• Journal of Korea Multimedia Society
• /
• v.7 no.7
• /
• pp.877-885
• /
• 2004

In this paper, we propose an enhancement shot change detection method using the neural net and the robust feature selection out of multiple features. The previous shot change detection methods usually used single feature and fixed threshold between consecutive frames. However, contents such as color, shape, background, and texture change simultaneously at shot change points in a video sequence. Therefore, in this paper, we detect the shot changes effectively using robust features, which are supplementary each other, rather than using single feature. In this paper, we use the typical CART (classification and regression tree) of data mining method to select the robust features, and the backpropagation neural net to determine the threshold of the each selected features. And to evaluation the performance of the robust feature selection, we compare the proposed method to the PCA(principal component analysis) method of the typical feature selection. According to the experimental result. it was revealed that the performance of our method had better that than the PCA method.

• Journal of the Korea Society for Simulation
• /
• v.30 no.1
• /
• pp.75-85
• /
• 2021

In this paper, we present a deep neural network-based prediction model that processes and analyzes the corporate credit and personal credit information of individual business owners as a new method to predict the default rate of individual business more accurately. In modeling research in various fields, feature selection techniques have been actively studied as a method for improving performance, especially in predictive models including many features. In this paper, after statistical verification of macroeconomic indicators (macro variables) and credit information (micro variables), which are input variables used in the default rate prediction model, additionally, through the credit information feature selection method, the final feature set that improves prediction performance was identified. The proposed credit information feature selection method as an iterative & hybrid method that combines the filter-based and wrapper-based method builds submodels, constructs subsets by extracting important variables of the maximum performance submodels, and determines the final feature set through prediction performance analysis of the subset and the subset combined set.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2007.04a
• /
• pp.101-104
• /
• 2007

As the proportion of underground construction increases, the impact of inappropriate selection of a underground construction method for a construction size increases. The purpose of this study is to develop an objective way of selecting an excavation method. There have been several attempts to achieve the same goal using various data mining methods such as the artificial neural network, the support vector machine, and the case-based reasoning. However, they focused only on the selection of a retaining wall construction method out of six types of retaining walls. When we categorized an underground construction work into four groups and added more number of independent variables (i.e., more number of construction methods), the predictability decreased. As an alternative, we developed a decision tree by analyzing 25 earthwork cases with detailed information. We implemented the developed decision tree as a computer-supported program called Dr. underground and are still in the process of validating and revising the decision tree. This study is still in a preliminary stage and will be improved by collecting and analyzing more cases.

• Smart Structures and Systems
• /
• v.5 no.1
• /
• pp.1-21
• /
• 2009

A two-stage damage detection method is proposed and demonstrated for structural health monitoring. In the first stage, the subset selection method is applied for the identification of the multiple damage locations. In the second stage, the damage severities of the identified damaged elements are determined applying SSGA to solve the optimization problem. In this method, the sensitivities of residual force vectors with respect to damage parameters are employed for the subset selection process. This approach is particularly efficient in detecting multiple damage locations. The SEREP is applied as needed to expand the identified mode shapes while using a limited number of sensors. Uncertainties in the stiffness of the elements are also considered as a source of modeling errors to investigate their effects on the performance of the proposed method in detecting damage in real-life structures. Through a series of illustrative examples, the proposed two-stage damage detection method is demonstrated to be a reliable tool for identifying and quantifying multiple damage locations within diverse structural systems.

• Journal of Astronomy and Space Sciences
• /
• v.36 no.2
• /
• pp.97-103
• /
• 2019

An automated signal-acquisition method for the NASA's space geodesy satellite laser ranging (SGSLR) system is described as a selection of two system parameters with specified probabilities. These parameters are the correlation parameter: the minimum received pulse number for a signal-acquisition and the frame time: the minimum time for the correlation parameter. The probabilities specified are the signal-detection and false-acquisition probabilities to distinguish signals from background noise. The steps of parameter selection are finding the minimum set of values by fitting a curve and performing a graph-domain approximation. However, this selection method is inefficient, not only because of repetition of the entire process if any performance values change, such as the signal and noise count rate, but also because this method is dependent upon system specifications and environmental conditions. Moreover, computation is complicated and graph-domain approximation can introduce inaccuracy. In this study, a new method is proposed to select the parameters via a conditional equation derived from characteristics of the signal-detection and false-acquisition probabilities. The results show that this method yields better efficiency and robustness against changing performance values with simplicity and accuracy and can be easily applied to other satellite laser ranging (SLR) systems.

• Journal of Microbiology and Biotechnology
• /
• v.15 no.5
• /
• pp.1022-1027
• /
• 2005

Based on plasmid display technology by the complexes of fusion protein and the encoding plasmid DNA, an in vitro selection method for high affinity DNA-binding protein was developed and experimentally demonstrated. The GAL4 DNA-binding domain (GAL4 DBD) was selected as a model DNA-binding protein, and enhanced green fluorescent protein (EGFP) was used as an expression reporter for the selection of target proteins. Error prone PCR was conducted to construct a mutant library of the model. Based on the affinity decrease with increased salt concentration, mutants of GAL4 DBD having high affinity were selected from the mutant protein library of protein-encoding plasmid complex by this method. Two mutants of (Lys33Glu, Arg123Lys, Ile127Lys) and (Ser47Pro, Ser85Pro) having high affinity were obtained from the first generation mutants. This method can be used for rapid in vitro selection of high affinity DNA-binding proteins, and has high potential for the screening of high affinity DNA-binding proteins in a sequence-specific manner.

• Journal of Environmental Impact Assessment
• /
• v.8 no.1
• /
• pp.71-79
• /
• 1999

The comparative evaluation is the most effective method for site selection because the selection of waste treatment facility is to determine the optimum site out of limited candidate sites. This study adopted the ordinal scale evaluation, one of methods of comparative evaluation. The ordinal scale evaluation aims to determine the investigating items referring to the character of sites, to determine the importance factors for investigating items, and to determine the optimum site according to the quantitative evaluation. As a result of this study, the defects of the former reports on the environmental characteristics, such as obscurity of meaning and subjective statement, were reduced by the ordinal scale evaluation which is one of the quantitative evaluation methods. This ordinal scale evaluation method has some valuable advantages, such as, to be able to consider the cost-effect efficiency, to consider the objectiveness and the clearness of the reports on the environmental characteristics. Therefore the reducement of social complications about site selection of the indisposed facilities could be expected by this study.

• Transactions of the Korean Society of Machine Tool Engineers
• /
• v.18 no.1
• /
• pp.59-67
• /
• 2009

The purpose of this study is to provide a decision support to select an appropriate layered manufacturing(LM) machine that suits the application of a part. Selection factors include concept model, form/fit/functional model, pattern model far molding, material property, build time and part cost that greatly affect the performance of LM machines. However, the selection of a LM is not an easy decision because they are uncertain and vague. For this reason, the aim of this research is to propose hybrid multiple attribute decision making approaches to effectively evaluate LM machines. In addition, because subjective considerations are relevant to selection decision, a fuzzy logic approach is adopted. The proposed selection procedure consists of several steps. First, we identify LM machines that the users consider After constructing the evaluation criteria, we calculate the weights of the criteria by applying the fuzzy Analytic Hierarchy Process(AHP) method. Finally, we construct the fuzzy Technique of Order Preference by Similarity to Ideal Solution(TOPSIS) method to achieve the ranking order of all machines providing the decision information for the selection of LM machines.

• Proceedings of the Korea Society for Energy Engineering kosee Conference
• /
• 1999.11a
• /
• pp.119-124
• /
• 1999

A selection methodology of liquid levelmeters, especially, level sensors in non-nuclear category, to be installed in nuclear energy facilities is developed using linguistic fuzzy approaches such as fully-linguistic and semi-linguistic methods. Depending on defuzzification techniques, the linguistic fuzzy methodology leads to either linguistic (exactly, fully-linguistic) or cardinal (i.e., semi-linguistic) evaluation. For the linguistic method, for each alternative, fuzzy preference index is converted to linguistic utility value by means of a similarity measure determining the degree of similarity between fuzzy index and linguistic ratings. For the cardinal method, the index is translated to cardinal overall utility value. According to these values, alternatives of interest are linguistically or numerically evaluated and a suitable alternative can be selected. Under given selection criteria, the suitable selections out of some liquid levelmeters for nuclear facilities are dealt with using the linguistic fuzzy methodology proposed. Then, linguistic fuzzy evaluation results are compared with qualitative result available in the literature. It is found that as to a suitable option the linguistic fuzzy selection is in agreement with the qualitative selection. Additionally, the comparative study shows that the fully-linguistic method using adequate scale system facilitates linguistic interpretation regarding evaluation results.

• Journal of the Korea Society of Computer and Information
• /
• v.24 no.11
• /
• pp.219-228
• /
• 2019

Naval command and control system are very important for operation and their failures can be fatal for warfare. To prepare for these failures, we use feature selection method which is one of the data mining techniques. First, we analyzes failure data set of Navy from 2016 to 2018. And then We derive attributes that are associated with failure and to predict failure using feature selection method. We propose a method for prioritizing maintenance using the degree of association of attributes. This improves the efficiency and economics of command and control system maintenance.