress causes a decrease in immunity and disease occurrence in livestock, increasing mortality and impairing productivity. In particular, chickens are very vulnerable to high temperatures compared to other livestock species because their entire body is covered with feathers and sweat glands are not developed. Currently, air conditioning systems are essential in broiler houses to prevent high-air temperature damage to broilers, but conventional cooling facilities are greatly affected by the external environment, so there are limits to their use. In this study, to propose a cooling method, thermal insulation paint and a heat pump were apply in the broiler houses to evaluate the temperature reduction effect. The heat pump experiment was to analyze the cooling effect according to the change in ventilation rate and propose an appropriate. As a result of the experiment, the heat-insulating paint reduced the temperature of the broiler houses by maximum 1-2℃, and in the broiler houses where the heat pump was operated, the temperature decrease was the largest when the ventilation rate was the lowest. When the air temperature in the house is similar to or lower than the outside air temperature, it is considered to be most effective to use a heat pump while maintaining only the minimum ventilation rate.

• Journal of Mushroom
• /
• v.18 no.3
• /
• pp.274-279
• /
• 2020

This study was conducted to investigate the characteristics of the medium used on the composting step, comparing the excavator agitator with the self-propelled turner. The temperature of the outdoor composting medium tended to increase rapidly after flipping in the turner. The late composting medium temperature was maintained at the excavator treatment area (farm practice), and the late composting effect progressed. During the field composting stage, various microorganisms such as Bacillus spp., Actinomycetes, fluorescent Pseudomonas spp., and filamentous fungi were distributed in the medium, and the density of aerobic bacteria involved in the decomposition of the medium was increased. Under high-temperature composting conditions, blue fungi, and mesophilic actinomycetes were inhibited or killed. Thermophilic actinomycetes, which play an important role in decomposing organic matter, showed higher densities than those observed in farm practices in the self-propelled turner process. The length of rice straw was slightly shorter when the self-propelled turner was used, and the water content did not show any significant difference between treatments. The a and b values tended to increase as the inverter was turned over. The CN ratio of the composting broth was lowered from 23.1 to 16.2 for the 5th turnover in the context of farming practices, and from 23.3 to 16.9 in the context of the self-propelled turner. The yield of each treatment was increased by 20% in 1 period, 28% in 2 periods, and 26% in 3 periods; the overall yield was 23%.