• Journal of Korea Artificial Intelligence Association
• /
• v.1 no.2
• /
• pp.21-25
• /
• 2023

The purpose of this study was to compare the performance using multiple regression models to predict the energy consumption of steel industry. Specific independent variables were selected in consideration of correlation among various attributes such as CO2 concentration, NSM, Week Status, Day of week, and Load Type, and preprocessing was performed to solve the multicollinearity problem. In data preprocessing, we evaluated linear and nonlinear relationships between each attribute through correlation analysis. In particular, we decided to select variables with high correlation and include appropriate variables in the final model to prevent multicollinearity problems. Among the many regression models learned, Boosted Decision Tree Regression showed the best predictive performance. Ensemble learning in this model was able to effectively learn complex patterns while preventing overfitting by combining multiple decision trees. Consequently, these predictive models are expected to provide important information for improving energy efficiency and management decision-making at steel industry. In the future, we plan to improve the performance of the model by collecting more data and extending variables, and the application of the model considering interactions with external factors will also be considered.

• International Journal of Internet, Broadcasting and Communication
• /
• v.16 no.2
• /
• pp.161-168
• /
• 2024

As the size of big data models grows, distributed training is emerging as an essential element for large-scale machine learning tasks. In this paper, we propose ParamHub for distributed data training. During the training process, this agent utilizes the provided data to adjust various conditions of the model's parameters, such as the model structure, learning algorithm, hyperparameters, and bias, aiming to minimize the error between the model's predictions and the actual values. Furthermore, it operates autonomously, collecting and updating data in a distributed environment, thereby reducing the burden of load balancing that occurs in a centralized system. And Through communication between agents, resource management and learning processes can be coordinated, enabling efficient management of distributed data and resources. This approach enhances the scalability and stability of distributed machine learning systems while providing flexibility to be applied in various learning environments.

• Environmental and Resource Economics Review
• /
• v.30 no.4
• /
• pp.557-579
• /
• 2021

Collective energy is an intermediate stage in energy conversion and has a great influence on the power structure as a distributed power source. However, the problem of the collective energy business has recently emerged due to the worsening profitability of some collective energy operators. This study measured the technical efficiency of major operators through the estimation of the production efficiency of Korean collective energy operators, and based on this, we looked at ways to improve the profit structure of operators. After collecting detailed data from 16 collective energy operators between 2016 and 2019, the production efficiency of operators was estimated using the panel stochastic frontier model. As a result of the estimation, combined steam power operators showed the highest production efficiency and reverse CHP operators showed the lowest efficiency. Furthermore, as a result of examining the factors influencing profitability, it was confirmed that production efficiency has a positive effect on overall profitability. However, businesses with a high proportion of heat production, such as small district electricity operators, profitability was lower. This phenomenon is due to the structural limitations of the current heat sales market. Hence, the adjustment of the heat sales unit price is necessary to improve profitability of collective energy operators.

• Journal of Embryo Transfer
• /
• v.11 no.3
• /
• pp.249-258
• /
• 1996

To improve the efficiency of in vitro production of embryos with follicular oocytes in Korean Native cows, the recovery rates, in vitro maturation, fertilization and development, and the time required for collecting and processing oocytes by aspiration with or without slicing were evaluated comparatively. The ovaries were obtained from a local abattoir and placed in physiological saline at 25~28$^{\circ}C$ and brought to the laboratory within 3 hrs. The oocytes were collected by aspiration of follicles(2~6mm) with or without slicing ovaries after aspiration, and classified into Grade I, Grade II, Denuded, Expanded oocytes by the morphology of cumulus cells attached and the homogeneity of cytoplasmic granules. Also the time required for each step of collecting and processing oocytes were measured. The cumulus cells were removed in some Grade I oocytes to measure their size and nuclear configuration before and after in vitro maturation. The Grade I oocytes were matured in vitro(IVM) for 24 hrs. in TGM-199 supplemented with 35$\mu$g /ml FSH, 10$\mu$g /ml LH, 1 $\mu$g /ml at 39$^{\circ}C$ under 5% C02 in air. They were fertilized in vitro(IVF) by epididymal spermatozoa treated with heparin for 24hrs. and then the zygotes were cocultured in vitro (IVC) with bovine oviductal epithelial cells for 10 days. The results obtained were as follows: The number of oocytes recovered per ovary was averaged 6.6 by aspiration and 11.2 by slicing post aspiration, which summed to 17.8. The number of Grade I oocytes recovered per ovary was averaged 3.1 by aspiration and 3.6 by slicing, which summed to 6.7. The percentage of Grade I to total oocytes recovered was significantly(P<0.05) higher as 48.0 % in aspiration than 31.6% in slicing post aspiration. The time requlred for recovering a Grade I oocyte by aspiration and slicing was 1.1 and 2.5 min, respectively. The mean diameter of Grade I oocytes by aspiration and slicing was similar as 148.7 and 151.5$\mu$m, respectively. The percentage of Metaphase II stage oocytes after IVM for 24 hours was significantly (P

• Korean Journal of Environmental Biology
• /
• v.35 no.4
• /
• pp.640-647
• /
• 2017

The need for an efficient sampling technique to collect aquatic organisms has risen with the increase of interest in rice paddy fields, which have been recognized as important ecosystems supporting biodiversity. In the present study, a submerged funnel trap used with the assistance of attracting agents (fish meal and chemical light) was designed as an easy, objective and quantitative tool for collecting aquatic organisms in the rice paddy fields. The preference for collecting aquatic organisms as a means for attracting agents was analyzed using a generalized linear mixed model. Also, based on the data of previous research, we compared the community composition of the aquatic macroinvertebrates, which were collected using the quadrat method, and newly designed submerged funnel traps, by analyzing non-metric multidimensional scaling. The results showed that the catching efficiency of 18 of the total 65 taxa was affected by the attracting agents. 12 taxa including Pomacea canaliculata, Hippeutis cantori, Austropeplea ollula, Erpobdella lineata, Ostracoda spp. Branchinella kugenumaensis, Hydaticus grammicus, Rhantus pulverosus, Chironomidae spp., Rana nigromaculata, Cobitidae spp. etc., favored fish meal and 6 taxa including Ischnura asiatica, Coenagrionidae spp. Sternolophus rufipes etc., were attracted by chemical light. The submerged funnel trap used as a measurement tool for biodiversity was less applicable than the quadrat method; however, it was more effective for the selective collection of specific taxa. We expect that this newly designed trap can be a simple and quantitative method for collecting aquatic organisms, and could be used for long term and extensive surveys in rice paddy fields in the future.

• Plant Journal
• /
• v.15 no.4
• /
• pp.30-35
• /
• 2019

To meet both increasing social demand for reduction of fine dust and the strengthened air pollutant emission standards, this paper indicated performance enhancement of FGD with structural constraints in 500 MW coal fired thermal power plant's. Through modifying internal facilities for flue gases to make swirl in the absorption tower, it made turbulence and increased the efficiency of material transfer, the reaction area and time with the limestone slurry. Therefore, it could reduce dust and enhance the performance of collecting the SO₂. As a result, desulfurization efficiency was improved from 91.61% to 98.43% and dust removal efficiency was improved from 77.4% to 87.08%. Emission density is 7.85 ppm of SO₂ and 4.67 mg/㎥ of dust. This is a level that satisfies emission limit of 25 ppm of SO₂ and 5 mg/㎥ of dust which are the air pollutant emission standards of 2023. The performance enhancement method of this study is expected to be effectively applied to other coal-fired power plants with similar constraints.

• Proceedings of the Korean Vacuum Society Conference
• /
• 2016.02a
• /
• pp.150-150
• /
• 2016

Mankind is enjoying a great convenience of their life by the rapid growth of secondary industry since the Industrial Revolution and it is possible due to the invention of huge power such as engine. The automobile which plays the important role of industrial development and human movement is powered by the Engine Module, and especially Diesel engine is widely used because of mechanical durability and energy efficiency. The main work mechanism of the Diesel engine is composed of inhalation of the organic material (coal, oil, etc.), combustion, explosion and exhaust Cycle process then the carbon compound emissions during the last exhaust process are essential which is known as the major causes of air pollution issues in recent years. In particular, COx, called carbon oxide compound which is composed of a very small size of the particles from several ten to hundred nano meter and they exist as a suspension in the atmosphere. These Diesel particles can be accumulated at the respiratory organs and cause many serious diseases. In order to compensate for the weak point of such a Diesel Engine, the DPF(Diesel Particulate Filter) post-cleaning equipment has been used and it mainly consists of ceramic materials(SiC, Cordierite etc) because of the necessity for the engine system durability on the exposure of high temperature, high pressure and chemical harsh environmental. Ceramic Material filter, but it remains a lot of problems yet, such as limitations of collecting very small particles below micro size, high cost due to difficulties of manufacturing process and low fuel consumption efficiency due to back pressure increase by the small pore structure. This study is to test the possibility of new structure by direct infiltration of SiC Whisker on Carbon felt as the next generation filter and this new filter is expected to improve the above various problems of the Ceramic DPF currently in use and reduction of the cost simultaneously. In this experiment, non-catalytic VS CVD (Vapor-Solid Chemical Vaporized Deposition) system was adopted to keep high mechanical properties of SiC and MTS (Methyl-Trichloro-Silane) gas used as source and H2 gas used as dilute gas. From this, the suitable whisker growth for high performance filter was observed depending on each deposition conditions change (input gas ratio, temperature, mass flow rate etc.).

• Journal of Korean Society of Occupational and Environmental Hygiene
• /
• v.27 no.4
• /
• pp.291-301
• /
• 2017

Objectives: In order to improve the working environment and solve the complaints, many efforts have been made to remove the odor from the industrial process. There are many disposal methods to remove odor, but there are many disadvantages and inadequate applications. The Purpose of this study was to develop a bag-filer system for odor removal using powder adsorbent. Methods: The bag-filter system is composed of a shear bag filter, an absorbent spraying system and an absorbent circulation system. The spraying absorbent system was connected with the inlet duct of the shear bag filter for inputting adsorbent. And the absorbent circulation system can transport the collecting adsorbent from hoper to the inlet duct of the system. As a result, the adsorbent can remove odor with recycling in the system. Also affective factors like the powdered absorbent combination and injection method was researched for maximization of system efficiency. The study was conducted in two stages. The first step was testing equipment made and the second is to evaluate the efficiency of the odor control by connecting to the actual odor generation process. Results: Both experiment stages showed efficient odor control ability. The adsorption efficiency of the system is demonstrated and the odor was adsorbed well by the powder adsorbent. It is essential to accurately understand the characteristics of the odorous and use the appropriate adsorbent. Although the powder adsorbent was used in the experiment, the problem of scattering did not occur due to the high degree of system sealing. Also the system manufactured in this study was designed to recycle the adsorbent, so adsorbent reuse or batch processing is convenient. Conclusions: The applicability of the system has been proven through this research. Customized systems for industrial process and the appropriate adsorbent base on the characteristics of pollutant generation will show efficient odor collection ability.

• Solar Energy
• /
• v.6 no.2
• /
• pp.3-14
• /
• 1986

It is desirable to collect the solar thermal energy at relatively high temperature in order to minimize the size of thermal storage system and to enlarge the scope of solar thermal energy utilization. In this study, to develop a solar collector that has both advantages of collecting solar thermal energy at high temperature and fixing conveniently the collector system for long term period, a cylindrical parabolique concentrating solar collector (M.C.P.C.S.C) was designed, which has several rows of parabolique reflectors and thin thickness such as the flat-plate solar collector, maintaining the optical form of concentrating solar collector. The thermal performance of the M.C.P.C.S.C. newly designed in this study was analysed theoretically and experimentally. The results are summarized as follows: 1) prediction equation for outlet temperature, $T_o$, of heat transfer fluid and for the thermal efficiency, ${\eta}$, of the collector were derived as; o $$T_o=[C+B1_n(\frac{I_c(t)}{pv^3})]T_i$$ o $${\eta}=\frac{A}{A_c}\dot{m}[(C-1)+B1_n(E{\cdot}di^6\frac{I_c(t)}{\dot{m}^3})]\frac{T_i}{I_c(t)}$$ 2) When the insolation on the tilted solar collector surface, $I_c$, was $900-950W/m^2$ and the heat transfer fluid was not circulated in tubular absorber, the maximum temperature on the absorber surface was $100-118^{\circ}C$, this result suggested that the heat transfer fluid could be heated up to $98-116^{\circ}C$. The maximum temperature on the absorber surface was decreased with the increase of the collector shape factor, $L_p/L_w$ 3) There was a good agreement between the experimental and theoretical value of solar collector efficiency, ${\eta}$, which was proportional to the collector shape factor, $L_p/L_w$ 4) It is desirable to continue the study on the relationship between the collector shape factor, $L_p/L_w$, and the thermal efficiency of solar collector.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.19 no.4
• /
• pp.113-118
• /
• 2019

A solar power plant is a facility that produces electricity. As the risk of fire and electric shock accidents is diversified, the risk of workers, surrounding people, and facilities is increased, preventing safety accidents and promptly responding to safety accidents Is emerging. In light of the necessity of such development, it is necessary to develop a solar power generation management system that can diagnose and maintain the problems of the power generation system in real time by developing technologies for collecting and analyzing the data produced by the solar power generation system As a result, the utilization rate and the maintenance cost can be reduced. In order to do this, it is necessary to accurately predict the solar power generation amount in the present state, to diagnose the abnormality of the current power generation state and to grasp the abnormal position, and to use the model considering economical efficiency when the abnormal position is grasped, And the time and other information should be provided.