• Journal of the Korean Society of Manufacturing Technology Engineers
• /
• v.18 no.6
• /
• pp.681-689
• /
• 2009

Disk grinding was often applied to deburring process in order to enhance the final product quality. Inherent chamfering capability of the flexible disk grinding process in the early stage was analyzed with respect to various process parameters including workpiece length, wheel speed, depth of cut and feed. Initial chamfered edge defined as arc zone was characterized with local radius of curvature. Averaged radius and arc zone ratio was well evaluated using neural network system. Additional neural network analysis adding workpiece length showed enhance performance in predicting arc zone ratio and curvature radius with reduced error rate. A process condition design parameter was estimated using remaining input and output parameters with the prediction error rate lower than 2.0% depending on the relevant input parameter combination and neural network structure composition.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.7
• /
• pp.2488-2511
• /
• 2015

Data redundancy has high impact on Wireless Sensor Network's (WSN) performance and reliability. Spatial and temporal similarity is an inherent property of sensory data. By reducing this spatio-temporal data redundancy, substantial amount of nodal energy and bandwidth can be conserved. Most of the data gathering approaches use either temporal correlation or spatial correlation to minimize data redundancy. In Collective Prediction exploiting Spatio Temporal correlation (CoPeST), we exploit both the spatial and temporal correlation between sensory data. In the proposed work, the spatial redundancy of sensor data is reduced by similarity based sub clustering, where closely correlated sensor nodes are represented by a single representative node. The temporal redundancy is reduced by model based prediction approach, where only a subset of sensor data is transmitted and the rest is predicted. The proposed work reduces substantial amount of energy expensive communication, while maintaining the data within user define error threshold. Being a distributed approach, the proposed work is highly scalable. The work achieves up to 65% data reduction in a periodical data gathering system with an error tolerance of 0.6℃ on collected data.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.14 no.2
• /
• pp.534-539
• /
• 2010

In genomic studies, thousands of features are collected on relatively few samples. One of the goals of these studies is to build classifiers to predict the outcome of future observations. There are three inherent steps to build classifiers: a significant gene selection, model selection and prediction assessment. In the paper, with a focus on prediction assessment, we normalize microarray data with quantile-normalization methods that adjust quartile of all slide equally and then design a system comparing several methods to estimate 'true' prediction error of a prediction model in the presence of feature selection and compare and analyze a prediction error of them. LOOCV generally performs very well with small MSE and bias, the split sample method and 2-fold CV perform with small sample size very pooly. For computationally burdensome analyses, 10-fold CV may be preferable to LOOCV.

• Journal of Industrial Technology
• /
• v.28 no.A
• /
• pp.11-17
• /
• 2008

Applicability of hyperbolic settlement prediction method to consolidation settlement in the dredged and reclaimed ground was assessed by analyzing results of centrifuge tests modelling self-weight consolidation of soft marine clay. From literature review about self-weight consolidation of soft marine clays located in southern coast in Korea, constitutive relationships of void ratio - effective stress - permeability and typical self-weight consolidation curves with time were obtained by analyzing centrifuge model experiments. For the condition of surcharge loading, exact solution of consolidation settlement curve obtained by using Terzaghi's consolidation theory was compared with results predicted by the hyperbolic method. It was found to have its own inherent error to predict final consolidation settlement. From results of analyzing thc self-weight consolidation with time by using this method, it predicted relatively well in error range of 0.04~18% for the case of showing the linearity in the relationship between T vs T/S in the stage of consolidation degree of 60~90 %. However, it overestimated the final settlement with large errors if those relation curves were nonlinear.

• Journal of Ship and Ocean Technology
• /
• v.7 no.4
• /
• pp.41-49
• /
• 2003

Welding deformation reduces the accuracy of ship hull blocks and decreases productivity due to the need for correction work. Preparing an error-minimizing guide at the design stage will lead to higher quality as well as higher productivity. Therefore, developing a precise method to predict the weld deformation is an essential part of it. This paper proposes an efficient method for predicting the weld deformation of complicated structures based on the inherent strain theory combined with the finite element method. A simulation of a stiffened panel confirmed the applicability of this method to simple ship hull blocks.

• Journal of the Society of Naval Architects of Korea
• /
• v.37 no.2
• /
• pp.127-136
• /
• 2000

Welding deformations reduce the accuracy of ship hull blocks and decrease the productivity due to correction work. Preparing an error-minimizing guide at the design stage will lead to a high quality as well as high productivity. And a precise method to predict the weld deformation is an essential part of it. This paper proposes an efficient method to predict complicated weld deformations based on the inherent strain theory combined with the finite element method. The inherent strain is determined by the highest temperature and the degree of restraint. In order to calculate the inherent strain exactly, it is considered that the degree of restraint becomes different according to the fabrication stages in real structures. A simulation of a stiffened plate shows the applicability of this method to simple ship hull blocks.

• Journal of the Korean Geotechnical Society
• /
• v.35 no.3
• /
• pp.37-46
• /
• 2019

Recently, the use of CPT-based liquefaction assessment method has increased by providing more accurate results than other field tests. In CPT-based liquefaction evaluation, various soil properties are predicted and they are used for liquefaction potential assessment. In particular, fines content is one of the important input parameters in CPT-based liquefaction assessment, so it is very important to use correct prediction model and to make quantitative evaluation of estimating variability of fines content. In this study, the error evaluation of existing models for prediction of fines content through CPT was performed, and the most suitable model was selected for Pohang area, where the liquefaction phenomenon was observed in the 2017. In addition, the inherent variability of soil was analyzed, and the estimating variability of fines content was evaluated quantitatively considering the inherent variability of soil, measurement error of CPT and transformation uncertainty of selected model.

• KEPCO Journal on Electric Power and Energy
• /
• v.7 no.1
• /
• pp.171-177
• /
• 2021

In terms of distribution planning, accurate electric load prediction is one of the most important factors. The future load prediction has manually been performed by calculating the maximum electric load considering loads transfer/switching and multiplying it with the load increase rate. In here, the risk of human error is inherent and thus an automated maximum electric load forecasting system is required. Although there are many existing methods and techniques to predict future electric loads, such as regression analysis, many of them have limitations in reflecting the nonlinear characteristics of the electric load and the complexity due to Photovoltaics (PVs), Electric Vehicles (EVs), and etc. This study, therefore, proposes a method of predicting future electric loads on distribution lines by using Machine Learning (ML) method that can reflect the characteristics of these nonlinearities. In addition, predictive models were developed based on actual data collected at KEPCO's existing distribution lines and the adequacy of developed models was verified as well. Also, as the distribution planning has a direct bearing on the investment, and amount of investment has a direct bearing on the maximum electric load, various baseline such as maximum, lowest, median value that can assesses the adequacy and accuracy of proposed ML based electric load prediction methods were suggested.

• Communications for Statistical Applications and Methods
• /
• v.13 no.1
• /
• pp.49-60
• /
• 2006

There are six approaches to constructing standardized coefficient for logistic regression. The standardized coefficient based on Kruskal's information theory is known to be the best from a conceptual standpoint. In order to calculate this standardized coefficient, the coefficient of determination based on entropy loss is used among many kinds of coefficients of determination for logistic regression. In this paper, this standardized coefficient is obtained by using four kinds of coefficients of determination which have the most intuitively reasonable interpretation as a proportional reduction in error measure for logistic regression. These four kinds of the sixth standardized coefficient are compared with other kinds of standardized coefficients.

• Proceedings of the Korean Vacuum Society Conference
• /
• 2013.08a
• /
• pp.127.1-127.1
• /
• 2013

Recent experimental evidence that fluorinated graphene creates local magnetic moments around F adatoms has not been supported by semilocal density-functional theory (DFT) calculations where the adsorption of an F adatom induces no magnetic moment in graphene. Here, we show that such an incorrect prediction of the nonmagnetic ground state is due to the self-interaction error inherent in semilocal exchange-correlation functionals. The present hybrid DFT calculation for an F adatom on graphene predicts not only a spin-polarized ground state with a spin moment of ${\sim}1{\mu}_B$, but also a long-range spin polarization caused by the bipartite nature of the graphene lattice as well as the induced spin polarization of the graphene states. The results provide support for the experimental observations of local magnetic moments in fluorinated graphene.