• The Journal of the Convergence on Culture Technology
• /
• v.10 no.6
• /
• pp.677-689
• /
• 2024

The quality of life, frailty, economic activity, and other indicators are crucial for assessing older adults' overall well-being and health status. A comprehensive evaluation using this information helps predict the health status of older adults. This study aims to apply and compare machine learning-based prediction models for comprehensive health indicators of community-dwelling older adults. Utilizing data from 4,652 individuals provided by the Aging Research Panel, we assessed various machine learning techniques to fit the predictor variables. Our findings reveal that the LightGBM Regression model performed the best, with an RMSE of 5.082 and an MSE of 25.83. The Gradient Boosting model best predicted current health status, with an RMSE of 0.588 and an R-Square of 0.456. Additionally, the Random Forest model showed strong performance in predicting economic activity participation among older adults. These machine learning-based models offer valuable insights for evaluating health status and predicting economic activity participation, highlighting the importance of employing diverse methodologies for comprehensive predictions.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2020.07a
• /
• pp.603-604
• /
• 2020

한국사회는 전통적인 대가족제도가 급속히 해체되고 저 출산 및 고령화로 인한 고령층의 1인 가정의 수가 급속히 증가하고 있는 추세이다. 고령자 1인 가구에 대한 다양한 서비스와 고도화가 필요한 이유이다. 본 연구에서는 1인 가정을 대상으로 IoT 기기를 통한 다양한 PHR 생체 신호와 환경정보을 수집하고 수집된 정보를 바탕으로 건강상태를 모니터링하는 시스템을 제안한다. 제안하는 시스템은 의료기기에서 제공되는 개방형 PHR 데이터의 융합으로 정보 분석 및 예측능력을 강화하고 고독사 상황파악 및 방지 프로그램을 이행할 수 있는 기본 인프라을 구축하고자 한다. 또한 중장년층의 미래에 대한 불확실성을 제거하고 사회복지서비스의 확대를 위한 정책적 과제의 논의적 목적을 가지고 있다. 본 연구의 결과물은 사회 소외 계층에 대한 서비스 확대와 국민의 의료환경 개선에 도움이 될 것으로 사료된다.

• The Korean Journal of Applied Statistics
• /
• v.31 no.5
• /
• pp.637-653
• /
• 2018

Rapid aging of the population affects population structure and population aging. Consequently, developed countries have focused on population aging as a major issue in regards to pension sustainability finances as well as health and the elderly welfare system. Mortality projections that result from population structure changes and population aging are increasingly important. This paper compares six mortality models using KOSTAT's life table from 1970 to 2016. The models are rooted in the Lee-Carter (LC) model (Lee and Carter, Journal of the American Statistical Association, 87, 659-671, 1992) and have been modified and improved on the assumptions of the LC model. We examined the improvement process and the check assumption by models in order to find a suitable mortality model for Korea. Korea shows rapid aging and declined mortality rate by age; therefore, it is desirable to estimate and predict mortality from LL&LC-ER models by combining LC-ER, LL, and LC-ER models that reflect the phenomena and modify age-specific mortality patterns without major changes in expected life expectancy.

• Journal of the Korean Society of Food Science and Nutrition
• /
• v.39 no.1
• /
• pp.146-153
• /
• 2010

The objectives of this study were to explore food-related lifestyle segments of the older consumers, to identify its socio-demographic characteristics, and to investigate the differences in variables regarding health beliefs. A survey was conducted of adults 55 years of age and older living in Seoul, South Korea from March 28 to April 10, 2007. Out of the 500 distributed questionnaires, 361 were retained for final analysis: a response rate of 72.2%. As a result of cluster analysis, five consumer segments were identified; health-managing group, diet-unconcerned group, convenience-oriented group, taste-oriented group, unpracticed group. Significant differences were found among the five segments in terms of socio-demographic characteristics and variables regarding health beliefs (i.e., perceived self-efficacy, perceived barriers, perceived benefits). In the health-managing group and taste-oriented group, mean scores of perceived self-efficacy (p<0.001) and perceived benefits (p<0.001) were significantly higher than other groups. However, in the diet-unconcerned group and convenience-oriented group, the mean scores of perceived barriers (p<0.01) were significantly high. This study shows that foodservice operators targeting the older consumers should consider characteristics of each segment to develop a customized program.

• 한국노년학
• /
• v.31 no.4
• /
• pp.1083-1101
• /
• 2011

The purpose of this study is to describe how the structural and functional features of social network change among widowed middle and older adults and to examine the effect of personal predictors of the social network change. Data was obtained from men and women between 45 to 98 years of age(N=118) who were bereaved by the death of their spouse since the first wave survey and participated in the second wave survey of the Korean Longitudinal Study of Ageing(KLoSA). The main findings are as follows: First, their social network after the bereavement was strengthened centered around children; for example, the number of adult children living in proximity to the parent, frequency of contact with children, and the financial and non-financial support from children generally increased. Second, the social network change pattern was categorized into four types such as "overall increased type," "children-centered increased type," "children/close relationship-centered increased type," and "stagnation type." Finally, the health condition of the widowed middle and older adults was a strong predictor of the social network change.