• Journal of Korean Society of Occupational and Environmental Hygiene
• /
• v.25 no.3
• /
• pp.380-391
• /
• 2015

Objectives: The objective of this study is to assess airborne particulate matter pollution and its effect on health of residents living near Ansim Briquette Fuel Complex and its vicinities. Also, this study measured and analyzed the concentration of TSP, $PM_{10}$, $PM_{2.5}$, and heavy metals which influences on the environmental and respiratory disease in Ansim Briquette Fuel Complex, Daegu, Korea. Methods: In this study, we analyzed various environmental pollutants such as particulate matter and heavy metals from Ansim Briquette Fuel Complex that adversely affected local residents's health. In particular, we verified the concentration distribution and characteristics of exposure for TSP, $PM_{10}$, and $PM_{2.5}$ among particulate matters, and heavy metals(Cd, Cr, Cu, Mn, Ni, Pb, Fe, Zn, and Mg). In that regard, the official test method on air pollution in Korea for analysis of particulate matter and heavy metal in atmosphere were conducted. The large capacity air sampling method by the official test method on air pollution in Korea were applied for sampling of heavy metals in atmosphere. In addition, we evaluated the concentration of seasonal environmental pollutants for each point of residence in Ansim Briquette Fuel Complex and surrounding area. The sampling measured periods for air pollutants were from August 11, 2013 to February 21, 2014. Furthermore, we measured and analyzed the seasonal concentrations(summer, autumn and winter). Results: The average concentration for TSP, $PM_{10}$, and $PM_{2.5}$ by direct influence area at Ansim Briquette Fuel Complex were 1.7, 1.4 and 1.9 times higher than reference region. In analysis results of seasonal concentrations for particulate matter in four direct influence and reference area, concentration levels for winter were generally somewhat higher than concentrations for summer and autumn. The average concentrations for Cd, Cr, Mn, Ni, Pb, Fe, and Zn in direct influence area at Ansim Briquette Fuel Complex were $0.0008{\pm}0.0004{\mu}g/Sm^3$, $0.0141{\pm}0.0163{\mu}g/Sm^3$, $0.0248{\pm}0.0059{\mu}g/Sm^3$, $0.0026{\pm}0.0011{\mu}g/Sm^3$, $0.0272{\pm}0.0084{\mu}g/Sm^3$, $0.4855{\pm}0.1862{\mu}g/Sm^3$, and $0.3068{\pm}0.0631{\mu}g/Sm^3$, respectively. In particularly, the average concentrations for Cd, Cr, Mn, Ni, Pb, Fe, and Zn in direct influence area at Ansim Briquette Fuel Complex were 1.9, 3.6, 2.1, 1.9, 1.4, 2.6, and 1.2 times higher than reference area, respectively. The continuous monitoring and management were required for some heavy metals such as Cr and Ni. Moreover, the average concentration in winter for particulate matter in direct influence area at Ansim Briquette Fuel Complex were generally higher than concentrations in summer and autumn. Also, average concentrations for TSP, $PM_{10}$, and $PM_{2.5}$ were from 1.5 to 2.0 times, 1.2 to 1.8 times, and 1.1 to 2.3 times higher than reference area, respectively. In results for seasonal atmospheric environment, TSP, $PM_{10}$, $PM_{2.5}$, and heavy metal concentrations in direct influence area were higher than reference area. Especially, the concentrations in C station were a high level in comparison with other area. Conclusions: In the results, some particulate matters and heavy metals were relatively high concentration, in order to understand the environmental pollution level and health effect in surrounding area at Ansim Briquette Fuel Complex. The concentration of some heavy metals emitted from direct influence area at Ansim Briquette Fuel Complex were relatively higher than reference area. In particular, average concentration for heavy metals in this study were higher than average concentrations in air quality monitoring station for heavy metal for 7 years in Deagu metropolitan region. Especially, the residents near Ansim Briquette Fuel Complex may be exposed to the pollutants(TSP, $PM_{10}$, $PM_{2.5}$, and heavy metals, etc) emitted from the factories in Ansim Briquette Fuel Complex.

• Journal of Intelligence and Information Systems
• /
• v.26 no.2
• /
• pp.105-129
• /
• 2020

This study uses corporate data from 2012 to 2018 when K-IFRS was applied in earnest to predict default risks. The data used in the analysis totaled 10,545 rows, consisting of 160 columns including 38 in the statement of financial position, 26 in the statement of comprehensive income, 11 in the statement of cash flows, and 76 in the index of financial ratios. Unlike most previous prior studies used the default event as the basis for learning about default risk, this study calculated default risk using the market capitalization and stock price volatility of each company based on the Merton model. Through this, it was able to solve the problem of data imbalance due to the scarcity of default events, which had been pointed out as the limitation of the existing methodology, and the problem of reflecting the difference in default risk that exists within ordinary companies. Because learning was conducted only by using corporate information available to unlisted companies, default risks of unlisted companies without stock price information can be appropriately derived. Through this, it can provide stable default risk assessment services to unlisted companies that are difficult to determine proper default risk with traditional credit rating models such as small and medium-sized companies and startups. Although there has been an active study of predicting corporate default risks using machine learning recently, model bias issues exist because most studies are making predictions based on a single model. Stable and reliable valuation methodology is required for the calculation of default risk, given that the entity's default risk information is very widely utilized in the market and the sensitivity to the difference in default risk is high. Also, Strict standards are also required for methods of calculation. The credit rating method stipulated by the Financial Services Commission in the Financial Investment Regulations calls for the preparation of evaluation methods, including verification of the adequacy of evaluation methods, in consideration of past statistical data and experiences on credit ratings and changes in future market conditions. This study allowed the reduction of individual models' bias by utilizing stacking ensemble techniques that synthesize various machine learning models. This allows us to capture complex nonlinear relationships between default risk and various corporate information and maximize the advantages of machine learning-based default risk prediction models that take less time to calculate. To calculate forecasts by sub model to be used as input data for the Stacking Ensemble model, training data were divided into seven pieces, and sub-models were trained in a divided set to produce forecasts. To compare the predictive power of the Stacking Ensemble model, Random Forest, MLP, and CNN models were trained with full training data, then the predictive power of each model was verified on the test set. The analysis showed that the Stacking Ensemble model exceeded the predictive power of the Random Forest model, which had the best performance on a single model. Next, to check for statistically significant differences between the Stacking Ensemble model and the forecasts for each individual model, the Pair between the Stacking Ensemble model and each individual model was constructed. Because the results of the Shapiro-wilk normality test also showed that all Pair did not follow normality, Using the nonparametric method wilcoxon rank sum test, we checked whether the two model forecasts that make up the Pair showed statistically significant differences. The analysis showed that the forecasts of the Staging Ensemble model showed statistically significant differences from those of the MLP model and CNN model. In addition, this study can provide a methodology that allows existing credit rating agencies to apply machine learning-based bankruptcy risk prediction methodologies, given that traditional credit rating models can also be reflected as sub-models to calculate the final default probability. Also, the Stacking Ensemble techniques proposed in this study can help design to meet the requirements of the Financial Investment Business Regulations through the combination of various sub-models. We hope that this research will be used as a resource to increase practical use by overcoming and improving the limitations of existing machine learning-based models.

• Korean Journal of Soil Science and Fertilizer
• /
• v.39 no.5
• /
• pp.321-327
• /
• 2006

In Korea, there is a growing competitive for water resources between industrial, domestic and agricultural consumer, and the environment as many other OECD countries. The demand on water use is also affecting aquatic ecosystems particularly where withdrawals are in excess of minimum environmental needs for rivers, lakes and wetland habits. OECD developed three indicators related to water use by the agriculture in above contexts : the first is a water use intensity indicator, which is expressed as the quantity or share of agricultural water use in total national water utilization; the second is a water stress indicator, which is expressed as the proportion of rivers (in length) subject to diversion or regulation for irrigation without reserving a minimum of limiting reference flow; and the third is a water use efficiency indicator designated as the technical and the economic efficiency. These indicators have different meanings in the aspect of water resource conservation and sustainable water use. So, it will be more significant that the indicators should reflect the intrinsic meanings of them. The problem is that the aspect of an overall water flow in the agro-ecosystem and recycling of water use not considered in the assessment of agricultural water use needed for calculation of these water use indicators. Namely, regional or meteorological characteristics and site-specific farming practices were not considered in the calculation of these indicators. In this paper, we tried to calculate water use indicators suggested in OECD and to modify some other indicators considering our situation because water use pattern and water cycling in Korea where paddy rice farming is dominant in the monsoon region are quite different from those of semi-arid regions. In the calculation of water use intensity, we excluded the amount of water restored through the ground from the total agricultural water use because a large amount of water supplied to the farm was discharged into the stream or the ground water. The resultant water use intensity was 22.9% in 2001. As for water stress indicator, Korea has not defined nor monitored reference levels of minimum flow rate for rivers subject to diversion of water for irrigation. So, we calculated the water stress indicator in a different way from OECD method. The water stress indicator was calculated using data on the degree of water storage in agricultural water reservoirs because 87% of water for irrigation was taken from the agricultural water reservoirs. Water use technical efficiency was calculated as the reverse of the ratio of irrigation water to a standard water requirement of the paddy rice. The efficiency in 2001 was better than in 1990 and 1998. As for the economic efficiency for water use, we think that there are a lot of things to be taken into considerations to make a useful indicator to reflect socio-economic values of agricultural products resulted from the water use. Conclusively, site-specific, regional or meteorogical characteristics as in Korea were not considered in the calculation of water use indicators by methods suggested in OECD(Volume 3, 2001). So, it is needed to develop a new indicators for the indicators to be more widely applicable in the world.

• Journal of Preventive Medicine and Public Health
• /
• v.28 no.4 s.51
• /
• pp.809-844
• /
• 1995

The purposes of this study are to define the scope of occupational health management and to classify occupational management by review of related journals from 1945 to 1994 in Korea. The steps of this study were as follows: (1) Search of secondary reference; (2) Collection and review of primary reference; (3) Survey; and (4) Analysis and discussion. The results were as follows ; 1. Most of the respondents majored in occupational health(71.6%), and were working in university (68.3%), males and over the age 40. Seventy percent of the respondents agreed with the idea that classification of occupational health management is necessary, and 10% disagreed. 2. After integration of the idea of respondents, we reclassified the scope of occupational health management. It was defined 3 parts, that is , occupational health system, occupational health service and others (such as assessment, epidemiology, cost-effectiveness analysis and so on). 3. The number of journals on occupational health management was 510. It was sightly increased from 1986 and abruptly increased after 1991. The kinds of journals related to occupational health management were The Korean Journal of Occupational Medicine(18.2%), Several Kinds of Medical Colloge Journal(17.0%), The Korean Journal Occupational Health(15.1%), The Korean Journal of Preventive Medicine(15.1%) and others(34.6%). As for the contents, the number of journals on occupational health management systems was 33(6.5%) and occupational health services 477(93.5%). Of the journals on occupational health management systems, the number of journals on the occupational health resource system was 15(45.5%), occupational finance system 8(24.2%), occupational health management system 6(18.2%), occupational organization 3(9.1%) and occupational health delivery system 1 (3.0%). Of the journals on occupational health services, the number of journals on disease management was 269(57.2%), health management 116(24.7%), working environmental management 85(18.1%). As for the subjects, the number of journals on general workers was 185(71.1%), followed by women worker, white coiler workers and so on. 4. Respondents made occupational health service(such as health management, working environmental management and health education) the first priority of occupational health management. Tied for the second are quality analysis(such as education, training and job contents of occupational health manager) and occupational health systems(such as the recommendation of systems of occupational and general disease and occupational health organization). 5. Thirty seven respondents suggested 48 ideas about the future research of occupational health management. The results were as follows: (1) Study of occupational health service 40.5%; (2) Study of organization system 27.1%; (3) Study of occupational health system (e.g. information network) 8.3%; (4) Study of working condition 6.2%; and (5) Study of occupational health service analysis 4.2%.