• Korean Journal of Environment and Ecology
• /
• v.29 no.3
• /
• pp.353-367
• /
• 2015

The goal of this study is to analyze the feedback structure of habitat changes of the Whooper Swan in Eulsukdo using system thinking to suggest a management plan for ecosystem health. Using the causal loop diagrams of population changes between Whooper Swan and other bird species in Eulsukdo, we found that the environmental changes in the roosting and foraging area affect the Whooper Swan's population. The causal loop diagrams of the Whooper Swan's roosting area indicated that the environmental changes (e.g., water level, noise, bird watching, and other experience activities) may influence their population density variation. In addition, the casual loop diagrams of the Whooper Swan's foraging area showed that the Whooper Swan's population was affected by various variables that included area factors such as surface area of freshwater, frozen water, salinity, and density of Scirpus planiculmis. Furthermore, through the integrated causal loop diagram, cumulative discharge of Nakdong estuary weir and building activities were identified as the variables that affect the population of the Whooper Swan. Thus, we selected this area as the strategic point to establish a management plan for the Whooper Swan's habitat. The results of this study will help in decision making of a long-term management plan for sustaining the environmental health of the ecosystem in Eulsukdo.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.44 no.3
• /
• pp.65-78
• /
• 2016

LID(Low-Impact Development) has received a great deal of attention in the field of urban water management. The spread of LID technologies as a natural drainage system has led to a rise in consideration of the applicability of policy in Korea. In this respect, the purpose of this study is to analyze experts' perception about utilization, applicability of policy, and improvements of LID by using Q-methodology. The sample included 31 experts who were government employees, landscape architects, researchers, and professors related to LID. All participants completed a 28-statement Q-sort task. Data was analyzed by using QUANL computer software. As a result of this study, four distinct experts' perceptions about LID are identified: Policy Enforcement Oriented Type, Expert Understanding Oriented Type, Manual Oriented Type, and Effectiveness Oriented Type. This study suggested appropriate directions related to LID technologies, and it is helpful to apply the domestic type's LID and increase the efficiency of LID in Korea. However, this study has a limit in which the viewpoint of the researcher intervenes: a complementary searcher is needed to verify the validity by type in policy decision-making.

• Journal of Navigation and Port Research
• /
• v.45 no.1
• /
• pp.9-15
• /
• 2021

According to IMO, MASS is defined as a vessel operated at various levels independent of human interference. The safety navigation support service for MASS is designed to improve the safety and efficiency of MASS by developing public services on shore for ship arrivals/departures and for cargo handling. The safety navigation support service consists of a total of six types of services: autonomous operation, berthing/unberthing/mooring, cargo handling and ship arrival/departure service, PSC inspection, condition monitoring, and accident response support services. In order to support accident response service, the relative importance of a bridge navigational equipment was assessed by stratifying the navigation system to provide safe and efficient support services by objective judgment through specific and quantitative methods using AHP, one of decision-making methods used by an expert group. The survey was conducted by dividing the bridge navigational equipment into depth, location, and speed information. As a result of applying the AHP method, the importance of depth, location, and speed information was assessed. The relative importance of each equipment for providing location information was also assessed in order of Radar, DGPS, ECDIS, Gyro compass, Autopilot, and AIS. This was similar to survey results on the utilization of each operator's preference and its impact on marine accidents.

• Journal of Navigation and Port Research
• /
• v.43 no.1
• /
• pp.72-78
• /
• 2019

The second-hand ship market provides immediate access to the freight market for shipping investors. When introducing second-hand vessels, the precise estimate of the price is crucial to the decision-making process because it directly affects the burden of capital cost to investors in the future. Previous studies on the second-hand market have mainly focused on the market efficiency. The number of papers on the estimation of second-hand vessel values is very limited. This study proposes an artificial neural network model that has not been attempted in previous studies. Six factors, freight, new-building price, orderbook, scrap price, age and vessel size, that affect the second-hand ship price were identified through literature review. The employed data is 366 real trading records of Panamax second-hand vessels reported to Clarkson between January 2016 and December 2018. Statistical filtering was carried out through correlation analysis and stepwise regression analysis, and three parameters, which are freight, age and size, were selected. Ten-fold cross validation was used to estimate the hyper-parameters of the artificial neural network model. The result of this study confirmed that the performance of the artificial neural network model is better than that of simple stepwise regression analysis. The application of the statistical verification process and artificial neural network model differentiates this paper from others. In addition, it is expected that a scientific model that satisfies both statistical rationality and accuracy of the results will make a contribution to real-life practices.

• Journal of Wetlands Research
• /
• v.15 no.3
• /
• pp.367-380
• /
• 2013

In this study, sub-indicators, and thematic mid-indexes to evaluate the water use characteristics were selected through historical data analysis and factor analysis, and consisted of the subject approach framework. And the integrated index was developed to evaluate water use characteristics of the watershed. Using developed index, the water use characteristics were assessed for 812 standard basins with the exception for North Korea using data of 1990 to 2007 from the relevant agencies. A sensitivity analysis is conducted for this study to determine the proper way through various normalization and weighting methods. To increase the objectivity of developed index, the history of the damage indicators are excluded in the analysis. In addition, in order to ensure its reliability, results from index with and without consideration of the damage history were compared. Also, the index is also applied to real data for 2008 Gangwon region to verify its field applicability. Through the validation process this index confirmed the adequacy for the indicators selection and calculation method. The results of this study were analyzed based on the spatial and time vulnerability of the basin's water use, which can be applied to various parts such as priority decision-making for water business or policy, mitigations for the vulnerable components of the basin, and supporting measures to establishment by providing relevant information about it.

• Journal of Korean Society of Forest Science
• /
• v.111 no.1
• /
• pp.186-200
• /
• 2022

The purpose of this study was to provide the basic data necessary for stakeholders to establish and promote policies related to the national forest trail. Awareness analysis was conducted on 800 visitors to the national forest trail, specifically to the Jirisan trail and Daegwallyeong forest trail, as well as 1,200 members of the public. Awareness of the national forest trail was low and at a similar level for both visitors and the general public; however, compared with the general public, the visitors had a higher need for the national forest trail system and were willing to visit and recommend the trail. The most common answers in response to the purpose of visit, reason for choosing the national trail, matters of interest, problems, necessary regulation, and role expectations were similar among the visitors and general public. Based on gender and age, there was a significant difference in the matters of interest and desired activity, but "scenery" was the most crucial factor. Therefore, after a comprehensive survey on the major view points, given that "scenery" was identified as an attractor, a system should be developed to identify and provide the information desired by visitors and the general public. These results are expected to be employed as basic data for stakeholders in decision making related to the national forest trail.

• Journal of Digital Convergence
• /
• v.17 no.3
• /
• pp.73-78
• /
• 2019

Recently, there is a need to introduce a Korean-style restriction sandbox system that exempts or suspends existing regulations so that new products or services based on new technologies can be commercialized without restrictions. In response, the government reorganized the relevant statutes to promptly check regulations centering on four fields, including industrial convergence, ICT, FinTech, and regional innovation growth, and to allow experimental, proof and market releases by setting certain conditions(zone, period, scale, etc.). However, despite the same regulatory sandbox application, depending on the nature of the field applied, differences in application subject, whether application of regulatory specifics, system of push ahead decision-making and whether support of financial and taxation are shown. This research is intended to present efficient operation measures for successful settling of Korean-style regulation sandboxes by comparing and analyzing, centering on the Industrial Fusion Promotion Act in the Industrial Convergence Field, ICT field's Information and Communication Convergence Act, FinTech field's Financial Innovation Act and Regional Special Zone Act in the Regional Innovation and Growth Sector.

• Journal of Intelligence and Information Systems
• /
• v.29 no.2
• /
• pp.85-100
• /
• 2023

Corporate ESG performance (environmental, social, and corporate governance) reflecting a company's strategic sustainability has emerged as one of the main factors in today's investment decisions. The traditional ESG performance rating process is largely performed in a qualitative and subjective manner based on the institution-specific criteria, entailing limitations in reliability, predictability, and timeliness when making investment decisions. This study attempted to predict the corporate ESG rating through automated machine learning based on quantitative and disclosed corporate financial information. Using 12 types (21,360 cases) of market-disclosed financial information and 1,780 ESG measures available through the Korea Institute of Corporate Governance and Sustainability during 2019 to 2021, we suggested a deep neural network prediction model. Our model yielded about 86% of accurate classification performance in predicting ESG rating, showing better performance than other comparative models. This study contributed the literature in a way that the model achieved relatively accurate ESG rating predictions through an automated process using quantitative and publicly available corporate financial information. In terms of practical implications, the general investors can benefit from the prediction accuracy and time efficiency of our proposed model with nominal cost. In addition, this study can be expanded by accumulating more Korean and international data and by developing a more robust and complex model in the future.

• Journal of the Korea Convergence Society
• /
• v.12 no.1
• /
• pp.99-104
• /
• 2021

In this paper, we propose health risk management using feature extraction and cluster analysis considering time flow. The proposed method proceeds in three steps. The first is the pre-processing and feature extraction step. It collects user's lifelog using a wearable device, removes incomplete data, errors, noise, and contradictory data, and processes missing values. Then, for feature extraction, important variables are selected through principal component analysis, and data similar to the relationship between the data are classified through correlation coefficient and covariance. In order to analyze the features extracted from the lifelog, dynamic clustering is performed through the K-means algorithm in consideration of the passage of time. The new data is clustered through the similarity distance measurement method based on the increment of the sum of squared errors. Next is to extract information about the cluster by considering the passage of time. Therefore, using the health decision-making system through feature clusters, risks able to managed through factors such as physical characteristics, lifestyle habits, disease status, health care event occurrence risk, and predictability. The performance evaluation compares the proposed method using Precision, Recall, and F-measure with the fuzzy and kernel-based clustering. As a result of the evaluation, the proposed method is excellently evaluated. Therefore, through the proposed method, it is possible to accurately predict and appropriately manage the user's potential health risk by using the similarity with the patient.

• Journal of Intelligence and Information Systems
• /
• v.17 no.3
• /
• pp.25-41
• /
• 2011

Recently, support vector machines (SVMs) are being recognized as competitive tools as compared with other data mining techniques for solving pattern recognition or classification decision problems. Furthermore, many researches, in particular, have proved them more powerful than traditional artificial neural networks (ANNs) (Amendolia et al., 2003; Huang et al., 2004, Huang et al., 2005; Tay and Cao, 2001; Min and Lee, 2005; Shin et al., 2005; Kim, 2003).The classification decision, such as a binary or multi-class decision problem, used by any classifier, i.e. data mining techniques is so cost-sensitive particularly in financial classification problems such as the credit ratings that if the credit ratings are misclassified, a terrible economic loss for investors or financial decision makers may happen. Therefore, it is necessary to convert the outputs of the classifier into wellcalibrated posterior probabilities-based multiclass credit ratings according to the bankruptcy probabilities. However, SVMs basically do not provide such probabilities. So it required to use any method to create the probabilities (Platt, 1999; Drish, 2001). This paper applied AdaBoost algorithm-based support vector machines (SVMs) into a bankruptcy prediction as a binary classification problem for the IT companies in Korea and then performed the multi-class credit ratings of the companies by making a normal distribution shape of posterior bankruptcy probabilities from the loss functions extracted from the SVMs. Our proposed approach also showed that their methods can minimize the misclassification problems by adjusting the credit grade interval ranges on condition that each credit grade for credit loan borrowers has its own credit risk, i.e. bankruptcy probability.