• Journal of Korean Society for Quality Management
• /
• v.28 no.2
• /
• pp.57-69
• /
• 2000

This paper discusses the local influence approach to the linear regression models with AR(2) errors. Diagnostics for the linear regression models with AR(2) errors are proposed and developed when simultaneous perturbations of the response vector are allowed- That is, the direction of maximum curvature of local influence analysis is obtained by studying the curvature of a surface associated with the overall discrepancy measure.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1998.10a
• /
• pp.204-210
• /
• 1998

This paper discusses an on-line fuzzy dynamic model(FDM) identification of nonlinear processes for the design of fuzzy model based fault detection and isolation(FDI). The dynamic behavior of a nonlinear process is represented by a fuzzy aggregation of a set of local linear models. The identification is divided into two procedures. The first is the off-line identification of membership function. The second is the on-line identification of the local linear models. Then, we propose a residual generation scheme based on the parameters of local linear models and show that the scheme can be used for the design of FDI

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.8
• /
• pp.3950-3964
• /
• 2017

With the increasing popularity of 3D technology such as 3D printing, 3D modeling, etc., there is a growing need to search for similar models on the internet. Matching non-rigid shapes has become an active research field in computer graphics. In this paper, we present an efficient and effective non-rigid model retrieval method based on topological structure and local volume. The integral geodesic distances are first calculated for each vertex on a mesh to construct the topological structure. Next, each node on the topological structure is assigned a local volume that is calculated using the shape diameter function (SDF). Finally, we utilize the Hungarian algorithm to measure similarity between two non-rigid models. Experimental results on the latest benchmark (SHREC' 15 Non-rigid 3D Shape Retrieval) demonstrate that our method works well compared to the state-of-the-art.

• Journal of the Korea Society of Computer and Information
• /
• v.16 no.10
• /
• pp.229-239
• /
• 2011

This study aims to suggest profitability models of local cultural festival to be a focal point of local culture to overcome the abuses as an annual event led by the local government agencies have been in force in every local areas currently, to elicit the local residents' voluntary participation and to engage the outside tourists in connection of a more effective promotion and marketing. The festival is attractive to people with that provoke mirth and inspire curiosity, but the festival is not a one-time event ongoing maintenance enlarge: It is absolutely necessary in order to effort to reach at consumer-oriented quality of service. Also this research intends to present a activation scheme by developing profitability models to make profits while holding a number of risks taking into account the characteristics of the local festival service carried out. To this end, based on established research, leading indicator and expert opinion were analyzed through multiple regression analysis.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2018.06a
• /
• pp.63-66
• /
• 2018

Recently, a convolutional neural network (CNN) models at single image super-resolution have been very successful. Residual learning improves training stability and network performance in CNN. In this paper, we compare four convolutional neural network models for super-resolution (SR) to learn nonlinear mapping from low-resolution (LR) input image to high-resolution (HR) target image. Four models include general CNN model, global residual learning CNN model, local residual learning CNN model, and the CNN model with global and local residual learning. Experiment results show that the results are greatly affected by how skip connections are connected at the basic CNN network, and network trained with only global residual learning generates highest performance among four models at objective and subjective evaluations.

• Journal of Ecology and Environment
• /
• v.32 no.2
• /
• pp.103-107
• /
• 2009

We investigated colonization and extinction patterns in a meta population of the gold-spotted pond frog (Rana planeyi ehoseniea) near the Korea National University of Education, Chungbuk, Korea, by surveying the frogs in the nine occupied habitat patches in the study area four times per breeding season for three years (2006$\sim$2008) and recording whether the patches were occupied by frogs as well as how many frogs were calling in the patches. We then developed five a priori year-specific models using the Akaike Information Criterion (AIC). The models predicted that: 1) probabilities of colonization and local extinction of the frogs were better explained by year-dependent models than by constant models, 2) there are high local extinction and low colonization probabilities, 3) approximately 31% number of patches will be occupied at equilibrium, and 4) that considerable variation in occupation rate should occur over a 30-year period, due to demographic stochasticity (in our model, the occupation rate ranged from 0.222 to 0.889). Our results suggest that colonization is important in this metapopulation system, which is governed by mainly stochastic components, and that more constructive conservation effects are needed to increase local colonization rates.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.27 no.2
• /
• pp.87-94
• /
• 2014

In solid mechanics, the peridynamics theory has provided a suitable framework for material failure and damage propagation simulation. Peridynamics is computationally expensive since it is required to solve enormous nonlocal interactions based upon integro-differential equations. Thus, multiscale coupling methods with other local models are of interest for efficient and accurate implementations of peridynamics. In this study, peridynamic models are restricted to regions where discontinuities or stress concentrations are present. In the domains characterized by smooth displacements, classical local models can be employed. We introduce a recently developed blending scheme to concurrently couple bond-based peridynamic models and the Navier equation of classical elasticity. We demonstrate numerically that the proposed blended model is suitable for point loads and static fracture, suggesting an alternative framework for cases where peridynamic models are too expensive, while classical local models are not accurate enough.

• Structural Engineering and Mechanics
• /
• v.61 no.6
• /
• pp.807-816
• /
• 2017

In this paper, we introduce an efficient new model reduction method, named the automated static condensation method, which is developed for the local analysis of large finite element models. The algebraic multilevel substructuring procedure is modified appropriately, and then applied to the original static condensation method. The retained substructure, which is the local finite element model to be analyzed, is defined, and then the remaining part of the global model is automatically partitioned into many omitted substructures in an algebraic perspective. For an efficient condensation procedure, a substructural tree diagram and substructural sets are established. Using these, the omitted substructures are sequentially condensed into the retained substructure to construct the reduced model. Using several large practical engineering problems, the performance of the proposed method is demonstrated in terms of its solution accuracy and computational efficiency, compared to the original static condensation method and the superelement technique.

• Journal of Communications and Networks
• /
• v.9 no.4
• /
• pp.356-367
• /
• 2007

In large networks, maintaining precise global network state information is impossible. The imprecise network state information has significant impacts on Quality-of-Service(QoS) routing and path establishment. In this paper, we develop analytical models for investigating the QoS routing schemes that are designed to tolerate imprecise network state information, and study the performance of various QoS routing schemes, including randomized routing, multi-path routing, and probability based routing, using both the models and simulations. We further propose a new mechanism, called local rerouting, that improves the effectiveness of QoS path establishment in the presence of imprecise global network state information. Local rerouting is orthogonal to existing schemes for dealing with imprecise state information and can be used in conjunction with them to alleviate the impacts of the imprecise information. The results of our performance study indicate that local rerouting is robust and effective.

• Journal of Mechanical Science and Technology
• /
• v.17 no.3
• /
• pp.449-456
• /
• 2003

In this study, numerical and experimental analysis on the spray atomization characteristics of a GDI injector is performed. For numerical approach, four hybrid models that are composed of primary and secondary breakup model are considered. Concerning the primary breakup, a conical sheet disintegration model and LISA model are used. The secondary breakup models are made based on the DDB model and RT model. The global spray behavior is also visualized by the shadowgraph technique and local Sauter mean diameter and axial mean velocity are measured by using phase Doppler particle analyzer Based on the comparison of numerical and experimental results, it is shown that good agreement is obtained in terms of spray developing process and spray tip penetration at the all hybrid models. However, the hybrid breakup models show different prediction of accuracy in the cases of local SMD and the spatial distribution of breakup.