• KIPS Transactions on Software and Data Engineering
• /
• v.8 no.5
• /
• pp.193-204
• /
• 2019

The explosion of data due to the improvement of sensor technology and computing performance has become the basis for analyzing the situation in the industrial fields, and various attempts to detect events based on such data are increasing recently. In particular, sound signals collected from sensors are used as important information to classify events in various application fields as an advantage of efficiently collecting field information at a relatively low cost. However, the performance of sound-event classification in the field cannot be guaranteed if noise can not be removed. That is, in order to implement a system that can be practically applied, robust performance should be guaranteed even in various noise conditions. In this study, we propose a system that can classify the sound event after generating the enhanced sound signal based on the deep learning algorithm. Especially, to remove noise from the sound signal itself, the enhanced sound data against the noise is generated using SEGAN applied to the GAN with a VAE technique. Then, an end-to-end based sound-event classification system is designed to classify the sound events using the enhanced sound signal as input data of CNN structure without a data conversion process. The performance of the proposed method was verified experimentally using sound data obtained from the industrial field, and the f1 score of 99.29% (railway industry) and 97.80% (livestock industry) was confirmed.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2019.05a
• /
• pp.32-35
• /
• 2019

One of the major problems with the livestock industry is that in the summer, livestock will die from heat waves or infectious diseases. Under these circumstances, what livestock need is a proper indoor temperature and a regular sterilization system. Therefore, in this study, we developed a system that automatically controls the power of the fan according to the temperature inside the shaft, and a function that provides feed and sterilization on a regular basis, so that we could manage the toast efficiently. It also proposed the ability to automatically control the power of the fan, to display the temperature inside the shaft to mobile applications, and to provide food and sterilization. First, the function of controlling the power of the fan automatically turns the fan on when the temperature inside the shaft rises above a certain level. Conversely, if the temperature inside the shaft falls below a certain level, turn off the fan. Second, the function of the mobile application is to check the temperature inside the shaft. The third feeding function is periodically fed using a servo motor, and the feeding provided is delivered to livestock through a conveyor belt. Finally, the sterilization function is a function to sterilize livestock periodically using DC motor pump. The intelligent congratulatory functions proposed in this study may contribute to the health of livestock.

• Clean Technology
• /
• v.27 no.1
• /
• pp.55-60
• /
• 2021

Antibiotics are compounds broadly used to treat patients with infectious diseases and to enhance productivity in agriculture, fisheries, and livestock industries. However, due to the overuse of antibiotics and their low biodegradability, a substantial amount of antibiotics is leaking into the sewer, subsequently resulting in pollution and the emergence of antibiotic-resistant bacteria. This study explores biodegradable serum albumin's potential as an adsorbent to remove antibiotics from water. Serum albumin is a natural blood protein that transports various metabolites and hormones to all tissues' extravascular spaces. While serum albumin is highly water-soluble, it has intrinsic binding sites which readily accommodate ionic, hydrophilic, or hydrophobic molecules, rendering it a good building block for a nano-adsorbent. To induce coacervation, a desolvating agent, ethanol, was added dropwise into the aqueous albumin solution, resulting in dehydration and liquid-liquid phase separation of albumins into albumin nanoparticles within a size range of 150 ~ 170 nm. The addition of glutaraldehyde as a cross-linker improved the size stability and homogeneity of albumin nanoparticles. Adsorption of amoxicillin antibiotics on albumin nanoparticles was dependent upon glutaraldehyde concentration used in desolvation and pH during adsorption. The maximum adsorption capacity measured by spectrophotometry was found to be 12.4 micrograms of amoxicillin per milligram of albumin nanoparticle. These results demonstrate serum albumin's potential as a building block for fabricating a natural nano-adsorbent to remove antibiotics from water.

• The Journal of the Convergence on Culture Technology
• /
• v.8 no.2
• /
• pp.385-391
• /
• 2022

Quality evaluation of beef carcasses is an important issue in the livestock industry. Recently, through the AI monitor system based on artificial intelligence, the quality manager can receive help in making accurate decisions based on the analysis of beef carcass images or result information. This artificial intelligence dataset is an important factor in judging performance. Existing datasets may have different surface orientation or resolution. In this paper, we proposed a two-stage classification model that can efficiently manage the grades of beef carcass image using deep learning. And to overcome the problem of the various conditions of the image, a new dataset of 1,300 images was constructed. The recognition rate of deep network for 5-grade classification using the new dataset was 72.5%. Two-stage evaluation is a method to increase reliability by taking advantage of the large difference between grades 1++, 1+, and grades 1 and 2 and 3. With two experiments using the proposed two stage model, the recognition rates of 73.7% and 77.2% were obtained. As this, The proposed method will be an efficient method if we have a dataset with 100% recognition rate in the first stage.

• Journal of Korean Society of Forest Science
• /
• v.111 no.4
• /
• pp.667-675
• /
• 2022

Agroforestry is an ecological and economic land-use system that enables sustainable agriculture by combining forestry, agriculture, and livestock industries. North Korea chose agroforestry as a strategy for the restoration of sloping land and deforested land. Agroforestry was proposed for the inter-Korean forest cooperation subcommittee meeting and is currently highlighting carbon removal and promoting the '2050 Carbon Neutral Strategy' and 'Korea Peninsula Green Détente.' The study area, Suan-gun, Hwanghaebuk-do, is a constant deforestation monitoring area and a pilot site for management by the International Center for Research in Agroforestry. The requirements for agroforestry were analyzed through literature analysis. The agroforestry site-suitability map was visualized by applying GIS overlap analysis. Approximately 8,839 ha of sloping area was selected as suitable for agroforestry management, which is about 15% of Suan. We compared the map with Google Earth images and visually detected the land use status, such as agroforestry in Suan, to verify the results. As a future study, we will consider both natural-environment and socioeconomic factors and evaluate the relative importance of the factors to produce a high-accuracy agroforestry sitesuitability map at the national scale with the goal of producing basic data for the inter-Korea forest cooperation policy for long-term goals.

• Journal of the Korea Organic Resources Recycling Association
• /
• v.30 no.2
• /
• pp.29-42
• /
• 2022

The government promotes the 2050 carbon-neutral policy. Therefore, the concern to convert livestock manure into energy is increasing for the reduction of greenhouse gases generated in the livestock industry sector. In this study, the economic feasibility of the livestock manure solid fuel power generation facility, which is a major consumer of livestock manure solid fuel, was assessed to expand the demand for livestock manure solid fuel. The production cost of livestock manure solid fuel showed the lowest production cost of 97.4 thousand won/ton when dried using solid fuel at a 200 ton/day scale bio-drying facility. The livestock manure solid fuel power generation facility showed economic feasibility at a REC weight of 1.5 in the case of the bio-drying facility, so it was necessary to set a REC weight of 1.5 or more to expand the demand for livestock manure solid fuel. The conversion of livestock manure into solid fuel has various environmental benefits, such as the reduction of greenhouse gases and the effect of reducing non-point pollutants in the water system. Therefore, in order to expand livestock manure solid fuel production facility, it was required to review the feasibility including various environmental benefits.

• Convergence Security Journal
• /
• v.22 no.5
• /
• pp.69-80
• /
• 2022

Now that climate change and food resource security are becoming issues around the world, smart farms are emerging as an alternative to solve them. In addition, changes in the production environment in the primary industry are a major concern for people engaged in all primary industries (agriculture, livestock, fishery), and the resulting food shortage problem is an important problem that we all need to solve. In order to solve this problem, in the primary industry, efforts are made to solve the food shortage problem through productivity improvement by introducing smart farms using the 4th industrial revolution such as ICT and BT and IoT big data and artificial intelligence technologies. This is done through the public and private sectors.This paper intends to consider the minimum requirements for the smart farm data collection system for the development and utilization of smart farms, the establishment of a sustainable agricultural management system, the sequential system construction method, and the purposeful, efficient and usable data collection system. In particular, we analyze and improve the problems of the data collection system for building a Korean smart farm standard model, which is facing limitations, based on in-depth investigations in the field of livestock and livestock (pig farming) and analysis of various cases, to establish an efficient and usable big data collection system. The goal is to propose a method for collecting big data.

• Korean Journal of Poultry Science
• /
• v.50 no.2
• /
• pp.81-90
• /
• 2023

Animal welfare was introduced relatively late to Korea in comparison with Western countries. Nonetheless, the Korean government has continuously improved animal welfare-friendly regulations as policy instruments. Given the current situation, it is predicted that spontaneous settlement of the animal welfare policies will be difficult and may cause conflict in the farm animal industry. To identify and categorize conflicts caused by animal-welfare-related policies in the last five years, we investigated the awareness of animal welfare among Korean hen farms and the level of compliance with the animal welfare regulations. We collected a sample of 53 egg-laying chicken farm operators (e.g., owners or head managers) was collected through the on-site survey (90% confidence level (Z-score: 1.65) and 10.18% tolerance, based on a number of 797 egg-laying farms in 2020). Ethical conflicts on the farms were categorized into three different types according to the hen farm's ethical awareness level: passive, moderate, and active. Additionally, we investigated the correlation between compliance with regulations and ethical consideration. This study confirmed that compliance with animal welfare-related regulations significantly correlated to the level of ethical consideration of farm operators. Interestingly, we also observed that farm operators did not comply with the regulation despite their high level of awareness of animal welfare. This conflict implies contradiction and unresolved ethical dilemmas. Therefore, this study argues that the policies cause conflict in the field despite the certain level of effectiveness on animal welfare regulations.

• Journal of the Korean Society of International Agriculture
• /
• v.23 no.5
• /
• pp.513-519
• /
• 2011

In recent, the cultivation of maize in the world is being increased as a feed for the animal due to the increase of the large amount of meat consumption. However, reduction of supply for the feeding maize by the natural disaster such as drought, flooding, and demanding materials for bioenergy are attributed to increase the cereal price of the world that caused for the fluctuation of prices. The research has been done to provide useful information to the Korean agricultural investor regarding the current status of maize production and distribution in Cambodia. The maize cultivation of Cambodia in 2009 presented as a second major crop at the area of 6.8% in the total crop production area, and it continuously increased maize production yearly basis for the internal uses as well as for the exportation. The total amount of production showed by amount of 0.92 million tons due to the increased production of unit area. The yield production of unit area in current shows about 4 tones per hectare. About 90% of total production produced during August to September at wet season, and area of Batambang province produced about 70% of the total production. The production of feeding maize cultivated about 70% of the total cultivation area, and the exportation have done around 60% and remains were consumed as a domestic uses. The prospects of maize production in Cambodia will be increased due to the acceleration of livestock industry as 8.7% of annual growth rate.

• Smart Media Journal
• /
• v.12 no.10
• /
• pp.55-62
• /
• 2023

Innovation and change are occurring rapidly in the agriculture and livestock industry, and new technologies such as smart bams are being introduced, and data that can be used to control equipment is being collected by utilizing various sensors. However, there are various challenges in the operation of bams, and virtual sensor technology is needed to solve these challenges. In this paper, we define various data items and sensor data types used in livestock farms, study cases that utilize virtual sensors in other fields, and implement and design a virtual sensor system for the final smart livestock farm. MBE and EVRMSE were used to evaluate the finalized system and analyze performance indicators. As a result of collecting and managing data using virtual sensors, there was no obvious difference in data values from physical sensors, showing satisfactory results. By utilizing the virtual sensor system in smart livestock farms, innovation and efficiency improvement can be expected in various areas such as livestock operation and livestock health status monitoring. This paper proposes an innovative method of data collection and management by utilizing virtual sensor technology in the field of smart livestock, and has obtained important results in verifying its performance. As a future research task, we would like to explore the connection of digital livestock using virtual sensors.