• Journal of Digital Convergence
• /
• v.20 no.5
• /
• pp.39-46
• /
• 2022

As the link between traffic accidents and social and economic losses has been confirmed, there is a growing interest in developing safety policies based on crash data and a need for countermeasures to reduce severe crash outcomes such as severe injuries and fatalities. In this study, we select Daejeon city where the relative proportion of fatal crashes is high, as a case study region and focus on the severity of pedestrian crashes. After a series of data manipulation process, we run machine learning algorithms for the optimal model selection and variable identification. Of nine algorithms applied, AdaBoost and Random Forest (ensemble based ones) outperform others in terms of performance metrics. Based on the results, we identify major influential factors (i.e., the age of pedestrian as 70s or 20s, pedestrian crossing) on pedestrian crashes in Daejeon, and suggest them as measures for reducing severe outcomes.

• Journal of Industrial Convergence
• /
• v.21 no.7
• /
• pp.9-17
• /
• 2023

This study was conducted to explore the factors that affect youth life satisfaction in order to find ways to increase their life satisfaction. For this purpose, we utilized data from the National Youth Policy Institute's '2021 Youth Socio-Economic Survey' to study 2,041 youth aged 18-34 as of 2021. The randomForest method was applied to explore various variables that affect youth life satisfaction. A total of 21 variables were analyzed, including demographic and socio-demographic factors and psychological and emotional factors.The results of exploring the variables affecting youth life satisfaction using randomForest are as follows. First, all 21 predictors were found to have an impact on young adults' life satisfaction. Second, the most significant impact on youth life satisfaction was found to be 'work values'. Third, it can be seen that young people's perceptions of society, such as 'political effectiveness' and 'perception of older generation', are also variables that affect youth life satisfaction. Based on these findings, the variables affecting youth life satisfaction are explained and discussion points are presented.

• Journal of Korean Society of Forest Science
• /
• v.99 no.4
• /
• pp.611-617
• /
• 2010

The current studies aim is to analyze the production cost of walnut tree cultivation and its object was targeted at walnut tree cultivating household region 163. The analysis is as follows. Our domestic walnut tree cultivating households averagely have cultivated about 0.7ha, and planting number per ha was averagely 204, and it showed that compared to the standard planting number (100), the plantation was done close planted. The most cultivar cultivated according to regions were Chungbuk region: sangchon 65.7%, Chungnam region: kwangduk 68.6%, Jeonbuk region: sangchon 98.0%, Gyeongbuk region: daeboo 61.2%. The production cost for cultivating walnuts can be classified into the followings; management cost(4436 thousand won/ha) such as manufacturing cost(292 thousand won/ha), intermediate material cost(3682 thousand won/ha), rent(103 thousand won/ha), employment cost(653 thousand won/ha) etc, and self-serviced expenses such as self-laboring cost(5,834 thousand won/ha), land security cost(490 thousand won/ha), fixed capital cost(834 thousand won/ha), circulating capital cost(234 thousand won/ha) etc. 11,820 thousand won were invested for the production cost of walnut and it made 11,586 thousand won/ha(rate of investment 72.3%) profit, and the net income was 4,196 thousand won/ha(net income rate 26.2%), showing high amount of income. The manufactured walnuts were marketed in Nong-hyup 39.8%, wholesalers 20.8%, dealers 19.8% and recently, as the amount of goods marketed directly to consumers themselves have increased, the income has reached up to 18.9%. At the basis of making most of idle soil, walnut tree's cultivated regions are fairly small, and due to the characteristics of sideline management, it has its limits in searching for production policy locally and promotion strategy of industries. Therefore, if the basic database can be established, subjected only to full-time cultivating households, then not only would the differences between the imported walnuts be reinforced, it would also be possible to transfer into the new and improved distribution system. Furthermore, through establishment of the database, it can be anticipated that it would contribute greatly in the increase of the household income.

• Journal of Korean Society of Forest Science
• /
• v.61 no.1
• /
• pp.37-44
• /
• 1983

This study was to estimate total annual volume growth by the measurement of mean tree growth during the last 10 years. Surveyed Forest stand was the second block (20.80 ha.)of Kyung Hee University Forests located at San 58 and 64, Gaegok-Ri, Gapyung-Yeup, Gapyung-Goon, Kyunggi province in Korea. The stand was mainly composed of uneven-aged Pinus densiflora and the estimation of tree volume was conducted by taking the cores at the D.B.H. of the sample tree which was selected by sub-sampling. The results obtained were as follows; 1) The regression between the diameter (D) and diameter growth ($\hat{I}$) was $\hat{I}=0.5499+0.0101D$. 2) The estimated equation of confidence interval for the diameter growth was $S^2{\hat{I}}=0.00817(0.09538-0.00952D+0.00027D^2$) 3) The equation for estimating tree height (H) from diameter was $H=1.32376D^{0.77958}$ 4) The equation for estimating tree volume from diameter and height $V=0.0000622D^{1.6918}H^{1.1397}$ 5) Total annual tree volume growth was $5.4041m^3/ha$, and ranged from 5.6131 to $5.1984m^3/ha$. 6) Annual growth rate of total tree volume and its error were 8.8% and 3.9%, respectively. The annual volume growth per tree for any districts can be estimated by this method, and the annual volume growth will be successfully predicted. Because of poor forest growing stock in Korea, annual amount of allowable cut should not exceed annual tree volume growth for better forest management. Accordingly, annual amount of allowable cut should be either equal to or less than annual tree volume growth for the balanced establishment between timber supply and demand in Korea. Demand shortage will be substituted with imported timber. Such plans enable Korean Government to develop a better policy of forest resources management.

• Journal of Environmental Impact Assessment
• /
• v.22 no.6
• /
• pp.649-657
• /
• 2013

UNFCCC(United Nations Framework Convention on Climate Change) agreed with Reducing emissions from deforestation and forest degradation(REDD). It is necessary to develop the method of REDD suitability assessment in national scale. Existing researches suggested projection methods of deforestation area by many deforestation factors, but the causes of deforestation were different by regions. Therefore, in this study, REDD suitability in Kon Tum province in Vietnam was analyzed by several significant deforestation factors. REDD suitability value was computed using the Fuzzy set. As a result, all deforestation factors related to deforestation area and the REDD suitability value was the highest in Sa Thay district, Dak Glei district, Kon Plong district and Dak Ha district. These provinces have high biodiversity, on the other hand deforestation problem has been occurred.

• Journal of Korean Society for Geospatial Information Science
• /
• v.19 no.4
• /
• pp.81-89
• /
• 2011

Low-carbon Green Growth is highlighted as the main issue from in and outof Korea. Recently Korean government and local goverment constructed a master plan and related database. Considering this as a starting point the carbon gross emission has become an important factor in the city planning and management of local goverment unit. This research was focused on the analysis of carbon gross emission and the environment of carbon occurrence using statistics and digital forest map for the Gyeonggi-do. Further research need to analysis the carbon absorption using satellite image for periodic database. These database will be available basic data for the policy making.

• Journal of Digital Convergence
• /
• v.11 no.7
• /
• pp.67-74
• /
• 2013

The purpose of this paper is to develop strategy for successful ecotourism in Sundarbans, Bangladesh, based on studying and explaining the ecotourism destinations success factors in already developed successful ecotourism mostly in developing countries. This thesis will analyze the economic potentiality of Sundarbans as an ecotourism spots of Bangladesh and its proper utilizations to enhance ecotourism as a profitable approach for economic growth of Bangladesh. The findings of the study are the current condition of Sundarbans and some applicable recommendations according to the needs.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.13 no.6
• /
• pp.49-62
• /
• 2010

This study aims to examine a significant difference in performance of, and attitudes towards, environmental tourism among domestic tourism companies by their types and scale, and to propose a policy direction for a new certification program on environmental tourism. This study conducted a survey with 152 tourism accommodations and 150 travel agencies. As a result, this study found that tourism accommodations and a large scale of companies had participated in environmental management practices more often than travel agencies and a small scale of companies. Also, tourism accommodations were more likely to recognize well a relation between their business and environmental tourism, and were more likely to participate in a new certification program than travel agencies. A large scale of tourism accommodations showed more positive attitudes towards environmental tourism than a small scale of tourism accommodations. On the other hand, all of the travel agencies showed less positive attitudes towards environmental tourism regardless of their size. In conclusion, this study proposed that the government should adopt a different approach to a new certification program according to tourism companies' types and scale, also it should provide a variety of incentives and supports for tourism companies.

• Journal of Environmental Science International
• /
• v.32 no.1
• /
• pp.37-46
• /
• 2023

This study investigated the effect of May 31, 2022 Miryang wildfire on fine particle concentrations in Busan and Gimhae, which are neighboring urban areas. In addition, fine particle characteristics and air pollution concentrations were investigated in Miryang, where haze occurred. The Miryang city wildfire that occurred on May 31, 2022, at 0925 LST, was driven by strong north winds and increased fine particle concentrations in Dongsangdong and Jangyoodong, Gimhae City, which are approximately 35 km to the southeast and south, respectively, of the wildfire occurrence site. Furthermore, the fine particle concentration in Myeongjidong, which is approximately 50 km south-southeast of the wildfire site, exhibited a temporary increase at 1400 LST owing to the effects of wildfire smoke. On the morning of June 1, the day after the fire, the Miryang area had very bad visibility because of the smoke from the fire. Therefore the PM₁₀ and PM_2.5 concentrations in Naeildong, 3 km south of the wildfire site, were 276 ㎍/㎥ and 222 ㎍/㎥, respectively, at 1200 LST. In addition, the gases O₃, CO, and SO₂ showed high concentrations at the time of haze generation. This study provides insights into policy making in response to the rapid increase in fine dust when wildfire occurs near cities.

• International Journal of Advanced Culture Technology
• /
• v.12 no.2
• /
• pp.167-179
• /
• 2024

This study addresses the challenge of objectively evaluating the performance of early-stage startups amidst limited information and uncertainty. Focusing on companies selected by TIPS, a leading private sector-driven startup support policy in Korea, the research develops a new indicator to assess technological efficiency. By analyzing various input and output variables collected from Crunchbase and KIND (Korea Investor's Network for Disclosure System) databases, including technology use metrics, patents, and Crunchbase rankings, the study derives technological efficiency for TIPS-selected startups. A prediction model is then developed utilizing machine learning techniques such as Random Forest and boosting (XGBoost) to classify startups into efficiency percentiles (10th, 30th, and 50th). The results indicate that prediction accuracy improves with higher percentiles based on the technical efficiency index, providing valuable insights for evaluating and predicting startup performance in early markets characterized by information scarcity and uncertainty. Future research directions should focus on assessing growth potential and sustainability using the developed classification and prediction models, aiding investors in making data-driven investment decisions and contributing to the development of the early startup ecosystem.