• 한국수자원학회논문집
• /
• 제38권8호
• /
• pp.595-604
• /
• 2005

관측자료의 보완이나 확충을 위한 강수량 모의발생은 수문분석에 있어서 중요한 과제라고 할 수 있다. 강수량을 모의하는 방법은 크게 기존의 매개변수적 방법과 비매개변수적 방법 두 가지로 나눌 수 있고, 강수량 모의의 시간간격에 따라 일강수량 자료의 모의 또는 시간강수량 자료의 모의 등으로 구분할 수 있다. 지금까지, Markov모형은 일강수량 모의발생에 많이 이용되어왔다. 이러한 대부분 Markov모형들은 동질성모형으로 상태벡터를 구축하는데 있어서 자료의 크기가 작으면 모형구축의 어려움이 따르고 같은 월에 대한 상태벡터의 동질성을 가정하는 등의 문제가 있다. 실제 강수발생의 과정은 비정상적(nonstationary)이므로 이를 보완하기 위해, 된 논문에서는 일강수량을 기존의 매개변수적인 방법이 아닌 단변량과 다변량에 대하여 비매개변수적인 방법으로 접근하여 모의하는 방법에 대하여 분석하였다.

• 한국기계가공학회지
• /
• 제7권4호
• /
• pp.115-120
• /
• 2008

The fatalities of pedestrian accounted for about 40.0% of all fatalities in Korea (2005 year). In pedestrian involved accident, the most important data to inspect accident is throw distance of pedestrian. The throw distance of pedestrian can be influenced by many variables, such as vehicular frontal shape, vehicular impact speed, the offset of impact point, the height of pedestrian, and road condition. The trajectory of pedestrian after collision can be influenced by vehicular frontal shape classified into sedan type, box type, SUV type and van type. Many studies have been done about pedestrian accident with passenger car model and bus model for simple factors. But the study of pedestrian accident by van type vehicle was much insufficient, and even that the influence of multiple factors such as the offset of impact point was neglected. In this paper, a series of pedestrian kinetic simulation were conducted to inspect relationship between throw distance and multiple factors with using PC-CRASH s/w, a kinetic analysis program for a traffic accident for van type. By based on the simulation results, multi-variate regression was conducted, and regression equation was presented.

• 한국산학기술학회논문지
• /
• 제15권8호
• /
• pp.4881-4894
• /
• 2014

본 논문은 2009년~2012년까지 코스닥시장에서 상장폐지된 기업 중 제조업을 영위하는 83개사를 부실기업표본으로 선정하고 동종품목 혹은 동종 산업군에 속하는 정상기업 83개사와 함께 쌍대표본으로 표본기업을 구성하였다. 상장폐지직전 5년간 75개의 재무적 비율을 부실기업과 정상기업 두 그룹의 평균차이분석을 통하여 5년 연속 유의미한 변수로 출현한 15개 변수를 선정하여 단일변량분석(이원분류법)과 다변량분석(로지스틱회귀분석 및 판별분석)을 진행하였다. 분석 결과, 로지스틱회귀분석모형의 판별력(분류정확도)이 가장 높게 나타났다. 본 연구는 기업부실이 장기간에 걸쳐 서서히 진행된다는 점을 감안하여 상장폐지직전 5년 전 자료까지 고려하여 기업부실을 예측함으로써 기존 선행연구들이 상장폐지 직전 3년 전 자료로 기업부실을 예측한 것과 달리 보다 조기에 기업부실을 예측하려고 시도한 점과 일반 이해관계자들도 쉽게 접근할 수 있는 이원분류법(단일변량분석)과 통계적으로 복잡한 다변량분석을 비교분석한 것도 기존 선행연구와 차별화된다.

• 한국지진공학회:학술대회논문집
• /
• 한국지진공학회 2003년도 추계 학술발표회논문집
• /
• pp.13-19
• /
• 2003

Discriminant method using seismic signal was studied for discrimination of surface explosion. By means of the seismic spectral characteristics, multi-variate discriminant analysis was performed. Four single discriminant techniques - Pg/Lg, Lg1/Lg2, Pg1/Pg2, and Rg/Lg - based on seismic source theory were applied to explosion and earthquake training data sets. The Pg/Lg discriminant technique was most effective among the four techniques. Nevertheless, it could not perfectly discriminate the samples of the training data sets. In this study, a compound linear discriminant analysis was defined by using common characteristics of the training data sets for the single discriminants. The compound linear discriminant analysis was used for the single discriminant as an independent variable. From this analysis, all the samples of the training data sets were correctly discriminated, and the probability of misclassification was lowered to 0.7％.

• 한국환경과학회지
• /
• 제15권9호
• /
• pp.887-895
• /
• 2006

Through this research of the analysis on the frequency flood discharges regarding basin property factors, a linear regression system was introduced, and as a result, the item with the highest correlation with the frequency flood discharges from Nakdong river basin is the basin area, and the second highest is the average width of basin and the river length. The following results were obtained after looking at the multi correlation between the flood discharge and the collected basin property factors using the data from the established river maintenance master plan of the one hundred twenty-five rivers in the Nakdong river basin. The result of analysis on multivariate correlation between the flood discharges and the most basic data in determining the flood discharges as basin area, river length, basin slope, river slope, average width of basin, shape factor and probability precipitation showed more than 0.9 of correlation in terms of the multi correlation coefficient and more than 0.85 for the determination coefficient. The model which induced a regression system through multi correlation analysis using basin property factors is concluded to be a good reference in estimating the design flood discharge of unmeasured basin.

• 한국지역사회생활과학회지
• /
• 제27권1호
• /
• pp.95-108
• /
• 2016

The objectives of this study are to analyze the characteristics of multi-cultural families in rural areas and to classify their types by applying multi-variate techniques and cluster analyses. Data for the study were obtained by a surveying 120 married migrant females in rural areas of Chungchengnam-do, South Korea. By utilizing the factor analysis to analyze the characteristics of multi-cultural families, 16 basic variables related to these female subjects were categorized into 6 factors: 'marriage length and age', 'language skill of migrant female', 'language skill of husband', 'family satisfaction', 'income and education', and 'general living satisfaction in Korea with remittance'. By appling the cluster analysis, multi-cultural families in rural areas were divided into the following 5 types: 'stable settlement', 'average but stagnant', 'below average yet positive', 'high- income with little communication', and 'young low-income'. In all types, it is strongly recommended to develop various programs regarding vocational education for the migrant females in order to increase their economic opportunities as well as social status.

• 한국학교보건학회지
• /
• 제22권2호
• /
• pp.85-101
• /
• 2009

Purpose: We interviewed 500 students attending to universities in Gwangju and Jeonnam using a questionnaire. The questionnaire was composed of some questions on general characteristics of the subjects, academic characteristics, health-related behaviors, family function, and drinking problems. Methods: The data collected were analysed with uses of t-test, dispersion analysis, correlations analysis and multi-variate regression analysis. Results: As a result of the simple analysis we found that variables related to drinking problems of college students were religion, family, residence, parents' job, living standard, major, academic year, exercise, parents' drinking, parents' attitude to drinking, drinking quantity, intimacy, conflicts, and upbringing tendency. As a result of the multi-variate regression analysis, we found that the higher intimacy between family members, deterioration in behaviors, family and personal relations, and social functions was statistically significantly low. Conclusion: This study demonstrated that drinking problems of college students had significant relations with intimacy, conflicts and upbringing tendency and suggests that an approach in an aspect of family functions is important to overcome drinking problems of college students.

• 한국학교ㆍ지역보건교육학회지
• /
• 제15권1호
• /
• pp.31-43
• /
• 2014

Objectives: The purpose of this study is to identify the relationship of personal hygiene education and hand-washing practices among adolescents. Then the impact of such factors on the hand-washing practices was analyzed. Methods: The data of the 2012 Youth Health Risk Behavior web-based Survey collected by Korean Center for Disease Control was analyzed using SPSS. Total 74,186 of middle and hish school students were included. Uni-variate analysis was done by complex sample crosstabs and multi-variate analysis was done by complex sample logistic regression. Results: The 26.8% of students experienced personal hygiene education. The students of boys, low school grade, coeducation, metropolitan, high school record and high economic status experienced more hygiene education. The hand-washing practices were high in the students with the experience of personal hygiene education. In the factors affecting the hand-washing practice, the experience of personal hygiene education was consistently significant. If students experienced the personal hygiene education, they showed 20~30% more rates of hand-washing practices. Conclusions: Hand-washing practice was high when experiencing personal hygiene education. The personal hygiene education was necessary to improve the rate of hand-washing practices.

• 보건행정학회지
• /
• 제27권4호
• /
• pp.315-323
• /
• 2017

Background: This study was purposed to analyze the effect of spatial accessibility to the psychiatry department in general hospital on the outpatient visit of mental patients. Methods: Data was provided from the Statistics Korea and Statistical Geographic Information Service, National Health Insurance Service, Health Insurance Review and Assessment Service, and Korea Transport Institute in 2015. The study regions were 103 administrative regions such as Si and Gu. The 103 regions had at least one general hospitals with a psychiatry department. The number of outpatient visit of mental patients in regions was used as the dependent variable. Spatial accessibility to mental general hospital was used as the independent variable. Control variables included such as demographic, economic, and health medical factors. This study used network analysis and multi-variate regression analysis. Network analysis by ArcGIS ver. 10.0 (ESRI, Redlands, CA, USA) was used to evaluate the average travel time and travel distance in Korea. Multi-variate regression analysis was conducted by SAS ver. 9.4 (SAS Institute Inc., Cary, NC, USA). Results: Travel distance and time had significant effects on the number of outpatient visits in mental patients in general hospital. Average travel time and travel distance had negative effects on the number of visits. Variables such as (number of total population, percentage of aged population over 65, and number of mental general hospital) had significant effects on the number of visit in mental patients. Conclusion: Health policy makers will need to consider the spatial accessibility to the mental healthcare organization in conducting regional health planning.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제11권2호
• /
• pp.81-86
• /
• 2022

시계열 데이터는 주식, IoT, 공장 자동화와 같은 다양한 실생활에서 수집되고 활용되고 있으며, 정확한 시계열 예측은 해당 분야에서 운영 효율성을 높일 수 있어서 전통적으로 중요한 연구 주제이다. 전반적인 시계열 데이터의 향상된 특징을 추출할 수 있는 대표적인 시계열 데이터 분석 방법인 다층 수평 예측은 최근 부가적 정보를 포함하는 시계열 데이터에 내재한 이질성(heterogeneity)까지 포괄적으로 분석에 활용하여 향상된 시계열 예측한다. 하지만 대부분의 심층 학습 기반 시계열 분석 모델들은 시계열 데이터의 이질성을 반영하지 못했다. 따라서 우리는 잘 알려진 temporal fusion transformers 방법을 사용하여 실생활과 밀접한 실제 데이터를 이질성을 고려한 다층 수평 예측에 적용하였다. 결과적으로 주식, 미세먼지, 전기 소비량과 같은 실생활 시계열 데이터에 적용한 방법이 기존 예측 모델보다 향상된 정확도를 가짐을 확인할 수 있었다.