• Journal of The Korean Society of Agricultural Engineers
• /
• v.64 no.1
• /
• pp.15-26
• /
• 2022

3D open-field farm model developed from UAV (Unmanned Aerial Vehicle) data could make crop monitoring easier, also could be an important dataset for various fields like remote sensing or precision agriculture. It is essential to separate crops from the non-crop area because labeling in a manual way is extremely laborious and not appropriate for continuous monitoring. We, therefore, made a 3D open-field farm model based on UAV images and developed a crop segmentation model using a supervised machine learning algorithm. We compared performances from various models using different data features like color or geographic coordinates, and two supervised learning algorithms which are SVM (Support Vector Machine) and KNN (K-Nearest Neighbors). The best approach was trained with 2-dimensional data, ExGR (Excess of Green minus Excess of Red) and z coordinate value, using KNN algorithm, whose accuracy, precision, recall, F1 score was 97.85, 96.51, 88.54, 92.35% respectively. Also, we compared our model performance with similar previous work. Our approach showed slightly better accuracy, and it detected the actual crop better than the previous approach, while it also classified actual non-crop points (e.g. weeds) as crops.

• Journal of Korean Society of Occupational and Environmental Hygiene
• /
• v.30 no.3
• /
• pp.292-298
• /
• 2020

Objectives: The aim of this research is to establish Similar Exposure Groups (SEGs) for chemical and biological risk factors that occur in farm work involving 24 tasks among 15 crops. Methods: To categorize SEGs, work type, work environment, and similar tasks for each crop were considered. After confirming the chemical risk factors (pesticides, inorganic dust-total dust and PM₁₀, ammonia, and hydrogen sulfide) and biological factors (organic dust-total dust and PM₁₀, and endotoxins) that occur in the crops and tasks, similar crops and tasks were selected as SEGs. Results: Among chemical risk factors, pesticides was selected for the SEGs, which was categorized by open field, greenhouse, fruit, and specialty crops. For inorganic dust, open field (plowing harrowing, seedling, planting, harvest, and sorting and packing) and specialty crops (plowing harrowing, seedling, planting, and harvest) were selected as SEGs. For ammonia and hydrogen sulfide, livestock (preparation of farm, management of nursery bed, feeding, shipment and manure treatment) were selected as SEGs. For biological risk factors such as organic dust (total dust, PM₁₀) and endotoxins, open field (manure application), greenhouse (plowing harrowing, planting, manure application, and harvest), fruit (manure application), specialty crops (manure application, making furrows, mixing mushroom media, harvest, and sorting and packing), and livestock (preparation of farm, maintaining poultry litter, feeding, shipment and manure treatment) were selected as SEGs. Conclusions: To establish similar exposure groups in agriculture, it is important that the characteristics of each hazard factor are categorized by identifying risk factors occurring by tasks.

• Journal of Korean Society of Rural Planning
• /
• v.29 no.4
• /
• pp.127-135
• /
• 2023

This study examined the impact of changes in agricultural production methods on society, the economy, and the environment. While traditional open-field farming relied heavily on natural conditions, modern approaches, including greenhouse and smart farming, have emerged to mitigate the effects of climate and seasonal variations. Facility horticulture has been on the rise since the 1990s, and recently, there has been a growing interest in smart farms due to reasons such as climate change adaptation and food security. We compared open-field spinach and greenhouse spinach using agricultural income survey data, and we also compared greenhouse tomato cultivation with smart farming tomato cultivation, utilizing data from the smart farm survey reports. The economic results showed that greenhouse spinach increased yield by 25.8% but experienced a 29% decrease in income due to equipment depreciation. In the case of tomato production in smart farms, both yield and income increased by 36-39% and 34-46%, respectively. In terms of environmental impact, we also compared fertilizer and energy usage. It was found that greenhouse spinach used 29% less fertilizer but 14% more energy compared to open-field spinach. Smart farming for tomatoes saw a negligible decrease in electricity and fuel costs. Regarding the social impact, greenhouse spinach reduced labor hours by 31%, and the introduction of smart farming for tomatoes led to an average 11% reduction in labor hours. This reduction is expected to have a positive effect on sustainable farming. In conclusion, the transition from open-field to greenhouse cultivation and from greenhouse cultivation to smart farming appears to yield positive effects on the economy, environment, and society. Particularly, the reduction in labor hours is beneficial and could potentially contribute to an increase in rural populations.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.11 no.1
• /
• pp.15-20
• /
• 2016

Recently, the u-IT applications for plants and livestock become larger and control of livestock farm environment has been used important in the field of industry. We implemented wireless sensor networks and farm environment automatic control system for applying to the breeding barn environment by calculating the THI index. First, we gathered environmental information like livestock object temperature, heart rate and momentum. And we also collected the farm environment data including temperature, humidity and illuminance for calculating the THI index. Then we provide accurate control action roof open and electric fan in of intelligent farm to keep the best state automatically by using collected data. We believed this technology can improve industrial competitiveness through the u-IT based smart integrated management system introduction for industry aversion and dairy industries labor shortages due to hard work and old ageing.

• Journal of Ocean Engineering and Technology
• /
• v.33 no.6
• /
• pp.648-656
• /
• 2019

The ecological changes in the ocean due to the drastic global warming require that action be taken to sustain the productivity of fisheries. Proper ocean facilities could help prevent the loss of the expenditures made on marine aquaculture and reduce the related compensation for various ocean conditions. The aim of this study was to develop a floating ocean wave-breaker using an eco-friendly concrete and conducting a site survey, a structural analysis, and a test of towing the tank. As a result, the wave at the fish farm would be reduced. The results of the holding power of anchors and the capability of moving the floating structures were considered in the design of the wave-breaker. The analyses of the material properties of concrete and the steel structures, as well as the CAPEX and OPEX analyses of the manufacturing and operation processes confirmed the superiority of the floating concrete wave-breaker. In particular, this study demonstrated that the concrete floating breakwater can protect the fish farm against typhoons and reverse-waves, thereby reducing losses of the fish.

• The Korean Journal of Community Living Science
• /
• v.24 no.4
• /
• pp.543-552
• /
• 2013

Physiological and subjective responses of the farmers and thermal environment during chili harvest in the open field were investigated to evaluate the thermal environments and farmers's workload. Eight career female farmers in their sixties participated as subjects both in morning work(MW, AM 9:00~10:30) and in afternoon work(AW, PM 15:00~16:30) with each lasting about 90 minutes. The results were as follows. 1) Air temperature, air humidity, globe temperature and WBGT of MW were mean $25.54^{\circ}C$, 81.82%RH, $37.72^{\circ}C$, $26.27^{\circ}C$ and AW were mean $30.63^{\circ}C$ 82.50%RH, $40.11^{\circ}C$, $30.02^{\circ}C$, respectively. By the WBGT, we evaluated that the thermal environment in the afternoon in the open field gave a thermal burden to farmers. 2) Mean skin temperature of AW($34.8{\pm}0.8^{\circ}C$) was higher than MW($33.5{\pm}1.2^{\circ}C$)(p<0.05). Clothing microclimate temperature on the chest of each work time were $31.3^{\circ}C$(MW) and $32.7^{\circ}C$(AW). Clothing microclimate humidity on the chest of each work time were over 80%RH. Heart rate were 88.5bpm(MW) and 91.7bpm(AW) respectively. 3) Farmers working in the afternoon felt uncomfortable after 45~60 min. of work and in the morning they felt uncomfortable after 90 min. of work. We evaluated that the harvesting of chilies in the open field was 'moderate work' by the physiological responses but the level of thermal burden increased over time especially in the afternoon work. It is suggested that farm workers should drink fluids between work to stay in homeostasis by sweating and to take frequent rests. Active clothing ventilation and wearing functional garments would help farm workers excrete sweat effectively.

• Asian-Australasian Journal of Animal Sciences
• /
• v.9 no.3
• /
• pp.281-285
• /
• 1996

On farm demonstration of urea treatment (5 kg urea dissolved in 60 litre water/100kg) of straw was performed at 6 different sites and treated straw was stored by three different methods i.e., plastic covered, mud plastered and existing farmers technique (mud plastered on the top and open from sides) to determine the best storage method in field. Untreated and treated samples were taken after 5 week storage period and subjected to crude protein, crude fibre and cell wall constituents analysis. In situ dry matter digestibility of straw was measured by nylon bag technique in buffalo bulls. Crude protein content increased by 100 to 153 percent in treated straw stored by different methods. Maximum increase in crude protein of treated straw was noticed in mud plastered method. Urea treatment of straw resulted in significant decrease in crude fibre contents in all the storage methods. Treatment of straw enhanced the in situ digestibility by 25-49 percent and maximum digestibility (53%) was found in mud plastered storage method. It was concluded that the mud plastered storage method for urea treated straw was found to be the best at farm level.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2016.10a
• /
• pp.496-499
• /
• 2016

The smartfarm is a leader in the Field of environmental monitoring in agriculture. By the use of wireless remote systems, monitoring applications of the smartfarm are able to provide vital information to the farmer wherever he may be. Absentee farmers are finding the ease of viewing the application graphs on their mobile phone is providing them with peace of mind. We design system and technical requirements of service for managing and operating smart-farm based on cloud technology. It describes requirements of cloud technology for monitoring, controlling, managing, and operating cloud-based smart farm. Smart farm system and service with cloud platform contains 3 interfaces and 3 services. In addition, smart-farm using cloud platform could have several cases so it should be established and managed in varying way depending on cultivars, its size and type. This paper will focus the industry's attention on the importance of Open/Standard Cloud platform thereby stimulating the smartfarm in agriculture.

• Journal of the Korean Institute of Landscape Architecture International Edition
• /
• no.1
• /
• pp.150-158
• /
• 2001

Maintenance open spaces and community development in large scale housing development is one of the most important issues. We(UDC) established a resident participation activity for maintenance and use open space with community development in Hachioji New Town from 1997. The purpose of this study is to establish resident participation activities for maintenance and use open space with community development in Hajichioji New Town, and to clarify the characteristics and to on sider about efficiency of the activity. We established Minamino Shizen-Juku as a methodology for maintenance and use open spaces at the same time Hachioji New Town was opened in 1997. The activity has continued by now in 2001. We conducted questionnaire survey to make sure efficiency and characteristics of the activity past three years. Minamino Shizen-Juku (nature friendly lessons) is a resident participation activity in Hachioji New Town. It was established in 1997 as soon as the new town was opened, this year is fifth since it was started. It has three objects. 1)Maintenance and use woody environment, 2) Community development, 3) Continuation and renewal native culture. And it has general course, three special courses and one extra course were established in the activity. 1) General course is an activity participated all of member. It's included farming experience in the native field and seasonal events. 2) Rice growing and woods maintenance course is rice growing and wild wood maintenance in the park as a series of annual farming activities. 3) Benefaction from farm course is started from planting spring vegetable at Mizukoshi(Leader of Minamino Shezen-Juku)'s field. There is the number of participant limit because of the area of the field. 4) Watching nature course is watching seasonal wild flowers, trees, animals and plants to know about native nature. 5) Extra program is programmed to know about native history and tradition. It's planned including participant's ideas. Not member can participate in this course too.

• Korean Journal of Remote Sensing
• /
• v.40 no.1
• /
• pp.93-101
• /
• 2024

Accurate field crop classification is essential for various agricultural applications, yet existing methods face challenges due to diverse crop types and complex field conditions. This study aimed to address these issues by combining support vector machine (SVM) models with multi-seasonal unmanned aerial vehicle (UAV) images, texture information extracted from Gray Level Co-occurrence Matrix (GLCM), and RGB spectral data. Twelve high-resolution UAV image captures spanned March-October 2021, while field surveys on three dates provided ground truth data. We focused on data from August (-A), September (-S), and October (-O) images and trained four support vector classifier (SVC) models (SVC-A, SVC-S, SVC-O, SVC-AS) using visual bands and eight GLCM features. Farm maps provided by the Ministry of Agriculture, Food and Rural Affairs proved efficient for open-field crop identification and served as a reference for accuracy comparison. Our analysis showcased the significant impact of hyperparameter tuning (C and gamma) on SVM model performance, requiring careful optimization for each scenario. Importantly, we identified models exhibiting distinct high-accuracy zones, with SVC-O trained on October data achieving the highest overall and individual crop classification accuracy. This success likely stems from its ability to capture distinct texture information from mature crops.Incorporating GLCM features proved highly effective for all models,significantly boosting classification accuracy.Among these features, homogeneity, entropy, and correlation consistently demonstrated the most impactful contribution. However, balancing accuracy with computational efficiency and feature selection remains crucial for practical application. Performance analysis revealed that SVC-O achieved exceptional results in overall and individual crop classification, while soybeans and rice were consistently classified well by all models. Challenges were encountered with cabbage due to its early growth stage and low field cover density. The study demonstrates the potential of utilizing farm maps and GLCM features in conjunction with SVM models for accurate field crop classification. Careful parameter tuning and model selection based on specific scenarios are key for optimizing performance in real-world applications.