• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2006년도 Proceedings of ISRS 2006 PORSEC Volume I
• /
• pp.114-117
• /
• 2006

One of the most important tasks of ocean color observations is to determine the distribution of phytoplankton primary production. A variety of bio-optical algorithms have been developed estimate primary production from these parameters. In this communication, we investigated the possibility of using a novel universal approximator-support vector machines (SVMs)-as the nonlinear transfer function between oceanic primary production and the information that can be directly retrieved from satellite data. The VGPM (Vertically Generalized Production Model) dataset was used to evaluate the proposed approach. The PPARR2 (Primary Production Algorithm Round Robin 2) dataset was used to further compare the precision between the VGPM model and the SVM model. Using this SVM model to calculate the global ocean primary production, the result is 45.5 PgC $yr^{-1}$, which is a little higher than the VGPM result.

• Journal of the Korean Data and Information Science Society
• /
• 제21권4호
• /
• pp.765-775
• /
• 2010

For the accelerated failure time (AFT) model a lot of effort has been devoted to develop effective estimation methods. AFT model assumes a linear relationship between the logarithm of event time and covariates. In this paper we propose a semiparametric support vector machine to consider situations where the functional form of the effect of one or more covariates is unknown. The proposed estimating equation can be computed by a quadratic programming and a linear equation. We study the effect of several covariates on a censored response variable with an unknown probability distribution. We also provide a generalized approximate cross-validation method for choosing the hyper-parameters which affect the performance of the proposed approach. The proposed method is evaluated through simulations using the artificial example.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1998년도 춘계학술대회 학술발표 논문집
• /
• pp.116-119
• /
• 1998

Abstract-In paper, an operation support software for combustion control of refuse incineration plant is developed using fuzzy model and genetic algorithm. It has two major modules which are simulation module and optimal operation module. In simulation module modelling is performed to obtain fuzzy model of the refuse incineration plant and obtained fuzzy model predicts outputs of the plant when inputs are given. This module can be used to obtain control strategy, and train and enhance operators' skill by simulating the plant. And in optimal operation module, genetic algorithm searches and finds out optimal control inputs over all possible solutions in respect to desired outputs. In order to testify proposed operation support software, computer simulation was carried out.

• 반도체디스플레이기술학회지
• /
• 제10권3호
• /
• pp.75-81
• /
• 2011

This paper presents a novel method for image classification based on a hybrid genetic algorithm (GA) and support vector machine (SVM) approach which can significantly improve the classification performance for content-based image retrieval (CBIR). Though SVM has been widely applied to CBIR, it has some problems such as the kernel parameters setting and feature subset selection of SVM which impact the classification accuracy in the learning process. This study aims at simultaneously optimizing the parameters of SVM and feature subset without degrading the classification accuracy of SVM using GA for CBIR. Using the hybrid GA and SVM model, we can classify more images in the database effectively. Experiments were carried out on a large-size database of images and experiment results show that the classification accuracy of conventional SVM may be improved significantly by using the proposed model. We also found that the proposed model outperformed all the other models such as neural network and typical SVM models.

• Computers and Concrete
• /
• 제18권3호
• /
• pp.389-404
• /
• 2016

In this study, effects of impact loads on reinforced concrete (RC) plates are examined analytically. During examination of RC plates, they were exposed to impact loading with two different support conditions in three different sizes. RC plates in different support conditions were analyzed with Concrete Damage Plasticity Model (CDP) and reinforcing steel was modeled with Classical Metal Plasticity Model (CMP) by ABAQUS finite element software. After the analysis it is found that impact loads, displacements, energy absorption capacities and damage patterns are changed due to support conditions and plate sizes. Results that are obtained from RC plate experiments in literature under impact loads are found to be similar with the results of numerical analysis with CDP material models.

• 대한가정학회지
• /
• 제23권1호
• /
• pp.71-85
• /
• 1985

The study attempts to explore factors which affect life satisfaction of the elderly, and thereby to identify the most efficient strategy to enhance their happiness and satisfaction with life by means of a family support system. Previous research suggests that the family is the main origin from which emotional and ecionomic satisfacton of the aged evolves, and satisfaction is facilitated by societal assistance for the family to financially support old persons. These theoretical antecedents are incorporated into a causal model for empirical verificatio. To this end, interviews were conducted in Seoul with 300 individuals who are 60 years old or over. The major findings of this study support the theoretical assertions of previous studies. They are summarized as follows : 1. Family solidarity is highly correlated with life satisfaction of the elderly. 2. Family solidarity is raised by the intensity of their social association, satisfaction with housing, and financial resources. 3. Eduation, income and marital status as exogenous variables do not directly affect life satisfaction and family solidarity, despite their strong overall correlation. Casual effects of each variable are linked to family solidarity and then to life satisfaction through a family support system for the elderly.

• 품질경영학회지
• /
• 제38권4호
• /
• pp.491-503
• /
• 2010

This paper presents a research model, which identifies a relationship between medical error reduction, efficiency of organizational systems, and employee satisfaction with organizational support. The proposed model was tested through hypotheses, based on data collected from 210 respondents from the medical staff of large -sized (i.e., more than 500 beds) residential hospitals in cities of South Korea. The results of the study showed that medical error reduction is associated with corrective system and employee satisfaction with organizational support. Therefore, it is very important that organizations improve their employees' satisfaction by providing sufficient support (e.g., information support and sharing, work guide book, etc.) for their work. In addition, in organizational systems, the corrective system has positive relationship with medical error reduction. In terms of corrective procedures, leaders or managers can make improvements by providing and supporting a friendly work environment where errors may be reported without blame and discussed in order to be corrected.

• 품질경영학회지
• /
• 제28권2호
• /
• pp.89-102
• /
• 2000

Many organizations have developed their own traditional quality information systems. But, they think of it as one of the functional information systems not as a company-wide decision support information systems. A study on traditional quality information systems(QIS) has been conducted and a new conceptual framework of quality information system is proposed in this paper. In order to support enterprise wide total quality management aggressively, a new conceptual framework, named quality management support information system(QMSIS) is developed and proposed. This framework is based upon Malcolm Baldrige National Quality Award(MBNQA) model integrates management information system approach and traditional quality information system concept. In this model, organizational performance and process performance can be monitored to support managers , decision making about organizational quality management activities.

• 패션비즈니스
• /
• 제15권4호
• /
• pp.87-109
• /
• 2011

This study was to examined the relationship between goal setting, self improvement, social support of parents, friendship, school adaptation, drop out. In our research model, goal setting, self improvement, social support of parents, and friendship is exogenous variable and school adaption and drop out is endogenous variable. A total of 323 undergraduate student(254 female, 69 male) complete the questionnaires. Structural equation modelling showed that, as hypothesized, establishment of goals, social support of parent and friendship have effect on school adaptation, and friendship also have direct effect on drop out. School adaptation mediate path from goal setting, social support of parents, and friendship. This study provides empirical evidence for a model that show how to control the drop out of students.

• 디지털융복합연구
• /
• 제5권2호
• /
• pp.25-36
• /
• 2007

In this paper, we studied on the effective structure of an e-Learning Korean Support System for foreigner based on computer systems which is to obey the rules of IMS/AICC International Standard regulations based on LCMS and SCORM. The most important task on this study is to support the function of self-study module through the review of the analysis and results of Korean learning and learning customs. We studied the effective PMS detail modules as well as the Standard Competency Module Management System, which related to LMS/LCMS, Learning an Individual Competency Management System, Competency Registry/Repository System, Knowledge Management System based on Community Competency Module, Education e-survey System and Module learning Support Service System. We suggested one of standard Effective Model of learning Korean Support System which is adopted in a various techniques for foreigner.