• Nuclear Engineering and Technology
• /
• v.50 no.8
• /
• pp.1306-1313
• /
• 2018

The randomness and incipient nature of certain faults in reactor systems warrant a robust and dynamic detection mechanism. Existing models and methods for fault diagnosis using different mathematical/statistical inferences lack incipient and novel faults detection capability. To this end, we propose a fault diagnosis method that utilizes the flexibility of data-driven Support Vector Machine (SVM) for component-level fault diagnosis. The technique integrates separately-built, separately-trained, specialized SVM modules capable of component-level fault diagnosis into a coherent intelligent system, with each SVM module monitoring sub-units of the reactor coolant system. To evaluate the model, marginal faults selected from the failure mode and effect analysis (FMEA) are simulated in the steam generator and pressure boundary of the Chinese CNP300 PWR (Qinshan I NPP) reactor coolant system, using a best-estimate thermal-hydraulic code, RELAP5/SCDAP Mod4.0. Multiclass SVM model is trained with component level parameters that represent the steady state and selected faults in the components. For optimization purposes, we considered and compared the performances of different multiclass models in MATLAB, using different coding matrices, as well as different kernel functions on the representative data derived from the simulation of Qinshan I NPP. An optimum predictive model - the Error Correcting Output Code (ECOC) with TenaryComplete coding matrix - was obtained from experiments, and utilized to diagnose the incipient faults. Some of the important diagnostic results and heuristic model evaluation methods are presented in this paper.

• Journal of Korean Institute of Architectural Sustainable Environment and Building Systems
• /
• v.12 no.6
• /
• pp.579-590
• /
• 2018

Anomaly detection on building energy consumption has been regarded as an effective tool to reduce energy saving on building operation and maintenance. However, it requires energy model and FDD expert for quantitative model approach or large amount of training data for qualitative/history data approach. Both method needs additional time and labors. This study propose a machine learning and data science approach to define faulty conditions on hourly building energy consumption with reducing data amount and input requirement. It suggests an application of Support Vector Data Description (SVDD) method on training normal condition of hourly building energy consumption incorporated with hourly outdoor air temperature and time integer in a week, 168 data points and identifying hourly abnormal condition in the next day. The result shows the developed model has a better performance when the ${\nu}$ (probability of error in the training set) is 0.05 and ${\gamma}$ (radius of hyper plane) 0.2. The model accuracy to identify anomaly operation ranges from 70% (10% increase anomaly) to 95% (20% decrease anomaly) for daily total (24 hours) and from 80% (10% decrease anomaly) to 10%(15% increase anomaly) for occupied hours, respectively.

• International Journal of Advanced Culture Technology
• /
• v.11 no.1
• /
• pp.171-180
• /
• 2023

This study is to develop a performance analysis model for SMEs.Based on similar performance indicators through previous studies, performance indicators for SMEs were rewritten.Through the Korean Journal Citation Index (KCI), 75 related data were classified and a comprehensive SME performance analysis model was developed.Performance analysis was divided into two axes and classified into tables.The horizontal axis is the spatial performance range, which is divided into three areas: performance management by department/function, integrated performance management for the entire organization, and governance performance management requiring policy feedback. The vertical axis is subdivided into short-term, mid-term, and long-term by time and growth stage, and is divided into three parts: technical performance according to technological input, economic performance as organizational performance, and social performance for policy utilization. Then, performance indicators were mapped to each column. As a result of the survey, 28% of technical performance was analyzed as a result of frequency analysis, and performance indicators were organized into five categories: IT, R&D, certification, patent, and innovation. Economic performance was divided into 29%, BSC, HRD, logistics, production quality management, financial support, asset management, etc. 6 categories, social performance 43%, ESG, marketing, export, policy support, consulting, cooperation, etc. 7 categories.Limitations of the study include the narrowness of the survey that derived only performance indicators despite being a meta-analysis, and the performance model was mapped and classified according to growth stage and support period.however Insufficiency of validity due to lack of evidence, performance indicators were developed, but there were limitations in utilization for practical use.

• Korean Journal of Remote Sensing
• /
• v.40 no.2
• /
• pp.123-139
• /
• 2024

Forest vertical structure is vital for comprehending ecosystems and biodiversity, in addition to fundamental forest information. Currently, the forest vertical structure is predominantly assessed via an in-situ method, which is not only difficult to apply to inaccessible locations or large areas but also costly and requires substantial human resources. Therefore, mapping systems based on remote sensing data have been actively explored. Recently, research on analyzing and classifying images using machine learning techniques has been actively conducted and applied to map the vertical structure of forests accurately. In this study, Sentinel-2 and digital surface model images were obtained on two different dates separated by approximately one month, and the spectral index and tree height maps were generated separately. Furthermore, according to the acquisition time, the input data were separated into cases 1 and 2, which were then combined to generate case 3. Using these data, forest vetical structure mapping models based on random forest, support vector machine, and extreme gradient boost(XGBoost)were generated. Consequently, nine models were generated, with the XGBoost model in Case 3 performing the best, with an average precision of 0.99 and an F1 score of 0.91. We confirmed that generating a forest vertical structure mapping model utilizing bi-seasonal data and an appropriate model can result in an accuracy of 90% or higher.

• Nuclear Engineering and Technology
• /
• v.55 no.11
• /
• pp.4102-4111
• /
• 2023

In order to better perform thermal hydraulic calculation and analysis of supercritical water reactor, based on the experimental data of supercritical water, the model training and predictive analysis of the heat transfer coefficient of supercritical water were carried out by using the support vector machine (SVM) algorithm. The changes in the prediction accuracy of the supercritical water heat transfer coefficient are analyzed by the changes of the regularization penalty parameter C, the slack variable epsilon and the Gaussian kernel function parameter gamma. The predicted value of the SVM model obtained after parameter optimization and the actual experimental test data are analyzed for data verification. The research results show that: the normalization of the data has a great influence on the prediction results. The slack variable has a relatively small influence on the accuracy change range of the predicted heat transfer coefficient. The change of gamma has the greatest impact on the accuracy of the heat transfer coefficient. Compared with the calculation results of traditional empirical formula methods, the trained algorithm model using SVM has smaller average error and standard deviations. Using the SVM trained algorithm model, the heat transfer coefficient of supercritical water can be effectively predicted and analyzed.

• Korean Journal of Social Welfare Studies
• /
• v.42 no.1
• /
• pp.117-149
• /
• 2011

This study examined the relationship between discrimination experienced by children of multicultural families and their psychological distress. As new minorities growing up with bicultural identities in Korean society, children from multicultural families are often exposed to racial discrimination and such experience often acts as a stressor in their everyday life. In order to examine the effect of discrimination on their psychological distress as well as the role of social support, a survey was conducted in 25 elementary schools in Daejeon city and Chungnam and Chungbuk province. Results indicated that children's experiences of discrimination significantly affected their psychological distress level that the more they were exposed to discrimination, the higher levels of depression and anxiety they experienced. Among social support domains, only peer support was found to be significantly related to both the experience of discrimination and their depression and anxiety levels. Supporting the social support deterioration model, the findings showed that more experiences of discrimination led to reduced peer support which in turn, increased the likelihood of being depressed and anxious. Peer support was also significant in partially mediating the discrimination-psychological distress relationship. Implications for social work practice with children from multicultural families are provided.

• Women's Health Nursing
• /
• v.24 no.2
• /
• pp.138-149
• /
• 2018

Purpose: To identify and clarify the concept of labor support. Methods: This study used Schwartz-Barcott & Kim's hybrid model to identify the main attributes and indicators. In the fieldwork stage, data were collected in Seoul and Chenmam, Korea. The participants were five nurses working in the delivery room and four women who delivered more than two children by vaginal delivery. Results: The concept of labor support was found to have nine attributes and 23 indicators in two dimensions. For the physical intervention dimension, five attributes were derived. They were pain relief, selective use of technology, ambulation/positioning, physiological pushing, and increasing comfort. For the labor support practices dimension the attributeswereprovidinginformation, relief and encouragement, family support, and presence. Conclusion: The concept analysis of labor support in this study could provide guidelines for 'labor support' nursing practice and be useful for research in the women's health field.

• The Journal of Information Systems
• /
• v.22 no.4
• /
• pp.1-22
• /
• 2013

Government initiatives are continuously being invested to nurture supporting business environment for small and medium sized enterprises (SMEs), such as government-support ERP systems project for SMEs. As such, scholars need to pay attention to SMEs can successfully adopt and manage government-support ERP systems. This study, therefore, conceptually developed and tested a research model for understanding what factors influence SMEs' intention to adopt government-support ERP systems. We obtained thirty samples from SMEs, which is organizational level, and data were analyzed using the partial least square (PLS) technique. The results of data analysis found that institutional pressure and resource dependence had positive effects on the adoption of government-support ERP systems. On the other hand, risk aversion of SMEs was found to have negative effects to adopt government-support ERP systems.

• Korean Journal of Child Studies
• /
• v.31 no.1
• /
• pp.19-33
• /
• 2010

This study examined the effects of family climate, peer support and self-esteem on children's self-regulation. The participants in this study were 369 children (M=11.78 year) who completed questionnaires regarding family climate, peer support, self-esteem and self-regulation. Data were analyzed means by of a Structural equation model using AMOS 7.0. Our results indicated that (1) family climate, peer support and self-esteem were directly linked with children's self-regulation (2) the associations between family climate or peer support and children's self-regulation were mediated by children's self-esteem. These results imply that family climate and peer support are important antecedent variables in predicting children's self-regulation as well as their relative levels of self-esteem.

• Journal of Families and Better Life
• /
• v.27 no.5
• /
• pp.59-68
• /
• 2009

External social support for family can be an important resource for families to overcome economic pressure, and can be a way to understand the concept and process of family resilience in the context of Korean economic crisis. To explore the role of external social support that alleviates the negative effects of economic pressure on marital satisfaction, the buffering effects were tested in two ways. First, the interaction effect between external social support and economic pressure on marital satisfaction was tested using hierarchical linear regression model. Second, the scores of marital satisfaction were plotted by the median scores of economic pressure and external social support. Results from the analyses of 191 couples (382 husbands and wives) indicated that external social support help families by buffering the negative effects of economic pressure on marital satisfaction by interacting with economic pressure.