• Journal of Bio-Environment Control
• /
• v.31 no.3
• /
• pp.152-162
• /
• 2022

This study developed simulation model for predicting the greenhouse interior environment using artificial intelligence machine learning techniques. Various methods have been studied to predict the internal environment of the greenhouse system. But the traditional simulation analysis method has a problem of low precision due to extraneous variables. In order to solve this problem, we developed a model for predicting the temperature inside the greenhouse using machine learning. Machine learning models are developed through data collection, characteristic analysis, and learning, and the accuracy of the model varies greatly depending on parameters and learning methods. Therefore, an optimal model derivation method according to data characteristics is required. As a result of the model development, the model accuracy increased as the parameters of the hidden unit increased. Optimal model was derived from the GRU algorithm and hidden unit 6 (r² = 0.9848 and RMSE = 0.5857℃). Through this study, it was confirmed that it is possible to develop a predictive model for the temperature inside the greenhouse using data outside the greenhouse. In addition, it was confirmed that application and comparative analysis were necessary for various greenhouse data. It is necessary that research for development environmental control system by improving the developed model to the forecasting stage.

• Journal of Convergence for Information Technology
• /
• v.9 no.10
• /
• pp.108-113
• /
• 2019

In relation to $4^{th}$ industrial revolution, it is required to build a smart agricultural system using the pest control drones, which are emerging fast these days as a role to support pest control work of farmers and improve aging issues in farming. However, the absence of accurate criteria on management of the pest control drones and the effect of pesticide application is leading to damage to crops by pesticides. The extreme shortage of analysis of management of the pest control drones and relevant studies, and big differences in pest control efficiency depending on the operation skills of controllers are the biggest reasons for the damage. Therefore, this paper suggests a basic study on agricultural pest control drone operation system buildup to make out working schedules and calculate the dosage of pesticide by understanding the features of the pest control drones properly based on the control using smart operating mode.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2019.05a
• /
• pp.618-620
• /
• 2019

Smart Farm, which combines agriculture and ICT convergence technology, is at a lower stage than other industries in Korea, but it is also one of the most active research and development fields. Smart Farm aims to improve the efficiency of each step by collecting, processing and analyzing various information of agriculture sector through convergence between agriculture and ICT technology. In this study, we studied the image processing method that can distinguish strawberry which can be harvested at harvest time by color for smart farm composition of strawberry which is a horticultural crop. Strawberry harvesting requires a lot of labor in the process of growing strawberries. In this study, we aim to collect information necessary for labor saving in strawberry harvester. As a precedent study, we plan to implement a form in which the color temperature changes according to the light direction and brightness value through OpenCV color detection using Python. In the future, it is planned to study strawberry color value suitable for harvest by applying compensation value to color temperature change.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.6
• /
• pp.1049-1055
• /
• 2023

The utilization of agricultural drones for pest control operations has been increasing due to its economic efficiency. However, variations in the effectiveness of these operations occur depending on the operator's proficiency. In this study, we applied a smart operating mode to overcome the limitations of manual flight mode and proposed a numerical model. Through comparative validation with prior research, we conducted experimental verification. As a result, we determined the spray time and calculation of spray area for each drone model. We selected a drone for pest control with a high similarity to the numerical model and verified it experimentally. Through this, we confirmed that the application of the smart operating mode is more effective in terms of calculation of spray area and operational efficiency compared to manual flight mode.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2014.05a
• /
• pp.715-718
• /
• 2014

Our country should continuously make efforts to secure the international competitiveness of the current domestic agriculture in a variety of industries converged with agriculture in order to get over the disaster due to global warming, cope with imported produces caused by FTA and scientific implementation technology provided by advanced countries like USA and European Union in spite of domestic agriculture advancement. Also, as domestic ICT technology is a world-class level, it is essential to make strategies of creating a high value such as the increase of productivity, efficiency and quality throughout the whole phase of production, circulation and consumption with the convergence of the existing agriculture technology and IT core technology including information management and automatic control. Therefore, this paper suggests standardization items which lead global standard and implementation direction on standardization through analysing the current situation of agriculture-ICT convergence in our country and technology/standardization trend.

• Journal of Internet of Things and Convergence
• /
• v.10 no.2
• /
• pp.61-67
• /
• 2024

In order to monitor the growth environment of new varieties of crops, it is necessary to build the agricultural production infrastructure and strengthen the agricultural resource management system using popular smart sensor tag technology. In addition, the infrastructure for improving high-quality new varieties of crops using IoT technology and the monitoring system must be strengthened. In other words, widespread smart sensor (RFID UHF Sensor Tag) technology for environmental monitoring required for improving new crop varieties is desperately needed in the smart farm environment. Therefore, in this paper, we implemented an integrated sensor that can implement smart tag functions based on heterogeneous integrated sensors. In addition, we developed a technology that can manage crops in real time through the implemented smart integrated tag and smartphone linkage. For this purpose, an integrated antenna capable of RFID and Bluetooth communication was constructed. In addition, a communication method that allows information to be collected directly from the smartphone through the Bluetooth function was used.

• Smart Media Journal
• /
• v.13 no.2
• /
• pp.136-144
• /
• 2024

In recent years, with the rapid development of IT technology and the aging of the population, various solutions to the labor shortage have emerged. In the livestock industry, there are an increasing number of management systems that utilize artificial intelligence technology. The Metaverse Smart Farm is a system that combines the digital virtual world with advanced agricultural technology. With this system, farmers can monitor the health of their animals in real time without having to visit the barns, and analyze the data collected through sensors and cameras for more efficient agricultural management. In addition, the barn environment can be adjusted through a remote control function, which is expected to reduce labor and revitalize the livestock industry.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.15 no.5
• /
• pp.413-422
• /
• 2022

Smart farms are receiving a lot of attention as a way to solve the chronic labor shortage and aging problems in agriculture. The smart farm industry, called the 6th industrial revolution, needs to strengthen its competitiveness. In order to apply innovative IT technology to agriculture, it is important to collect and analyze information about prior research or patents. This paper examines smart farm patent trends through 5,789 patent data related to smart farm using the domestic patent information search service(KIPRIS). This paper examines the domestic patent trends of smart farm information through keyword network, ego network, simultaneous appearance network, and bigram network analysis. As a result of network analysis related to smart farm patents, patents related to smart farm systems and control technologies were the most common. This paper can provide help in setting the direction of future smart farm-related patent research.

• Smart Media Journal
• /
• v.11 no.5
• /
• pp.9-16
• /
• 2022

Recently, agricultural sites are automating into digital agricultural smart farms by applying technologies such as big data and Internet of Things (IoT). These smart farms aim to increase production and improve crop quality by measuring the environment of crops, investigating and processing data. Production prediction is an important study in smart farm digital agriculture, which is a high-tech agriculture, and it is necessary to analyze environmental data using big data and further standardized research to manage the quality of growth information data. In this paper, environmental and production data collected from smart farm strawberry farms were analyzed and studied. Based on regression analysis, crop production prediction models were analyzed using Ridge Regression, LightGBM, and XGBoost. Among the three models, the optimal model was XGBoost, and R2 showed 82.5 percent explanatory power. As a result of the study, the correlation between the amount of positive fluid absorption and environmental data was confirmed, and significant results were obtained for the production prediction study. In the future, it is expected to contribute to the prevention of environmental pollution and reduction of sheep through the management of sheep by studying the amount of sheep absorption, such as information on the growing environment of crops and the ingredients of sheep.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.38C no.5
• /
• pp.479-485
• /
• 2013

In this paper, we propose a smart farming system using the visible light communication based on the software defined radio (SDR) technology and the conventional RF radio. The proposed system can continuously monitor growth environments of the LED plant factory and automatically control the LED plant factory to keep optimal growth environments. Furthermore, by creating a database from various growth factors, the LED plant factory can be efficiently managed.