• Journal of IKEEE
• /
• v.24 no.2
• /
• pp.632-637
• /
• 2020

The non-intrusive load monitoring (NILM) is an important way to cost-effective real-time monitoring the energy consumption and time of use for each appliance in a home or business using aggregated energy from a single recording meter. In this paper, we collect from the smart farm's power consumption data acquisition system to the server via an LTE modem, converted the total power consumption, and the power of individual electric devices into HDF5 format and performed NILM analysis. We perform NILM analysis using open source denoising autoencoder (DAE), long short-term memory (LSTM), gated recurrent unit (GRU), and sequence-to-point (seq2point) learning methods.

• Smart Media Journal
• /
• v.8 no.3
• /
• pp.88-94
• /
• 2019

Livestock disease is a very important issue in the livestock industry because if livestock disease is not responded quickly enough, its damage can be devastating. To solve the issues involving the occurrence of livestock disease, it is necessary to diagnose in advance the status of livestock disease and develop systematic and scientific livestock feeding technologies. However, there is a lack of domestic studies on such technologies in Korea. This paper, therefore, proposes Livestock Disease Forecasting and Livestock Farm Integrated Control System using Cloud Computing to quickly manage livestock disease. The proposed system collects a variety of livestock data from wireless sensor networks and application. Moreover, it saves and manages the data with the use of the column-oriented database Hadoop HBase, a column-oriented database management system. This provides livestock disease forecasting and livestock farm integrated controlling service through MapReduce Model-based parallel data processing. Lastly, it also provides REST-based web service so that users can receive the service on various platforms, such as PCs or mobile devices.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.9
• /
• pp.355-362
• /
• 2022

Smart Farm, which combines information and communication technologies with agriculture is moving from simple monitoring of the growth environment toward discovering the optimal environment for crop growth and in the form of self-regulating agriculture. To this end, it is important to collect related data, but it is more important for farmers with cultivation know-how to analyze the collected data from various perspectives and derive useful information for regulating the crop growth environment. In this study, we developed a web service that allows farmers who want to obtain necessary information with data related to crop growth to easily analyze data. Web-based data analysis serivice developed uses R language for data analysis and Express web application framework for Node.js. As a result of applying the developed data analysis service together with the growth environment monitoring system in operation, we could perform data analysis what we want just by uploading a CSV file or by entering raw data directly. We confirmed that a service provider could provid various data analysis services easily and could add a new data analysis service by newly adding R script.

• Smart Media Journal
• /
• v.13 no.6
• /
• pp.16-23
• /
• 2024

Pigs express their reactions to their environment and health status through a variety of sounds, such as grunting, coughing, and screaming. Given the significance of pig vocalizations, their study has recently become a vital source of data for livestock industry workers. To facilitate this, we propose a lightweight deep learning model based on MobileNet that analyzes pig vocal patterns to distinguish pig voices from farm noise and differentiate between vocal sounds and coughing. This model was able to accurately identify pig vocalizations amidst a variety of background noises and cough sounds within the pigsty. Test results demonstrated that this model achieved a high accuracy of 98.2%. Based on these results, future research is expected to address issues such as analyzing pig emotions and identifying stress levels.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2017.04a
• /
• pp.111-112
• /
• 2017

IoT(Internet of Thing)기술의 발전으로 다양한 분야에서 라즈베리파이(Raspberry Pi)와 같은 경량시스템으로, 실생활에 유용하게 사용될 수 있는 비전문 시스템에 대한 다양한 형태의 기술이 선보이고 있다. 한 예로, 스마트팜(Smart farm)분야에서는 다양한 온실 형태로 과실류를 재배하고 있으며, 보다 전문적인 챔버(Chamber)형태의 시스템으로는 관엽식물/채소/알뿌리식물/인삼 등 다양한 식물류에서 사용되어 질 수 있다. 이에 본 논문에서는 챔버 시스템 상에 서버와의 연결 없이 정해진 생육 규칙에 따라 자동으로 제어 되는 라즈베리파이 엣지(Edge)에 기반한 챔버 제어 시스템에 대한 연구를 담고 있다.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.12 no.3
• /
• pp.290-298
• /
• 2019

The proportion of farm households in the total population is decreasing every year. The aging of rural areas is expected to deepen. The aging of agriculture is continuing due to the aging of the aged population and the decline of the young population, and agricultural manpower shortage is emerging as a threat to agriculture and rural areas. The existing facility cultivation was concentrated on the production / yield per unit area. However, nowadays, not only production but also crop quality should be good so that the quality of crops must be improved because they can secure competitiveness in the market. Therefore, the government plans to increase the productivity by hi-techization of ICT infrastructure horticulture and to plan the dissemination of energy saving smart greenhouse. Therefore, it is necessary to develop a Smart Farm convergence service system based on a hybrid algorithm to enhance diversity and connectivity. Therefore, this study aims to develop smart farm convergence service system which collects data of growth environment of the rhizosphere environment of crops by wireless and monitor smartphone.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.63 no.6
• /
• pp.89-100
• /
• 2021

The conservation of stream habitats has been gaining more public attention and fish habitat suitability index (HSI) is an important measure for ecological stream habitat assessment. The fish habitat preference is affected not only by physical stream conditions but also by water quality of which HSI was not available due to the lack of field data. The purpose of this study is to estimate the HSI of Zacco platypus for water quality parameters of water temperature, dissolved oxygen (DO), and biochemical oxygen demand (BOD) using the water environment monitoring data provided by the Ministry of Environment (ME). Fish population data merged with water quality were constructed by spatio-temporal matching of nationwide water quality monitoring data with bio-monitoring data of the ME. Two types of the HSI were calculated by the Instream Flow and Aquatic Systems Group (IFASG) method and probability distribution (Weibull) fitting for the four major river basins. Both the HSIs by the IFASG and Weibull fitting appeared to represent the overall distribution and magnitude of fish population and this can be used in stream fish habitat evaluation considering water quality.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.39 no.6
• /
• pp.419-427
• /
• 2021

Due to the effects of climate change and the reduction of the labor force due to COVID-19, the crop yield, harvest time, and cultivated area are rapidly changing every year. In order to respond flexibly to this situation, attempts to apply smart farm technology based on ICT (Information and Communication Technology) to individual farms are increasing. On the other hand, various stakeholders are trying to predict the yield of crops using artificial intelligence and IoT technology, but accurate prediction is difficult due to the lack of learning data. In this study, in order to overcome the data collection problem limited to a specific institution, a smart farmer service technology based on community mapping was developed in which farmers directly participate, input and share accurate data to predict production. In the process, analysis was performed on napa cabbage, which is a vegetable with a large price change compared to production.

• Journal of Bio-Environment Control
• /
• v.31 no.4
• /
• pp.366-375
• /
• 2022

The monitoring of electricity consumption using Internet of Things (IoT) technology is attracting attention as a technology to reduce operation costs of smart farms. In this study, we propose a method to apply a real-time electrical consumption monitoring system (the e-Gauge system) and utilization of the collected data real-time while a melon-producing smart farm is in operation. For this purpose, the electrical consumption data for the individual smart-farm facilities such as boilers, nutrient distribution systems, automatic controllers, circulation fans, boiler controllers, and other IoT-related utilities were collected during three months of melon cultivation period. By using the monitoring results, the electrical energy consumption pattern was analyzed as an example, and necessary considerations needed to optimally utilize the measurement data were suggested. This paper will be useful in lowering the technological implementation barriers for new researchers to build a electrical consumption monitoring system and reducing trial and errors in the usage of the generated data.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.64 no.5
• /
• pp.27-39
• /
• 2022

The smart farm is recognized as a solution for future farmers having positive effects on the sustainability of the poultry industry. Intelligent microclimate control can be a key technology for broiler production which is extremely vulnerable to abnormal indoor air temperatures. Furthermore, better control of indoor microclimate can be achieved by accurate prediction of indoor air temperature. This study developed predictive models for internal air temperature in a mechanically-ventilated broiler house based on the data measured during three rearing periods, which were different in seasonal climate and ventilation operation. Three machine learning models and a mechanistic model based on thermal energy balance were used for the prediction. The results indicated that the all models gave good predictions for 1-minute future air temperature showing the coefficient of determination greater than 0.99 and the root-mean-square-error smaller than 0.306℃. However, for 1-hour future air temperature, only the mechanistic model showed good accuracy with the coefficient of determination of 0.934 and the root-mean-square-error of 0.841℃. Since the mechanistic model was based on the mathematical descriptions of the heat transfer processes that occurred in the broiler house, it showed better prediction performances compared to the black-box machine learning models. Therefore, it was proven to be useful for intelligent microclimate control which would be developed in future studies.