• International Journal of Control, Automation, and Systems
• /
• v.2 no.4
• /
• pp.423-434
• /
• 2004

In this paper, we introduce a new topology of Self-Organizing Polynomial Neural Networks (SOPNN) based on genetically optimized Multi-Layer Perceptron (MLP) and discuss its comprehensive design methodology involving mechanisms of genetic optimization. Let us recall that the design of the 'conventional' SOPNN uses the extended Group Method of Data Handling (GMDH) technique to exploit polynomials as well as to consider a fixed number of input nodes at polynomial neurons (or nodes) located in each layer. However, this design process does not guarantee that the conventional SOPNN generated through learning results in optimal network architecture. The design procedure applied in the construction of each layer of the SOPNN deals with its structural optimization involving the selection of preferred nodes (or PNs) with specific local characteristics (such as the number of input variables, the order of the polynomials, and input variables) and addresses specific aspects of parametric optimization. An aggregate performance index with a weighting factor is proposed in order to achieve a sound balance between the approximation and generalization (predictive) abilities of the model. To evaluate the performance of the GA-based SOPNN, the model is experimented using pH neutralization process data as well as sewage treatment process data. A comparative analysis indicates that the proposed SOPNN is the model having higher accuracy as well as more superb predictive capability than other intelligent models presented previously.reviously.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.18 no.4
• /
• pp.227-235
• /
• 2018

The purpose of this study was to analyze the factors affecting on pre-service early childhood teachers' adoption intention of Robot-based education. For this purpose, the survey was conducted on 259 college students and the collected data was analyzed using SPSS 23.0. T-test and one-way ANOVA were used to compare the differences of adoption intention and predictive factors according to pre-service early childhood teachers' background variables. In addition, multiple linear regression analysis was conducted to analyze influence of perceived ease of use, perceived efficacy, innovative will, and social effect on adoption intention. The results were found that adoption intention and predictive factors did not show any significant difference according to background variables and that perceived ease of use and perceived efficacy influenced on pre-service early childhood teachers' adoption intention. Moreover, innovative will and social effect had an effect on perceived ease of use and perceived ease of use and social effect had an effect on perceived efficacy.

• 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.

• 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.

• 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.