• Journal of the Korean Data and Information Science Society
• /
• v.22 no.2
• /
• pp.197-206
• /
• 2011

The ability to detect online abnormal events in signals is essential in many real-world signal processing applications. In order to detect abnormal events, previously known algorithms require an explicit signal statistical model, and interpret abnormal events as statistical model abrupt changes. In general, maximum likelihood and Bayesian estimation theory to estimate well as detection methods have been used. However, the above-mentioned methods for robust and tractable model, it is not easy to estimate. More freedom to estimate how the model is needed. In this paper, we investigate a machine learning, descriptor-based approach that does not require a explicit descriptors statistical model, based on support vector machines are known to be robust statistical models and a sequential optimal algorithm online support vector machine is introduced.

• Nuclear Engineering and Technology
• /
• v.39 no.6
• /
• pp.703-716
• /
• 2007

As digital and computer technologies have grown, human-machine interfaces (HMIs) have evolved. In safety-critical systems, especially in nuclear power plants (NPPs), HMIs are important for reducing operational costs, the number of necessary operators, and the probability of accident occurrence. Efforts have been made to improve main control room (MCR) interface design and to develop automated or decision support systems to ensure convenient operation and maintenance. In this paper, an integrated decision support system to aid operator cognitive processes is proposed for advanced MCRs of future NPPs. This work suggests the design concept of a decision support system which accounts for an operator's cognitive processes. The proposed system supports not only a particular task, but also the entire operation process based on a human cognitive process model. In this paper, the operator's operation processes are analyzed according to a human cognitive process model and appropriate support systems that support each cognitive process activity are suggested.

• Journal of Korean Academy of Nursing
• /
• v.45 no.1
• /
• pp.97-106
• /
• 2015

Purpose: This study was done to develop and test a structural model for caregiving experience including caregiving satisfaction and caregiving strain in families providing care for family members with a mental disorder. Methods: The Stress-appraisal-coping model was used as the conceptual framework and the structural equation model to confirm the path that explains what and how variables affect caregiving experience in these families. In this hypothesis model, exogenous variables were optimism, severity of illness and uncertainty. The endogenous variables were self efficacy, social support, caregiving satisfaction and caregiving strain. Data were collected using structured questionnaires. Results: Optimism and caregiving self-efficacy had significant direct and indirect effects on caregiving satisfaction. Optimism, severity of illness and uncertainty had significant direct and indirect effects on caregiving strain. The modified path model explained effects of optimism on caregiving self-efficacy with social support in the path structure as a mediator. Also, there were direct and indirect effects of optimism and uncertainty on caregiving satisfaction with social support and caregiving self-efficacy in the path structure as a mediators. Conclusion: Results suggest the need to improve caregiving self-efficacy of these families, establish support systems such as a mental health professional support programs for caregiving self-efficacy. Optimism, severity of illness and uncertainty perceived by families need to be considered in the development of support programs in order to increase their effectiveness.

• Research in Community and Public Health Nursing
• /
• v.11 no.2
• /
• pp.321-332
• /
• 2000

The purpose of this study was to test the hypothetical model designed to explain nursing students' perceived stress, coping levels, and stress outcomes. This hypothetical model was based on the Kim. Jung Hee(l987)' s stress model and stress-related literature. Exogenous variables were self-efficacy. hardiness. social support. and exercise. Endogenous variables were stress perception. coping levels. and stress outcomes. Empirical data for testing the hypothetical model consisted of 205 nursing students. SAS PC Program and LISREL 8.12a program were used for descriptive statistics and linear structural relationship(LISREL) modeling. The results were as follows. 1) The overall fit of the hypothetical model to the data was good( $x^2$=78.41(p=0.010), $x^2$/ df=1.50. RMSEA=0.05, standardized RMR= 0.05, GFI=0.95, AGFI=0.91, NNFI=0.90, NFI=0.94). 2) The results of statistical testing of the hypotheses were as follows. (1) As expected. self-efficacy had a significant effect on stress perception. But. hardiness. social support, and exercise did not have a significant effect on stress perception. Self-efficacy, hardiness. social support, and exercise explained 12% of the total variance of stress perception. (2) As expected, self-efficacy, hardiness, social support, exercise, and stress perception had a significant effect on coping behavior, Self-efficacy, hardiness, social support, exercise, and stress perception explained 53% of the total variance of coping behavior. (3) As expected, stress perception and coping behavior had a significant effect on stress outcomes. Stress perception and coping behavior explained 84% of the total variance of stress outcomes. In conclusion, the hypothetical model of this study was confirmed in explaining and predicting stress perception, coping levels, and stress outcomes in nursing students. And these findings suggest the need to develop nursing intervention to enhance self-efficacy, hardiness, social support, and exercise to decrease the harmful outcomes of stress.

• Journal of the Korean Data and Information Science Society
• /
• v.17 no.3
• /
• pp.821-830
• /
• 2006

This paper develops support vector based fuzzy linear and nonlinear regression models and applies it to forecasting the exchange rate. We use the result of Tanaka(1982, 1987) for crisp input and output. The model makes it possible to forecast the best and worst possible situation based on fewer than 50 observations. We show that the developed model is good through real data.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2015.05a
• /
• pp.475-478
• /
• 2015

The objective of this study is to apply a hybrid model for estimating solar radiation and investigate their accuracy. A hybrid model is wavelet-based support vector machines (WSVMs). Wavelet decomposition is employed to decompose the solar radiation time series into approximation and detail components. These decomposed time series are then used as inputs of support vector machines (SVMs) modules in the WSVMs model. Results obtained indicate that WSVMs can successfully be used for the estimation of daily global solar radiation at Champaign and Springfield stations in Illinois.

• The Journal of the Korea Contents Association
• /
• v.17 no.8
• /
• pp.570-578
• /
• 2017

This study aims to develop suitable and appropriate support models for ADHD children to provide effective and efficient support for the target children. The diverse characteristics of target area, educational, social conditions, and supporting organization and delivery systems have been comprehensively considered. Domestic and overseas literature review has been performed to analyze the status of support services for ADHD children to develop the model. The FGI was adapted to identify eligibility and expectations for the qualification of ADHD children and the awareness and expectations of relevant professionals. Based on the theoretical rationale and empirical analysis results derived from these systematic procedures, suitable and appropriate support models were developed for ADHD children as a special educational subjects. The support model includes the development of individualized support programs for the needs of the entire ADHD student population, which require screening and assessment of the entire student population and requiring support for special needs. Support methods were developed in a system that supports family support, educational support, medical assistance, and medical support.

• Journal of the Korean Society for Railway
• /
• v.5 no.4
• /
• pp.244-252
• /
• 2002

We must notice ground movement by excavation for reasonable tunnel designs. The convergence confinement method is an attempt to evaluate tunnel stability conditions by means of a mathematical model and a ground response curve. In this study, the convergence confinement method by numerical model was examined. This method don't need the basic assumptions for a mathematical model of circular tunnel shape, and hydrostatic in situ stress. Also modified ground response curve that is calculated after installing the support, is suggested, which informs us the ground movement mechanism. The ground response curve and the support reaction curve are mutually dependent. Especially the support reaction curve depends upon the ground response curve. The mechanism of tunnel must be analyzed by the interaction between support and ground. Consequently the stability of tunnel must be qualitatively investigated by a ground response curve and quantitatively adjudged by a numerical analysis for the reasonable design of tunnel.

• Journal of Families and Better Life
• /
• v.31 no.4
• /
• pp.65-82
• /
• 2013

This study focuses on the roles of family and parents as primary environments for character education of children and adolescents, examines surrounding micro and macro environments in a bioecological model, and explores parent support methods for restoring character education in family. For this study, we had interviews with 54 parents(44 mothers & 10 fathers). Through the interviews we found difficulties of character education in family and analyzed them in children and teenagers, parents, school, and social-cultural dimensions based on the bioecological model. On the basis of the parents' perception for these difficulties, we proposed how to support the roles of family and parents for recovering character education in family. The policy methods were propsed in family, school, and society dimensions. This study is meaningful in that it suggests evidence base for making the parent support policy.

• Korean Management Science Review
• /
• v.23 no.2
• /
• pp.75-91
• /
• 2006

The purpose of this paper is to propose a new software development cost estimation method using SVR(Support Vector Regression) SVR, one of machine learning techniques, has been attracting much attention for its theoretic clearness and food performance over other machine learning techniques. This paper may be the first study in which SVR is applied to the field of software cost estimation. To derive the new method, we analyze historical cost data including both well-known overseas and domestic software projects, and define cost drivers affecting software cost. Then, the SVR model is trained using the historical data and its estimation accuracy is compared with that of the linear regression model. Experimental results show that the SVR model produces more accurate prediction than the linear regression model.