• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.35 no.6
• /
• pp.1297-1308
• /
• 2015

In Korea, the local traffic safety master plan has been established and implemented according to the Traffic Safety Act. Each local government is required to establish a customized traffic safety policy and share roles for improvement of traffic safety and this means that local governments lead and promote effective local traffic safety policies fit for local circumstances in substance. For implementing efficient traffic safety policies, which accord with many-sided characteristics of local governments, the prediction of community-based traffic accidents, which considers local characteristics and the analysis of accident influence factors must be preceded, but there is a shortage of research on this. Most of existing studies on the community-based traffic accident prediction used social and economic variables related to accident exposure environments in countries or cities due to the limit of collected data. For this reason, there was a limit in applying the developed models to the actual reduction of traffic accidents. Thus, this study developed a local traffic accident prediction model, based on smaller regional units, administrative districts, which were not omitted in existing studies and suggested a method to reflect traffic safety facility and policy variables that traffic safety policy makers can control, in addition to social and economic variables related to accident exposure environments, in the model and apply them to the development of local traffic safety policies. The model development result showed that in terms of accident exposure environments, road extension, gross floor area of buildings, the ratio of bus lane installation and the number of crossroads and crosswalks had a positive relation with accidents and the ratio of crosswalk sign installation, the number of speed bumps and the results of clampdown by police force had a negative relation with accidents.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.20 no.4
• /
• pp.348-356
• /
• 2018

Most of fires were human-caused fires in Korea, but meteorological factors are also big contributors to fire behavior and its spread. Thus, meteorological factors as well as topographical and forest factors were considered in the fire danger rating systems. This study aims to develop an advanced national integrated daily weather index(DWI) using weather data in the spring and fall to support forest fire prevention strategy in South Korea. DWI represents the meteorological characteristics, such as humidity (relative and effective), temperature and wind speed, and we integrated nine logistic regression models of the past into one national model. One national integrated model of the spring and fall is respectively $[1+{\exp}\{-(2.706+(0.088^*T_{mean})-(0.055^*Rh)-(0.023^*Eh)-(0.014^*W_{mean}))\}^{-1}]^{-1}$, $[1+{\exp}\{-(1.099+(0.117^*T_{mean})-(0.069^*Rh)-(0.182^*W_{mean}))\}^{-1}]^{-1}$ and all weather variables significantly (p<0.01) affected the probability of forest fire occurrence in the overall regions. The accuracy of the model in the spring and fall is respectively 71.7% and 86.9%. One integrated national model showed 10% higher accuracy than nine logistic regression models when it is applied weather data with 66 random sampling in forest fire event days. These findings would be necessary for the policy makers in the Republic of Korea for the prevention of forest fires.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.444-444
• /
• 2021

하천의 오염부하량 관리 계획은 지속적인 모니터링을 통한 자료 구축과 모형을 이용한 예측결과를 기반으로 수립된다. 하천의 모니터링과 예측 분석은 많은 예산과 인력 등이 필요하나, 정부의 담당 공무원 수는 극히 부족한 상황이 일반적이다. 이에 정부는 전문가에게 관련 용역을 의뢰하지만, 한국과 같이 지형이 복잡한 지역에서의 오염부하량 배출 특성은 각각 다르게 나타나기 때문에 많은 예산 소모가 발생 된다. 이를 개선하고자, 본 연구는 합성곱 신경망 (convolution neural network)과 수문학적 이미지 (hydrological image)를 이용하여 강우 발생시 BOD 및 총인의 부하량 예측 모형을 개발하였다. 합성곱 신경망의 입력자료는 일반적으로 RGB (red, green, bule) 사진을 이용하는데, 이를 그래도 오염부하량 예측에 활용하는 것은 경험적 모형의 전제(독립변수와 종속변수의 관계)를 무너뜨리는 결과를 초래할 수 있다. 이에, 본 연구에서는 오염부하량이 수문학적 조건과 토지이용 등의 변수에 의해 결정된다는 인과관계를 만족시키고자 수문학적 속성이 내재된 수문학적 이미지를 합성곱 신경망의 훈련자료로 사용하였다. 수문학적 이미지는 임의의 유역에 대해 2차원 공간에서 무차원의 수문학적 속성을 갖는 grid의 집합으로 정의되는데, 여기서 각 grid의 수문학적 속성은 SCS 토양보존국(soil conservation service, SCS)에서 발표한 수문학적 토양피복형수 (curve number, CN)를 이용하여 산출한다. 합성곱 신경망의 구조는 2개의 Convolution Layer와 1개의 Pulling Layer가 5회 반복하는 구조로 설정하고, 1개의 Flatten Layer, 3개의 Dense Layer, 1개의 Batch Normalization Layer를 배열하고, 마지막으로 1개의 Dense Layer가 연결되는 구조로 설계하였다. 이와 함께, 각 층의 활성화 함수는 정규화 선형함수 (ReLu)로, 마지막 Dense Layer의 활성화 함수는 연속변수가 도출될 수 있도록 회귀모형에서 자주 사용되는 Linear 함수로 설정하였다. 연구의 대상지역은 경기도 가평군 조종천 유역으로 선정하였고, 연구기간은 2010년 1월 1일부터 2019년 12월 31일까지로, 2010년부터 2016년까지의 자료는 모형의 학습에, 2017년부터 2019년까지의 자료는 모형의 성능평가에 활용하였다. 모형의 예측 성능은 모형효율계수 (NSE), 평균제곱근오차(RMSE) 및 평균절대백분율오차(MAPE)를 이용하여 평가하였다. 그 결과, BOD 부하량에 대한 NSE는 0.9, RMSE는 1031.1 kg/day, MAPE는 11.5%로 나타났으며, 총인 부하량에 대한 NSE는 0.9, RMSE는 53.6 kg/day, MAPE는 17.9%로 나타나 본 연구의 모형은 우수(good)한 것으로 판단하였다. 이에, 본 연구의 모형은 일반 ANN 모형을 이용한 선행연구와는 달리 2차원 공간정보를 반영하여 오염부하량 모의가 가능했으며, 제한적인 입력자료를 이용하여 간편한 모델링이 가능하다는 장점을 나타냈다. 이를 통해 정부의 물관리 정책을 위한 의사결정 및 부족한 물관리 분야의 행정력에 도움이 될 것으로 생각된다.

• Journal of Korean Academy of Nursing Administration
• /
• v.6 no.2
• /
• pp.195-209
• /
• 2000

The purpose of this study is to estimate the population requiring nursing home services among elderly people in Korea. This study identifies the need of nursing home services determined by health care professionals and estimates the proportion of elderly people requiring nursing home service according to the admission criteria. Surveys were conducted on health care professionals including medical doctors, home care nurses, and nurse practitioners. They were asked to assess nursing home need based on four content areas: Physical function (Activities of Daily Living), chronic disease, Physical symptoms (incontinence), mobility, eating, and sensory function. Based on the professionally determined need criteria the proportion of elderly people requiring nursing home services was estimated using secondary data from the 1994 Survey on the Living Status of the Korean Elderly. The number of study subjects to estimate nursing home need who were 60 and older totaled 2,058. The most important factor contributing to the admission eligibility criteria was the elderly living alone. Other factors related were the elderly being unable or having difficulty carrying out activities, and having insufficient help from other our activities, and having insufficient help from other members of the household. Using only physical function, the proportion of elderly people requiring nursing home was $8{\sim}9%$. When only chronic disease was used, proportions varied widely; for the doctor's group, the proportion was over 30%. Using all areas, the proportions of elderly people requiring nursing home were between 13% and 38%. The estimate using chronic disease and physical function was similar to the on using all areas.

• Health Policy and Management
• /
• v.21 no.3
• /
• pp.414-424
• /
• 2011

The purpose of this study is to describe the characteristics associated with the hypertension educated population, and to develop and analyze a simple predictive model of the hypertension management education status. Based on the Korea National Health and Nutrition Examination Survey in 2008, a cross-sectional design was used in this study. An effective 1.165 adults(${\geq}30$) sample was divided into a participation group (n=66) and a non-participation group(n=1,099), and to compare demographic, socio-economic and health characteristics between two groups. Moreover, predictors associated with participation in hypertension education programs were identified by the logistic regression analysis. The participation rate in hypertension education in Korea is only 5.7% which is vastly low given the various programs were provided, and there are statistically significant differences between a participation group and a non-participation group in age(p=0.050), marital status(p=0.002), education level(p=0.000), and residence area(p=0.037). Furthermore, age for 40-49 years(OR : 0.207), education level of high school(OR : 2.579) and college(OR : 6.417), duration of hypertension(OR : 1.044), CVA(OR : 2.463), and blood pressure(OR : 1.041) are statistically significant predictors associated with the participation in hypertension education programs. To increase the participation of hypertension education program, variables such as age, education level, duration of hypertension, CVA, and blood pressure are more concerned. And, high-risk patients and family members need targeted outreach programs.

• Health Policy and Management
• /
• v.27 no.2
• /
• pp.149-156
• /
• 2017

Background: This study was conducted to evaluate the performance of the Hierarchical Condition Category (HCC) model, identify potentially high-cost patients, and examine the effects of adding prior utilization to the risk model using Korean claims data. Methods: We incorporated 2 years of data from the National Health Insurance Services-National Sample Cohort. Five risk models were used to predict health expenditures: model 1 (age/sex groups), model 2 (the Center for Medicare and Medicaid Services-HCC with age/sex groups), model 3 (selected 54 HCCs with age/sex groups), model 4 (bed-days of care plus model 3), and model 5 (medication-days plus model 3). We evaluated model performance using $R^2$ at individual level, predictive positive value (PPV) of the top 5% of high-cost patients, and predictive ratio (PR) within subgroups. Results: The suitability of the model, including prior use, bed-days, and medication-days, was better than other models. $R^2$ values were 8%, 39%, 37%, 43%, and 57% with model 1, 2, 3, 4, and 5, respectively. After being removed the extreme values, the corresponding $R^2$ values were slightly improved in all models. PPVs were 16.4%, 25.2%, 25.1%, 33.8%, and 53.8%. Total expenditure was underpredicted for the highest expenditure group and overpredicted for the four other groups. PR had a tendency to decrease from younger group to older group in both female and male. Conclusion: The risk adjustment models are important in plan payment, reimbursement, profiling, and research. Combined prior use and diagnostic data are more powerful to predict health costs and to identify high-cost patients.

• Informatization Policy
• /
• v.21 no.3
• /
• pp.85-101
• /
• 2014

This study analyzed the influencing factors for knowledge sharing at GKMC, and then tried to illuminate the policy meanings implied in the results. To build a framework of analysis, reviewing the KM-related studies, the author selected five influencing factors for knowledge sharing, such as CMC quality, community commitment, structural social capital, cognitive social capital, and relational capital, and actors, and identified the fact that all the factors have a positive effect on knowledge sharing. In the case of Kwang-ju metropolitan city, the first factor that affects knowledge sharing is community commitment, the second one is CMC quality, and the third one is structural social capital. This result means that to succeed in knowledge sharing, the local government managers should try to shape the bonding among members, and then to get rid of the causes of complaints. In addition, local government also needs to predict problems claims and take proper actions for GKMC to be used conveniently through monitoring their work continuously. Furthermore, they should make a free and happy working environment, closely examining the change of the relationship among social capitals.

• Health Policy and Management
• /
• v.14 no.2
• /
• pp.78-98
• /
• 2004

The purpose of this study was to categorize the contribution evasion and develop the expected models for contribution arrears in National Health Care System. The modified logistic regression model in non-payments was used as logistic regression model based on the statistical method. By using this model, we arranged non-payment types and typical branches those are appeared by statistical technique. First fact, sex and age branches those are able to take a part in economy had effect mostly. Also they had difference in non-payment probability by existence of their incomes and property. Especially people who didn't have their own house and car were appeared in high non-payment probability, disease and reduction characteristic(rare diseases, reduction of seniors, handicaps, numbers of medical treatments) didn't effect much in probability. The reason for some characteristic of non-payment which is higher than the correct threshold value of Logistic Regression Model (a suggested model for predicting non-payment)'s distribution of probability was mostly moral hazard. Living difficulty was the bigger reason for non-payment, but moral slackening was the bigger reason for non-payment. But it is careless to decide that moral hazard is just the reason, there is a necessity to examine on the side of sociology based in family. By the reason, the member's non-payment reason can be classified by economy, population, and psychology, but there was a comprehension that losing of work desire could be one reason. So we analyzed informations for composition of family of members. In conclusion, we grasped that family conflict makes non-payment and conversion of member in the National Basic Livelihood Protection System difficult.

• The Journal of Society for e-Business Studies
• /
• v.16 no.3
• /
• pp.225-247
• /
• 2011

Universities have been investing in their information systems to keep their management functions working efficiently and effectively. Thanks to these efforts, faculty members and other university employees can perform their tasks efficiently almost anywhere and anytime. Several universities embarked upon information systems projects to take advantage of emerging information technologies in their administration and management. Only a limited number of universities have achieved their objectives; some others have been even tinkering with the idea of abandoning their newly developed academic information systems. The development of academic information systems often start with a relatively high risk of system failure. Sometimes, these systems encounter unforeseen obstacles or fail in systems development. These universities with problems also can overcome these issues by collecting their wisdom. The mindfulness theory is suitable for dealing with implementing academic information systems. This research analyzes an academic information systems development case from a mindfulness perspective, and also addresses its research implications and theoretical contributions.

• Health Policy and Management
• /
• v.16 no.2
• /
• pp.21-48
• /
• 2006

As prior studies indicate that chronic diseases are mainly attributed to health behavior, preventive health care rather than treatment for illness needs to improve health status. Since chronic conditions require long-term therapy, health care expenditures to treat chronic diseases have been substantial burden at national level. In this point of view, this study suggests that the health promotion program should be based on Knowledge Based System Using Data Mining Technique, we developed a predictive model for preventive healthcare management on diabetes mellitus. Generally, in the outbreak of diabetes mellitus there is a difference in lifestyle and the risk factors according to gender. So we developed a predictive model in accordance with gender difference and applied the Logistic Regression Model based on Data Mining process. The result of the study were as follow. The lift of the last predictive model was an average 2.23 times(male model : 2.13, female model 2.33) more improved than in the random model in upper 10% group. The health risk factors of diabetes mellitus are gender, age, a place of residence, blood pressure, glucose, smoking, drinking, exercise rate. On the basis of these factors, we suggest the program of the health promotion.