• Journal of Institute of Control, Robotics and Systems
• /
• v.8 no.2
• /
• pp.126-135
• /
• 2002

The study is concerned with an approach to the design of new architectures of fuzzy neural networks and the discussion of comprehensive design methodology supporting their development. We propose an Adaptive Fuzzy Polynomial Neural Networks(APFNN) based on Fuzzy Neural Networks(FNN) and Self-organizing Networks(SON) for model identification of complex and nonlinear systems. The proposed AFPNN is generated from the mutually combined structure of both FNN and SON. The one and the other are considered as the premise and the consequence part of AFPNN, respectively. As the premise structure of AFPNN, FNN uses both the simplified fuzzy inference and error back-propagation teaming rule. The parameters of FNN are refined(optimized) using genetic algorithms(GAs). As the consequence structure of AFPNN, SON is realized by a polynomial type of mapping(linear, quadratic and modified quadratic) between input and output variables. In this study, we introduce two kinds of AFPNN architectures, namely the basic and the modified one. The basic and the modified architectures depend on the number of input variables and the order of polynomial in each layer of consequence structure. Owing to the specific features of two combined architectures, it is possible to consider the nonlinear characteristics of process system and to obtain the better output performance with superb predictive ability. The availability and feasibility of the AFPNN are discussed and illustrated with the aid of two representative numerical examples. The results show that the proposed AFPNN can produce the model with higher accuracy and predictive ability than any other method presented previously.

• Journal of Periodontal and Implant Science
• /
• v.46 no.1
• /
• pp.10-21
• /
• 2016

Purpose: This study evaluated the predictive performance of a combination of self-report questionnaires, salivary hemoglobin levels, and age as a non-invasive screening method for periodontitis. Methods: The periodontitis status of 202 adults was examined using salivary hemoglobin levels, responses to 10 questions on a self-report questionnaire, and the Community Periodontal Index (CPI). The ability of those two variables and the combination thereof with age to predict the presence of CPI scores of 3-4 and 4 was assessed using logistic regression and receiver operating characteristic (ROC) curve analysis. Results: CPI scores of 3-4 and 4 were present among 79.7% and 46.5% of the sample, respectively. The area under the ROC curves (AUROCs) of salivary hemoglobin levels for predicting prevalence of CPI scores of 3-4 and 4 were 0.63 and 0.67, respectively (with sensitivity values of 71% and 60% and specificity values of 56% and 72%, respectively). Two distinct sets of five questions were associated with CPI scores of 3-4 and 4, with AUROCs of 0.73 and 0.71, sensitivity values of 76% and 66%, and specificity values of 63% and 69%. The combined model incorporating both variables and age showed the best predictive performance, with AUROCs of 0.78 and 0.76, sensitivity values of 71% and 65%, and specificity values of 68% and 77% for CPI scores of 3-4 and 4, respectively. Conclusions: The combination of salivary hemoglobin levels and self-report questionnaires was shown to be a valuable screening method for detecting periodontitis.

• Geomechanics and Engineering
• /
• v.25 no.1
• /
• pp.1-16
• /
• 2021

Machine learning models have been widely used for landslide susceptibility assessment (LSA) in recent years. The large number of inputs or conditioning factors for these models, however, can reduce the computation efficiency and increase the difficulty in collecting data. Feature selection is a good tool to address this problem by selecting the most important features among all factors to reduce the size of the input variables. However, two important questions need to be solved: (1) how do feature selection methods affect the performance of machine learning models? and (2) which feature selection method is the most suitable for a given machine learning model? This paper aims to address these two questions by comparing the predictive performance of 13 feature selection-based machine learning (FS-ML) models and 5 ordinary machine learning models on LSA. First, five commonly used machine learning models (i.e., logistic regression, support vector machine, artificial neural network, Gaussian process and random forest) and six typical feature selection methods in the literature are adopted to constitute the proposed models. Then, fifteen conditioning factors are chosen as input variables and 1,017 landslides are used as recorded data. Next, feature selection methods are used to obtain the importance of the conditioning factors to create feature subsets, based on which 13 FS-ML models are constructed. For each of the machine learning models, a best optimized FS-ML model is selected according to the area under curve value. Finally, five optimal FS-ML models are obtained and applied to the LSA of the studied area. The predictive abilities of the FS-ML models on LSA are verified and compared through the receive operating characteristic curve and statistical indicators such as sensitivity, specificity and accuracy. The results showed that different feature selection methods have different effects on the performance of LSA machine learning models. FS-ML models generally outperform the ordinary machine learning models. The best FS-ML model is the recursive feature elimination (RFE) optimized RF, and RFE is an optimal method for feature selection.

• Journal of Korean Academy of Nursing
• /
• v.50 no.6
• /
• pp.799-812
• /
• 2020

Purpose: This study aimed to construct and test a predictive model that explains and predicts the quality of life in older men living alone. Methods: A self-report questionnaire was used to collect data from 334 older adult men living along aged 65 years or over living in Jeollanam-do provinces. The endogenous variables were depression, self-rated health, instrumental activity of daily life, health promotion behaviors, the number of social participation activities and quality of life. Data were analyzed using the SPSS 21.0 and AMOS 21.0 programs. Results: The final model with 14 of the 8 analysed paths showed a good fit to the empirical data: χ2 = 173.26(p < .001, df = 53), normed χ2 = 3.27, GFI = .92, NFI = .90, CFI = .93, TLI = .89, RMSEA = .08 and SRMR = .06. Activities had direct effect on quality of life of older men living alone and social support had both direct and indirect effects. Meanwhile, function and socioeconomic status showed only indirect effects. The variables included in the eight significant paths explained 83.7% of variance in the prediction model. Conclusion: Instrumental activities of daily living and social support effect directly on quality of life in the older men living alone. Findings suggest that health care providers including community nurses need to provide social support as well as empowerment programs of instrumental activities of daily living and health promotion for improving quality of life of the older men living alone.

• Journal of The Korean Association of Information Education
• /
• v.24 no.6
• /
• pp.597-606
• /
• 2020

Recently, as students' programming classes are being conducted online, interest in factors that can lead to the success of online programming classes is also increasing. Therefore, in this study, online programming classes were conducted for specialized high school students using a web-based simulation programming tool through TinkerCad. In these online programming classes, students' self-regulation ability and learning flow were set as variables that influence both learning engagement and teaching presence, and the predictive power of each was analyzed. As a result, it was found that both self-regulation ability and learning flow were predictive variables for learning engagement and teaching presence, and that learning flow played a mediating role between self-regulation ability, learning engagement, and teaching presence. This study is meaningful in that it suggested that self-regulation ability and learning flow should be considered more meaningfully in online programming classes, and a practical strategy for this is presented.

• Journal of Korean Academy of Nursing
• /
• v.52 no.3
• /
• pp.308-323
• /
• 2022

Purpose: This study aimed to construct and test a predictive model for the quality of life (QOL) in mothers of children with developmental disabilities (DB). The hypothesized model included severity of illness, distress, uncertainty, self-help, and parenting efficacy as influencing factors, QOL as a consequence based on the Braden's Self-Help Model. Methods: The data were collected through a direct and online surveys from 206 mothers in 8 locations, including welfare or daycare centers, developmental treatment centers, and The Parents' Coalition for the Disabled located in two provinces of Korea. Data were analysed using SPSS/WIN 23.0 and AMOS 21.0 program. Results: The fit indices of the predictive model satisfied recommended levels; 𝛘² = 165.79 (p < .001), normed 𝛘² (𝛘²/df) = 2.44, RMR = .04, RMSEA = .08, GFI = .90, AGFI = .85, NFI = .91, TLI = .93, CFI = .95. Among the variables, distress (β = - .46, p < .001), parenting efficacy (β = .22, p < .001), and self-help (β = .17, p = .018) had direct effects on QOL. Severity of illness (β = - .61, p = .010) and uncertainty (β = - .08, p = .014) showed indirect effects. The explanatory power of variables was 61.0%. Conclusion: The study results confirm the utility of Braden's Self-Help Model. They provide a theoretical basis for improving QOL in mothers of children with DB. Nursing intervention strategies that can relieve mothers' distress and uncertainty related to disease and enhance parenting efficacy and self-help behavior should be considered.

• Knowledge Management Research
• /
• v.24 no.4
• /
• pp.63-85
• /
• 2023

This study aims to identify the primary user group in the growing metaverse space based on the increased interest during the COVID-19 era. It also aims to explore the predictive factors for metaverse adoption. To predict online activities, the study examined user purposes, motivations, and relevant demographic factors as predictive variables through model analysis. The data from the Korean Media Panel Survey were used, and a two-stage analysis with the Heckman two-stage sample selection model was conducted to predict metaverse users. The analysis revealed that the key factors influencing metaverse adoption were offline activities, openness, OTT usage, and purchasing of paid content. Moreover, in the second stage model, openness, gender, and paid content purchases were identified as significant variables for increasing metaverse usage time. These results indicate that understanding metaverse users is essential in the context of the rising interest in online activities during the COVID-19 era and can provide valuable insights for metaverse platform-related companies and developers.

• Journal of Korean Academy of Nursing
• /
• v.54 no.2
• /
• pp.193-210
• /
• 2024

Purpose: The objective of this study was to develop a predictive model for the sexual experiences of adolescents using the random forest method and to identify the "variable importance." Methods: The study utilized data from the 2019 to 2021 Korea Youth Risk Behavior Web-based Survey, which included 86,595 man and 80,504 woman participants. The number of independent variables stood at 44. SPSS was used to conduct Rao-Scott χ² tests and complex sample t-tests. Modeling was performed using the random forest algorithm in Python. Performance evaluation of each model included assessments of precision, recall, F1-score, receiver operating characteristics curve, and area under the curve calculations derived from the confusion matrix. Results: The prevalence of sexual experiences initially decreased during the COVID-19 pandemic, but later increased. "Variable importance" for predicting sexual experiences, ranked in the top six, included week and weekday sedentary time and internet usage time, followed by ease of cigarette purchase, age at first alcohol consumption, smoking initiation, breakfast consumption, and difficulty purchasing alcohol. Conclusion: Education and support programs for promoting adolescent sexual health, based on the top-ranking important variables, should be integrated with health behavior intervention programs addressing internet usage, smoking, and alcohol consumption. We recommend active utilization of the random forest analysis method to develop high-performance predictive models for effective disease prevention, treatment, and nursing care.

• Tuberculosis and Respiratory Diseases
• /
• v.58 no.3
• /
• pp.230-242
• /
• 2005

Background : Spirometry should be compared with the normal predictive values obtained from the same population using the same procedures, because different ethnicity and different procedures are known to influence the spirometry results. This study was performed to obtain the normal predictive values of the Forced Vital Capacity(FVC), Forced Expiratory Volume in 1 Second($FEV_1$), Forced Expiratory Volume in 6 Seconds($FEV_6$), and $FEV_1/FVC$ for a representative Korean population. Methods : Based on the 2000 Population Census of the National Statistical Office of Korea, stratified random sampling was carried out to obtain representative samples of the Korean population. This study was performed as a part of the National Health and Nutrition Survey of Korea in 2001. The lung function was measured using the standardized methods and protocols recommended by the American Thoracic Society. Among those 4,816 subjects who had performed spirometry performed, there was a total of 1,212 nonsmokers (206 males and 1,006 females) with no significant history of respiratory diseases and symptoms, with clear chest X-rays, and with no significant exposure to respiratory hazards subjects. Their residence and age distribution was representative of the whole nation. Mixed effect models were examined based on the Akaike's information criteria in statistical analysis, and those variables common to both genders were analyzed by regression analysis to obtain the final equations. Results : The variables affecting the normal predicted values of the FVC and $FEV_6$ for males and females were $age^2$, height, and weight. The variables affecting the normal predicted values of the $FEV_1$ for males and females were $age^2$, and height. The variables affecting the normal predicted values of the $FEV_1/FVC$ for male and female were age and height. Conclusion : The predicted values of the FVC and $FEV_1$ was higher in this study than in other Korean or foreign studies, even though the difference was < 10%. When compared with those predicted values for Caucasian populations, the study results were actually comparable or higher, which might be due to the stricter criteria of the normal population and the systemic quality controls applied to the whole study procedures together with the rapid physical growth of the younger generations in Korea.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.34 no.2
• /
• pp.35-54
• /
• 2009

The recent economic crisis not only reduces the profit of department stores but also incurs the significance losses caused by the increasing late-payment rate of credit cards. Under this pressure, the scope of credit prediction needs to be broadened from the simple prediction of whether this customer has a good credit or not to the accurate prediction of how much profit can be gained from this customer. This study classifies the delinquent customers of credit card in a Korean department store into homogeneous clusters. Using this information, this study analyzes the repayment patterns for each cluster and develops the credit prediction system to manage the delinquent customers. The model presented by this study uses Kohonen network, which is one of artificial neural networks of data mining technique, to cluster the credit delinquent customers into clusters. Cox proportional hazard model is also used, which is one of survival analysis used in medical statistics, to analyze the repayment patterns of the delinquent customers in each cluster. The presented model estimates the repayment period of delinquent customers for each cluster and introduces the influencing variables on the repayment pattern prediction. Although there are some differences among clusters, the variables about the purchasing frequency in a month and the average number of installment repayment are the most predictive variables for the repayment pattern. The accuracy of the presented system leaches 97.5%.