• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2016.10a
• /
• pp.485-488
• /
• 2016

The level of domestic greenhouse complex environmental control technology is a hardware-oriented automation steps that mechanically control the environments of greenhouse, such as temperature, humidity and $CO_2$ through the technology of cultivation and consulting experts. This automation brings simple effects such as labor saving. However, in order to substantially improve the output and quality of agricultural products, it is essential to track the growth and physiological condition of the plant and accordingly control the environments of greenhouse through a software-based complex environmental control technology for controlling the optimum environment in real time. Therefore, this paper is a part of general methods on the greenhouse complex environmental control technology. and presents a horticulture production forecasting methods using artificial neural networks through the analysis of big data systems of smart farm performed in our country and artificial neural network technology trends.

• The Journal of the Korea Contents Association
• /
• v.21 no.4
• /
• pp.424-433
• /
• 2021

The aim of this study is to explores the possibility of applying new aquaponics using guppies, a tropical fish breeding as companion fish at home, different from the aquaponics system using fish species such as loach, carp, and catfish for commercial purposes. To facilitate the application of Aquaponics at home, a system was established by connecting a water tank, water plants, hydroponic pots, plant growth LEDs, and Arduino sensors using Internet of Things(IoT) technology. As a hydroponic crops, lettuce that can be easily obtained and consumed at home was selected. In order to confirm the applicability of aquaponics using tropical fish, the growth rates of hydroponic crops in the same environment were compared as a control. The growth rate of aquaponics crops using tropical fish was about 77.4% of that of hydroponic crops. This will produce the same effect as hydroponic cultivation if conditions correspond with enough fish quantity to feed plant and appropriate pH control for growth are met. It can be seen that, and in the future, it can be used to develop an Aquaphonics standard system applicable at home.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.15 no.6
• /
• pp.1137-1144
• /
• 2020

This paper aims to provide strategic suggestions by analyzing technology trends related to big data, IoT, and artificial intelligence. To this end, analysis was performed using the 2018 national R&D information, and major basic analysis and language network analysis were performed. As a result of the analysis, research and development related to big data, IoT, and artificial intelligence are being conducted by focusing on the basic and development stages, and it was found that universities and SMEs have a high proportion. In addition, as a result of the language network analysis, it is judged that the related fields are mainly research for use in the smart farm and healthcare fields. Based on these research results, first, big data is essential to use artificial intelligence, and personal identification research should be conducted more actively. Second, they argued that full-cycle support is needed for technology commercialization, not simple R&D activities, and the need to expand application fields.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.63 no.4
• /
• pp.23-32
• /
• 2021

For agricultural water management, it is essential to establish the digital infrastructure data such as agricultural watershed, irrigated area and canal network in rural areas. Approximately 70,000 irrigation facilities in agricultural watershed, including reservoirs, pumping and draining stations, weirs, and tube wells have been installed in South Korea to enable the efficient management of agricultural water. The total length of irrigation and drainage canal network, important components of agricultural water supply, is 184,000 km. Major problem faced by irrigation facilities management is that these facilities are spread over an irrigated area at a low density and are difficult to access. In addition, the management of irrigation facilities suffers from missing or errors of spatial information and acquisition of limited range of data through direct survey. Therefore, it is necessary to establish and redefine accurate identification of irrigated areas and canal network using up-to-date high resolution images. In this study, previous existing data such as RIMS (Rural Infrastructure Management System), smart farm map, and land cover map were used to redefine irrigated area and canal network based on appropriate image data using satellite imagery, aerial imagery, and drone imagery. The results of the building the digital infrastructure in rural areas are expected to be utilized for efficient water allocation and planning, such as identifying areas of water shortage and monitoring spatiotemporal distribution of water supply by irrigated areas and irrigation canal network.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.63 no.1
• /
• pp.103-116
• /
• 2021

Analysis of runoff is substantial for effective water management in the watershed. Runoff occurs by reaction of a watershed to the rainfall and has non-linearity and uncertainty due to the complex relation of weather and watershed factors. ANN (Artificial Neural Network), which learns from the data, is one of the machine learning technique known as a proper model to interpret non-linear data. The performance of ANN is affected by the ANN's structure, the number of hidden layer nodes, learning rate, and activation function. Especially, the activation function has a role to deliver the information entered and decides the way of making output. Therefore, It is important to apply appropriate activation functions according to the problem to solve. In this paper, ANN models were constructed to estimate runoff with different activation functions and each model was compared and evaluated. Sigmoid, Hyperbolic tangent, ReLU (Rectified Linear Unit), ELU (Exponential Linear Unit) functions were applied to the hidden layer, and Identity, ReLU, Softplus functions applied to the output layer. The statistical parameters including coefficient of determination, NSE (Nash and Sutcliffe Efficiency), NSEln (modified NSE), and PBIAS (Percent BIAS) were utilized to evaluate the ANN models. From the result, applications of Hyperbolic tangent function and ELU function to the hidden layer and Identity function to the output layer show competent performance rather than other functions which demonstrated the function selection in the ANN structure can affect the performance of ANN.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.64 no.5
• /
• pp.67-77
• /
• 2022

Recently, the trend in structural analysis and design is moving towards the development of reliable system. The reliability-based method defines various limit states related to usability and failure, thereby enabling multiple levels of design according to the importance of a structure. Meanwhile, an actual structure is composed of a set of several elements, and particularly, a frame type is composed of a system in which the members are connected each other. At this time, the actual connection between members is in a semi-rigid condition, not in complete rigid or hinged. This semi-rigid is found in several structures, especially in agricultural facilities designed with lightweight materials. In this study, a system reliability analysis technique for frame structure was established, and applied to an analysis of the semi-rigid connection. Various conditions of correlation were applied to reflect the connectivity between members, and through this, the limitations of existing structural analysis method and the behavioral characteristics of structure were analyzed. The failure probability of the frame member component and the overall structure system was significantly different in consideration of the semi-rigid connection. In addition, it was evaluated that the behavior of structure can be more accurately analyzed if the correlation according to the position of members in a system is further investigated.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.64 no.6
• /
• pp.1-12
• /
• 2022

Estuary reservoirs were artificial reservoir with seawalls built at the exit points of rivers. Although many water resources can be saved, it is difficult to manage due to the large influx of pollutants. To manage this, it is necessary to analyze watersheds and reservoirs through accurate modeling. Therefore, in this study, we linked the Hydrological Simulation Program-FORTRAN (HSPF), Environmental Fluid Dynamics Code (EFDC), and Water quality Analysis Simulation Program (WASP) models to simulate the hydrology and water quality of the watershed and the water level and quality of estuary lakes. As a result of applying the linked model in stream, R² 0.7 or more was satisfied for the watershed runoff except for one point. In addition, the water quality satisfies all within 15% of PBIAS. In reservoir, R² 0.72 was satisfied for water level and the water quality was within 15% of T-N and T-P. Through the modeling system, We applied upstream pollutant management scenarios to analyze changes in water quality in estuary reservoirs. Three pollution source management were applied as scenarios, the improvement of effluent water quality from the sewage treatment plant and the livestock waste treatment plant was effective in improving the quality of the reservoir water, while the artificial wetland had little effect. Water quality improvement was confirmed as a measure against upstream pollutants, but it was insufficient to achieve agricultural water quality, so additional reservoir management is required.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.17 no.6
• /
• pp.1105-1112
• /
• 2022

Field data monitoring systems such as renewable energy generation and smart farm integrated control are developing from PC and server to mobile first, and various wireless communication and application services have emerged with the development of IoT technology. Low-power wide-area networks are services optimized for low-power, low-capacity, and low-speed data transmission, and data collected in the field is transmitted to designated storage servers or cloud-based data platforms, enabling data monitoring. In this paper, we implement an IoT repeater that collects field data with a single device and transmits it to a wireless carrier cloud data flat using a low-power wide-area network, and a monitoring app using it. Using this, the system configuration is simpler, the cost of deployment and operation is lower, and effective data accumulation is possible.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.64 no.3
• /
• pp.63-73
• /
• 2022

A more accurate understanding of the irrigation water supply is necessary for efficient agricultural water management. Although we measure water levels in an irrigation canal using ultrasonic water level gauges, some errors occur due to malfunctions or the surrounding environment. This study aims to apply CNN (Convolutional Neural Network) Deep-learning-based image classification and segmentation models to the irrigation canal's CCTV (Closed-Circuit Television) images. The CCTV images were acquired from the irrigation canal of the agricultural reservoir in Cheorwon-gun, Gangwon-do. We used the ResNet-50 model for the image classification model and the U-Net model for the image segmentation model. Using the Natural Breaks algorithm, we divided water level data into 2, 4, and 8 groups for image classification models. The classification models of 2, 4, and 8 groups showed the accuracy of 1.000, 0.987, and 0.634, respectively. The image segmentation model showed a Dice score of 0.998 and predicted water levels showed R² of 0.97 and MAE (Mean Absolute Error) of 0.02 m. The image classification models can be applied to the automatic gate-controller at four divisions of water levels. Also, the image segmentation model results can be applied to the alternative measurement for ultrasonic water gauges. We expect that the results of this study can provide a more scientific and efficient approach for agricultural water management.

• Journal of Software Assessment and Valuation
• /
• v.17 no.1
• /
• pp.75-82
• /
• 2021

Mastitis in cows is a major factor that hinders dairy productivity of farms, and many attempts have been made to solve it. However, research on mastitis has been limited to diagnosis rather than prediction, and even this is mostly using a single sensor. In this study, a predictive model was developed using multivariate data including biometric data and environmental data. The data used for the analysis were collected from robot milking machines and sensors installed in farmhouses in Chungcheongnam-do, South Korea. The recurrent neural network model using three weeks of data predicts whether or not mastitis is diagnosed the next day. As a result, mastitis was predicted with an accuracy of 82.9%. The superiority of the model was confirmed by comparing the performance of various data collection periods and various models.