• 융합정보논문지
• /
• 제9권8호
• /
• pp.248-253
• /
• 2019

노인성 치매의 전 임상단계인 경도인지장애(MCI)를 조기 진단하고, 조기 개입한다면, 치매의 발병률을 줄일 수 있다. 본 연구는 우리나라 지역사회 노인의 MCI 예측 모형을 개발하고 노년기 인지장애의 예방을 위한 기초자료를 제공하였다. 연구대상은 2012년 Korean Longitudinal Survey of Aging(KLoSA)에 참여한 65세 이상 지역사회 노인 3,240명(남성 1,502명, 여성 1,738명)이다. 결과변수는 MCI유병으로 정의하였고, 설명변수는 성, 연령, 혼인상태, 교육수준, 소득수준, 흡연, 음주, 주1회 이상의 정기적인 운동, 월평균 사회활동 참여시간, 주관적 건강, 고혈압, 당뇨병을 포함하였다. 예측모형의 개발은 Restricted Boltzmann Machine(RBM) 인공신경망을 이용하였다. RMB 인공신경망을 이용하여 우리나라 지역사회 노인의 MCI 예측 모형을 구축한 결과, 유의미한 요인은 연령, 성별, 최종학력, 주관적 건강, 혼인상태, 소득수준, 흡연, 규칙적 운동이었다. 이 결과를 기초로 MCI 고위험군의 특성을 고려한 맞춤형 치매 예방 프로그램의 개발이 요구된다.

• Clinical Nutrition Research
• /
• 제12권2호
• /
• pp.138-153
• /
• 2023

The prevalence of metabolic syndrome (MetS) and its cost are increasing due to lifestyle changes and aging. This study aimed to develop a deep neural network model for prediction and classification of MetS according to nutrient intake and other MetS-related factors. This study included 17,848 individuals aged 40-69 years from the Korea National Health and Nutrition Examination Survey (2013-2018). We set MetS (3-5 risk factors present) as the dependent variable and 52 MetS-related factors and nutrient intake variables as independent variables in a regression analysis. The analysis compared and analyzed model accuracy, precision and recall by conventional logistic regression, machine learning-based logistic regression and deep learning. The accuracy of train data was 81.2089, and the accuracy of test data was 81.1485 in a MetS classification and prediction model developed in this study. These accuracies were higher than those obtained by conventional logistic regression or machine learning-based logistic regression. Precision, recall, and F1-score also showed the high accuracy in the deep learning model. Blood alanine aminotransferase (β = 12.2035) level showed the highest regression coefficient followed by blood aspartate aminotransferase (β = 11.771) level, waist circumference (β = 10.8555), body mass index (β = 10.3842), and blood glycated hemoglobin (β = 10.1802) level. Fats (cholesterol [β = -2.0545] and saturated fatty acid [β = -2.0483]) showed high regression coefficients among nutrient intakes. The deep learning model for classification and prediction on MetS showed a higher accuracy than conventional logistic regression or machine learning-based logistic regression.

• 한국IT서비스학회지
• /
• 제21권3호
• /
• pp.63-72
• /
• 2022

The extinction crisis of local cities, caused by a population density increase phenomenon in capital regions, directly causes the increase of vacant houses in local cities. According to population and housing census, Gunsan-si has continuously shown increasing trend of vacant houses during 2015 to 2019. In particular, since Gunsan-si is the city which suffers from doughnut effect and industrial decline, problems regrading to vacant house seems to exacerbate. This study aims to provide a foundation of a system which can predict and deal with the building that has high risk of becoming vacant house through implementing a data driven vacant house prediction machine learning model. Methodologically, this study analyzes three types of machine learning model by differing the data components. First model is trained based on building register, individual declared land value, house price and socioeconomic data and second model is trained with the same data as first model but with additional POI(Point of Interest) data. Finally, third model is trained with same data as the second model but with excluding water usage and electricity usage data. As a result, second model shows the best performance based on F1-score. Random Forest, Gradient Boosting Machine, XGBoost and LightGBM which are tree ensemble series, show the best performance as a whole. Additionally, the complexity of the model can be reduced through eliminating independent variables that have correlation coefficient between the variables and vacant house status lower than the 0.1 based on absolute value. Finally, this study suggests XGBoost and LightGBM based machine learning model, which can handle missing values, as final vacant house prediction model.

• Journal of the Korean Data and Information Science Society
• /
• 제23권6호
• /
• pp.1117-1125
• /
• 2012

식중독 발생에 대한 기존 연구에서는 기온과 습도와 같은 기후변수가 주된 설명변수로 취급되어 왔다. 이 논문에서는 주별 식중독 발생건수와 기후변수 간에 관계를 고찰하고 식중독 발생건수를 예측하기 위한 모형으로 포아송 회귀모형과 자기회귀이동평균모형을 비교한다. 비교결과 우리나라 식중독 발생은 시차를 두고 기후 변수에 영향을 많이 받고 있으나 식중독 발생 예측은 이들 변수보다 이전 시점의 식중독 발생 건수에 더 많이 영향을 받는 것으로 나타났으며 포아송 회귀모형은 예측의 관점에서 문제가 있음을 보였다.

• Journal of Welding and Joining
• /
• 제15권3호
• /
• pp.118-127
• /
• 1997

With the trend towards welding automation and robotization, mathematical models for studying the influence of various variables on the weld bead geometry in gas metal arc (GMA) welding process are required. Partial penetration, single-pass bead-on-plate welds using the GMA welding process were fabricated in 12mm mild steel plates employed four different process variables. Experimental results has been designed to investigate the analytical and empirical formulae, and develop mathematical equations for understanding the relationship between process variables and weld bead geometry. The relationships can be usefully employed not only for open loop process control, but also for adaptive control provided that dynamic sensing of process output is performed.

• Asian-Australasian Journal of Animal Sciences
• /
• 제33권4호
• /
• pp.615-622
• /
• 2020

Objective: The objectives were to investigate correlations between energy digestibility (digestible energy [DE]:gross energy [GE]) and various fiber types including crude fiber (CF), total dietary fiber (TDF), soluble dietary fiber (SDF), insoluble dietary fiber (IDF), neutral detergent fiber (NDF), and acid detergent fiber (ADF), and to develop prediction equations for estimating DE in feed ingredients and diets for growing pigs. Methods: A total of 289 data with DE values and chemical composition of feeds from 39 studies were used to develop prediction equations for DE. The equations were validated using values provided by the National Research Council. Results: The DE values in feed ingredients ranged from 2,011 to 4,590 kcal/kg dry matter (DM) and those in diets ranged from 2,801 to 4,203 kcal/kg DM. In feed ingredients, DE:GE was negatively correlated (p<0.001) with NDF (r = -0.84), IDF (r = -0.83), TDF (r = -0.82), ADF (r = -0.78), and CF (r = -0.72). A best-fitting model for DE (kcal/kg) in feed ingredients was: 1,356 + (0.704 × GE, kcal/kg) - (60.3 × ash, %) - (27.7 × NDF, %) with R² = 0.80 and p<0.001. In diets, DE:GE was negatively correlated (p<0.01) with NDF (r = -0.72), IDF (r = -0.61), TDF (r = -0.52), CF (r = -0.45), and ADF (r = -0.34). A best-fitting model for DE (kcal/kg) in diets was: 1,551 + (0.606 × GE, kcal/kg) - (22.1 × ash, %) - (25.6 × NDF, %) with R² = 0.62 and p<0.001. All variables are expressed as DM basis. The equation developed for DE in feed ingredients had greater accuracy than a published equation for DE. Conclusion: All fiber types are reasonably good independent variables for predicting DE of swine feeds. The best-fitting model for predicting DE of feeds employed neutral detergent fiber as an independent variable.

• 한국전자거래학회지
• /
• 제23권2호
• /
• pp.33-47
• /
• 2018

도시가스 배관은 지중에 매설되어 있기 때문에 세부 관리가 어렵고 다양한 위험에 노출되어 있다. 본 연구에서는 도시가스 배관압력 실시간 데이터를 분석해 배관압력 이상을 예측하고 전문가의 의사결정을 돕는 모델을 제안한다. 국내 도시가스 공급업체들 중 하나인 중부도시가스사의 정압기에서 수집하는 실시간 배관압력 데이터와 시간변수, 외부환경변수를 통합해 분석 데이터로 사용한다. 아산시와 천안시에 위치하는 11개 정압기를 분석 대상으로 하며 분 단위 배관압력 예측모델을 구현한다. Random forest, support vector regression(SVR), long-short term memory(LSTM) 알고리즘을 사용해 회귀모델을 구현한 결과 LSTM 모델에서 우수한 성능을 보인다. 아산시 배관압력 예측모델의 경우 LSTM 모델에서 RMSE가 0.011, MAPE가 0.494이며, 천안시 배관압력 예측모델의 경우 LSTM 모델에서 평균제곱근오차(root mean square error, RMSE)가 0.015, 절대평균백분율오차(mean absolute percentage error, MAPE)가 0.668로 가장 낮은 오류율을 보인다.

• 한국수자원학회논문집
• /
• 제34권3호
• /
• pp.275-285
• /
• 2001

우리 나라 갈수기의 하천유출은 대부분 지하수에서 공급되는 유출이므로 홍수기 강우량에 의해 침투한 유역의 수분상태에 지배된다. 따라서, 홍수기의 지하수 함양량 추정을 통한 유역 상태 정보를 이용한다면 갈수기 월유출 예측을 만족스럽게 수행할 수 있는 수문학적 환경을 가지고 있다. 본 연구의 목적은 지하수 함양량에 의한 월유출량의 영향을 평가하고, 이를 다중회귀모형의 독립변수로 이용하여 장기 월유출량 예측을 시도하는 것이다. 해당 월의 유출량, 강수량, 선행 유출량과 강수량 및 지하수 함양량의 상관분석을 이용하여 다중회귀모형의 최적독립변수들을 평가하였다. 지하수 함양량을 독립변수로 포함한 모형에서 향상된 예측결과를 얻었다. 또한, 사전에 파악된 강수량과 지하수함량의 관계를 이용하여 지하수 유출 이월효과를 고려하면서 강수량만으로 유출 예측모형을 개발할 수 있음을 제시하였다.

• Computers and Concrete
• /
• 제12권2호
• /
• pp.187-209
• /
• 2013

This paper presents a study on the prediction of transfer length of 13 mm seven-wire prestressing steel strand in pretensioned prestressed concrete members with rectangular cross-section including several material properties and design and manufacture parameters. To this end, a carefully selected database consisting of 207 different cases coming from 18 different sources spanning a variety of practical transfer length prediction situations was compiled. 16 single input features and 5 combined input features are analyzed. A widely used feedforward neural regression model was considered as a representative of several machine learning methods that have already been used in the engineering field. Classical multiple linear regression was also considered in order to comparatively assess performance and robustness in this context. The results show that the implemented model has good prediction and generalization capacity when it is used on large input data sets of practical interest from the engineering point of view. In particular, a neural model is proposed -using only 4 hidden units and 10 input variables-which significantly reduces in 30% and 60% the errors in transfer length prediction when using standard linear regression or fixed formulas, respectively.

• 인터넷정보학회논문지
• /
• 제19권6호
• /
• pp.101-112
• /
• 2018

A lot of manpower and budgets are being used to prevent fires, and only a small portion of the data generated during this process is used for disaster prevention activities. This study develops a prediction model of fire occurrence probability based on data mining in order to more actively use these data for disaster prevention activities. For this purpose, variables for predicting fire occurrence probability of various buildings were selected and data of construction administrative system, national fire information system, and Korea Fire Insurance Association were collected and integrated data set was constructed. After appropriate data cleansing and preprocessing, various data mining methodologies such as artificial neural network, decision trees, SVM, and Naive Bayesian were used to develop a prediction model of the fire occurrence probability of buildings. The most accurate model among the derived models is Linear SVM model which shows 68.42% as experimental data and 63.54% as verification data and it is the best model to predict fire occurrence probability of buildings. As this study develops the prediction model which uses only the set values of the specific ranges, future studies may explore more opportunites to use various setting values not shown in this study.