• Steel and Composite Structures
• /
• 제51권6호
• /
• pp.679-695
• /
• 2024

This paper presents a novel technique that combines machine learning (ML) with moth-flame optimization (MFO) methods to predict the axial compressive strength (ACS) of concrete filled double skin steel tubes (CFDST) columns. The proposed model is trained and tested with a dataset containing 125 tests of the CFDST column subjected to compressive loading. Five ML models, including extreme gradient boosting (XGBoost), gradient tree boosting (GBT), categorical gradient boosting (CAT), support vector machines (SVM), and decision tree (DT) algorithms, are utilized in this work. The MFO algorithm is applied to find optimal hyperparameters of these ML models and to determine the most effective model in predicting the ACS of CFDST columns. Predictive results given by some performance metrics reveal that the MFO-CAT model provides superior accuracy compared to other considered models. The accuracy of the MFO-CAT model is validated by comparing its predictive results with existing design codes and formulae. Moreover, the significance and contribution of each feature in the dataset are examined by employing the SHapley Additive exPlanations (SHAP) method. A comprehensive uncertainty quantification on probabilistic characteristics of the ACS of CFDST columns is conducted for the first time to examine the models' responses to variations of input variables in the stochastic environments. Finally, a web-based application is developed to predict ACS of the CFDST column, enabling rapid practical utilization without requesting any programing or machine learning expertise.

• Steel and Composite Structures
• /
• 제52권2호
• /
• pp.145-163
• /
• 2024

This paper presents six novel hybrid machine learning (ML) models that combine support vector machines (SVM), Decision Tree (DT), Random Forest (RF), Gradient Boosting (GB), extreme gradient boosting (XGB), and categorical gradient boosting (CGB) with the Harris Hawks Optimization (HHO) algorithm. These models, namely HHO-SVM, HHO-DT, HHO-RF, HHO-GB, HHO-XGB, and HHO-CGB, are designed to predict the ultimate strength of both rectangular and circular reinforced concrete (RC) columns. The prediction models are established using a comprehensive database consisting of 325 experimental data for rectangular columns and 172 experimental data for circular columns. The ML model hyperparameters are optimized through a combination of cross-validation technique and the HHO. The performance of the hybrid ML models is evaluated and compared using various metrics, ultimately identifying the HHO-CGB model as the top-performing model for predicting the ultimate shear strength of both rectangular and circular RC columns. The mean R-value and mean a20-index are relatively high, reaching 0.991 and 0.959, respectively, while the mean absolute error and root mean square error are low (10.302 kN and 27.954 kN, respectively). Another comparison is conducted with four existing formulas to further validate the efficiency of the proposed HHO-CGB model. The Shapely Additive Explanations method is applied to analyze the contribution of each variable to the output within the HHO-CGB model, providing insights into the local and global influence of variables. The analysis reveals that the depth of the column, length of the column, and axial loading exert the most significant influence on the ultimate shear strength of RC columns. A user-friendly graphical interface tool is then developed based on the HHO-CGB to facilitate practical and cost-effective usage.

• Nutrition Research and Practice
• /
• 제2권1호
• /
• pp.35-40
• /
• 2008

A cross-sectional study involving 400 mothers was conducted in the Manya Krobo district of Ghana with the objective of studying household dietary practices, quality of diets and family nutritional status of rural Ghana, A combination of methods, including structured interviews using questionnaire, dietary assessments and anthropometry was used to collect data for the study. The data obtained was analyzed using Statistical Package for Social Sciences (SPSS) Version 10 in Windows. Means and standard deviations were generated for continuous variables and frequency distribution for categorical variables. Most women consumed meals three times a day but only a few (12.5%) cooked all three meals at home. Breakfast and lunch were the two main meals purchased from food vendors. The most frequently consumed food items on daily basis were the starchy staples, maize, fish, pepper, onion, tomato and palm fruits. The nutritional qualities of diets were poor in terms of calcium and the B-vitamins. A significant proportion of the women were nutritionally at risk of being either underweight (12%), overweight (17%) or obese (5%). For adequate nutrition in this population, nutrition education intervention programs aimed at improving nutrient intake through improved diet diversity and increased use of local foods rich in calcium and the B-vitamins needs to be undertaken. There is also the need to intensify education on excessive weight gain and its attendant health problems in the area.

• Nutrition Research and Practice
• /
• 제10권1호
• /
• pp.81-88
• /
• 2016

BACKGROUND/OBJECTIVES: Serum ferritin levels are significantly increased after menopause and greatly affect women's health. The aim of this study was to investigate the dietary and non-dietary factors associated with high ferritin levels in postmenopausal women. SUBJECTS/METHODS: Among adult women in 2010-2012, qualified postmenopausal women (n = 3880) were separated into quartiles of serum ferritin. The variable differences among the quartiles of ferritin were determined using either procsurvey chi-square test (${\chi}^2$-test) among categorical variables, or GLM (Generalized Linear Model) among continuous variables. The odds ratio for high ferritin in relation to dietary factors was also determined using procsurvery logistic analysis. RESULTS: Age, obesity, drinking habit, and blood glucose levels were found to be significant indicators of high serum ferritin level after adjusting for all confounding factors. Among the food groups, grain, milk, vegetable, and seaweed intakes were significantly associated with high ferritin levels, but after adjusting for all confounding factors, only grains and vegetables remained significant factors. Among the nutrient groups, calcium, vitamin A, and vitamin C intake were significant factors, but after adjustment, none of the nutrient groups analyzed were associated with a high risk of ferritin. CONCLUSION: Age, obesity, drinking habit, and glucose levels, as well as inadequate intakes of grains and vegetables, were found to be significantly associated with high serum ferritin levels in postmenopausal Korean women.

• 치위생과학회지
• /
• 제19권3호
• /
• pp.147-153
• /
• 2019

Background: With increased interest in oral health, several efforts have been made to improve oral health conditions. To achieve this, needs for oral health must be precisely determined and accurately measured. Therefore, factors influencing both objective unmet dental needs, which were determined by experts, and perceived unmet dental needs, which were determined by patients, were examined in this study. Methods: Responses of 17,735 respondents aged greater than 19 years from the Korean National Health and Nutrition Survey collected using the fifth (2010~2012) rotation sample survey were analyzed. Based on the information collected from the survey and dental examination, we determined the associations between the independent (sex and socioeconomic level) and dependent variables using a chi-squared test. Moreover, ordinal logistic regression analyses on multiple categorical values were performed using perceived and objective dental needs as the dependent variables. Results: Generally, factors influencing both perceived and objective dental needs were similar. These included sex, household income, educational level, private insurance, and subjective oral health status. However, the high-income groups had lesser perceived and objective dental needs compared to the low-income groups. Furthermore, factors such as sex, educational level, and marital status had different influence on both needs. Conclusion: Generally, factors that affect perceived and objective dental needs were similar. To minimize unmet dental needs, factors influencing both perceived and objective dental needs should be examined for a broad dental insurance coverage, and efforts to prevent oral diseases are also required.

• Journal of Korean Biological Nursing Science
• /
• 제21권2호
• /
• pp.152-159
• /
• 2019

Purpose: To understand awareness, attitude and knowledge levels of muscle health of adults over 18 years old. Methods: This study was a cross-sectional study using questionnaires. A total of 401 questionnaires were included for final analysis. Mean and standard deviation of the continuous variables were analyzed and frequency analysis of categorical variables was performed. To identify differences according to general characteristics, t-test was used. Results: Awareness scores about the importance of muscle health and exercises were 8.3 and 13.0, respectively. Attitude score and knowledge score were 12.4 and 15.0, respectively. There were differences in attitude toward muscle health according to gender, age, physical activity, and diet habits. However, there was no difference in attitude toward muscle health according to educational level, smoking, drinking, or sleeping. Conclusion: It is necessary to seek a strategy to improve awareness and attitude toward muscle health based on knowledge, not merely to raise knowledge level about muscle health. Since nurses play a central role in health promotion and disease prevention, they should also play an important role in strategic development and application of intervention.

• 한국식생활문화학회지
• /
• 제39권1호
• /
• pp.30-37
• /
• 2024

Consumption market research was conducted on gradually increasing vegetarians using various selection attributes. Factors were extracted to identify vegetarian selection attributes and to divide the study cohort into groups, continuous variables (health, animal welfare, eco-friendliness, religion, familiarity, convenience, stability, and cost) and categorical variables (age, marital status, vegetarian duration, and vegetarian frequency) were simultaneously subjected to two-step cluster analysis. Cluster 1 contained high proportions of 20-29 and 30-39 year-olds, which are MZ-generation age groups. A high proportion had a vegetarian duration of 1-3 years, and the popular reasons for vegetarian selection were animal welfare and eco-friendliness. Cluster 2 contained high proportions of 50-59 and 40-49 year-olds, and many in this cluster were married, and mean vegetarian duration was ≥15 years. In addition, significant differences were observed between Clusters 1 and 2 in terms of religion, health, familiarity, cost, stability, and convenience. This study should contribute significantly to predicting vegetarian consumers' selection decisions and consumption behaviors and provide reliable marketing data for foodservice companies that develop vegetarian foods.

• 응용통계연구
• /
• 제19권2호
• /
• pp.271-282
• /
• 2006

본 논문에서는 범주형과 연속형 변수들이 혼합된 데이터에 적용할 수 있는 나무형 군집화 알고리즘을 제안하였다. 특히 혼합된 변수들이 공통의 의미를 갖도록 하기 위해 범주형 변수들을 전처리하는 방법을 고안하였다. 수치 예로서 SPSS의 신용(credit) 데이터와 독일신용자료(German credit data)에 알고리즘을 적용하고 그 결과를 검토하였다.

• 한국경영과학회지
• /
• 제36권4호
• /
• pp.161-184
• /
• 2011

As movie demands become more and more diversified, it is necessary for movie related firms to segment a whole heterogeneous market into a number of small homogeneous markets in order to identify the specific needs of consumer groups. Relevant market segmentation helps them to develop valuable offer to target segments through effective marketing planning. In this article, we introduce various segmentation methods and compare their advantages and disadvantages. In particular, we analyze "2009~2010 consumer survey data of Korean Film Industry" by using Latent Class Analysis(LCA), a statistical segmentation method which identifies exclusive set of latent classes based on consumers' responses to an observed categorical and numerical variables. It is applied PROC LCA, a new SAS procedure for conducting LCA and finally get the result of 11 distinctive clusters showing unique characteristics on their buying behaviors.

• Journal of the Korean Data and Information Science Society
• /
• 제18권1호
• /
• pp.185-194
• /
• 2007

The information of covariates are available to do fully efficient fractional imputation(FEFI). The new method, FEFI with logistic regression is proposed to construct complete contingency tables. Jackknife method is used to get a standard errors of log-odds ratio from the completed table by the new method. Simulation results, when covariates have more information about categorical variables, reveal that the new method provides more efficient estimates of log-odds ratio than either multiple imputation(MI) based on data augmentation or complete case analysis.