• Korean Journal of Social Welfare
• /
• v.62 no.3
• /
• pp.83-108
• /
• 2010

This study aims to estimate the trajectory of outpatient medical service use and examine what factors are associated with the trajectory among older adults 60 and over with specific focuses on age variations. Using the first three waves of the Korean Welfare Panel Study data, the trajectory and predictors were examined through the Latent Growth Curve Modeling and age variations were examined through the Multi-group Comparison Analyses. The research model was developed based on the Anderson Model. The results showed that study participants tend to increase outpatient medical service use with years. Individuals 75 or younger presented a much faster increasing rate of medical service use than those 75 and over. Similar to the findings of the previous studies, most predisposing factors, resource factors, and needs factors were found to be associated with the trajectory of outpatient medical service use. Needs factors were more closely associated with the medical service use trajectory than resource factors. With regard to age variations in predictors, few significant age variations were found. Based on the finding of the study, implications and future research directions were discussed.

• Korean Journal of Construction Engineering and Management
• /
• v.9 no.4
• /
• pp.92-100
• /
• 2008

Productivity is acknowledged as a very important factor for successful construction projects. Various data items collected daily form a construction site can be used for monitoring its productivity by analyzing them. However, no analytical methods for that purpose have been established in the domestic construction industry yet. Previous researches that utilized OLAP and data mining to analyze the factors that affect the productivity did not do well with predicting future cases with sufficient reliability. This research therefore proposes a new analytical process which is capable of figuring out the factors that would affect the productivity of future projects, through qualitative and quantitative analysis of the data collected from past projects.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.01a
• /
• pp.31-34
• /
• 2023

주택 매매에 있어서 가격에 대한 예측은 매우 중요하지만, 실거래 발생 전까지는 정확한 가격을 알 수 없다. 그렇기에 주택가격을 예측하는 많은 연구가 진행되어왔다. 주택가격을 결정하는 영향요인은 크게 주택의 내부요인과 주택의 외부 요인으로 구분되는데, 내부적인 요인 (공급면적, 전용면적, 층, 방 개수 등)에 대한 연구가 많이 진행되었다. 하지만 외부적인 요인 (위치 요인, 금융요인 등)에 대한 연구는 미비하였다. 본 연구는 주택 매수자 관점에서 가격 예측 시 외부적인 요인 역시 중요하다고 판단하여 외부요인을 적용하고자 한다. 본 논문에서 제안하는 방법은 다양한 외부요인 중 주택의 위치 정보를 활용하여, 해당 정보 기반으로 도출 가능한 데이터를 추가한다. 또한 이용량에 따른 지하철역 데이터를 추가하여 관련된 여러 영향요인들을 분석 및 적용 후 머신러닝 기반 예측 모델을 생성한다. 생성된 모델들에 주택매매 실거래 데이터를 적용하여 예측 정확도를 비교 후 높은 정확성을 보이는 모델 결과에 주요하게 영향을 끼치는 요인에 관하여 기술한다.

• Proceedings of the KIEE Conference
• /
• 2011.07a
• /
• pp.638-639
• /
• 2011

전력수요는 여러 가지 사회, 경제, 기상 등의 복합적인 요인에 의해 결정되므로 예측하기 쉽지 않다. 수요 예측 시스템을 통해 예측된 결과는 예측일의 상황에 맞는 여러 가지 예측과 관련된 변동 요인의 적용범위가 수치적으로 달라 질 수 있어 예측 데이터와 실제 수요와의 오차율이 높아질 수 있다. 따라서 전력수요 실적과 예측간 오차에 영향을 주는 변동 요인의 영향력을 분석하고, 예측일의 상황에 맞게 적절한 수치의 변수를 예측 시스템에 제공하여 예측의 정확성을 향상시키는 방안에 대하여 알아보았다.

• Journal of Digital Convergence
• /
• v.12 no.8
• /
• pp.19-27
• /
• 2014

Traditionally, Anderson model is recognized as suitable for analysis of predictive factors for the use of medical and social services. Therefore, the present study was aimed to investigate the predictors of the elderly's use of the social service based on previous studies by configuring Anderson model's predisposing factors(gender, age, education level, place of residence, marital status), enabling factors(economic status, health literacy, use of welfare center or not), and need factors(whether held chronic disease, IADL and depression). To this aim, SPSS 18.0 was used for the subject of 329 elderly living in Chungbuk region. The main findings of this study are as follows. The most influential factor on the social service use of the elderly turned out to be whether to use the welfare centers and health literacy of enabling factors. Next, the depressed levels showed the most significant impact among the need factors, and gender was the most influential among the predisposing factors. Based on the results of these studies, some measures were suggested to activate the elderly's use of social services.

• Korean Journal of Social Welfare Studies
• /
• no.39
• /
• pp.5-28
• /
• 2008

The purpose of this study is two-fold: 1) to identify different adolescent smoking trajectories in Korea; and 2) to examine predictors of those smoking trajectories within a social developmental frame. Data were from the Korea Youth Panel Survey(KYPS), a longitudinal study of 3,449 youths followed since 2003. Using semi-parametric group-based modeling, four smoking trajectories were identified: non initiators, late onsetters, experimenters, and escalators. Multinomial logistic regressions were then used to identify risk and protective factors that distinguish the trajectory groups from one another. Among non smokers at age 13, late onsetters were distinguished from non initiators by a variety of factors in every ecological domain. Among youths who already smoked at age 13, escalators who increased their smoking were distinguished from experimenters who almost desisted from smoking by age 17 by self-esteem and academic achievement. Finally, implications for youth welfare practice from this study were discussed.

• The Journal of the Korea Contents Association
• /
• v.20 no.1
• /
• pp.519-529
• /
• 2020

The purpose of this study is to establish a model for predicting academic achievement of college students and to reveal the interrelationship and relative influence of each factor. For this, we surveyed the personal factors and learning strategy factors of 1,310 learners at J University, and analyzed the discriminant factors and patterns of the predictors of academic achievement through the decision tree analysis, a data mining method, and examined the relative effects of each factor. Binary logistic regression analysis was performed for viewing. As a result, the most important factor for predicting academic achievement was efficacy, and other factors such as motivation, time management, and depression were predictive of academic achievement. The patterns of factors predicting academic achievement were found to be high in efficacy and time management, and high in motivation for learning even if the efficacy was moderate. Low efficacy and learning motivation, and high depression have been shown to decrease academic achievement. Based on these results, the study suggested the efficacy and motivation to improve academic achievement of college students, strengthening time management education, and managing negative emotions.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.05a
• /
• pp.539-541
• /
• 2019

오프라인 소비자의 의사결정은 크게 라이프스타일, 동기, 개성, 학습 등 개인적인 영향요인과 문화, 기후, 가족 등 기타 상황적 요인을 포함하는 환경적 영향요인에 의해 결정된다. 이러한 요인들을 입력 값으로 하는 다양한 딥러닝 모델을 이용한 소비예측 연구들이 진행되고 있다. 딥러닝을 이용한 예측모델을 사용하기 위해서는 먼저 요인들이 의사를 결정하는데 있어 얼마나 상관관계가 있는지 파악하는 작업이 중요하다. 본 논문에서는 이를 위해 다양한 상관관계 분석모델을 이용해 소비 의사결정 요소 중 기후, 문화와 같은 상황적 요인과 소비와의 상관관계를 도출하고, 기후, 문화를 대변하는 미세먼지 데이터와, SNS 버즈량 데이터와 소비데이터를 학습하는 소비예측 LSTM모델을 제안하고자 한다.

• International Area Studies Review
• /
• v.21 no.4
• /
• pp.159-172
• /
• 2017

In a typical trend-cycle decomposition of GDP, the trend component is usually assumed to follow a random walk process. This paper considers an ARIMA trend and assesses the validity of the ARIMA trend model. I construct univariate and bivariate unobserved-components(UC) models, allowing the ARIMA trend. Estimation results using U.S. data are favorable to the ARIMA trend models. I, also, compare the forecasting performance of the UC models. Dynamic pseudo-out-of-sample forecasting exercises are implemented with recursive estimations. I find that the bivariate model outperforms the univariate model, the smoothed estimates of trend and cycle components deliver smaller forecasting errors compared to the filtered estimates, and, most importantly, allowing for the ARIMA trend can lead to statistically significant gains in forecast accuracy, providing support for the ARIMA trend model. It is worthy of notice that trend shocks play the main source of the output fluctuation if the ARIMA trend is allowed in the UC model.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.12
• /
• pp.7-13
• /
• 2018

The strength of concrete is affected significantly not only by the internal influence factors of cement, water, sand, aggregate, and admixture, but also by the external influence factors of concrete placement delay and curing temperature. The objective of this research was to predict the concrete strength considering both the internal and external influence factors when concrete is placed at the construction site. In this study, a concrete strength test was conducted on the 24 combinations of internal and external influence factors, and a neural network model was constructed using the test data. This neural network model can predict the concrete strength considering the external influence factors of the concrete placement delay and curing temperature when concrete is placed at the construction site. Contractors can use the concrete strength prediction neural network model to make concrete more robust to external influence factors during concrete placement at a construction site.