• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2001.04a
• /
• pp.439-442
• /
• 2001

The Accuracy of a free-form artifact is affected by machine tool errors, machining process errors, environmental causes and other uncertainty. This paper deals with methodological approach about machine tool errors that are defined the relationship between CMM and OMM inspections of the free-form artifact. In order to analyze the measurement data, Reverse engineering was used. In other words, Surface of Free-Form Artifact is generated by NURBS surface approximation method. Finally, Volumetric error map is made to compare surface of CMM data with that of OMM data.

• The Journal of Korea Robotics Society
• /
• v.3 no.2
• /
• pp.117-122
• /
• 2008

This paper presents a multi-robot localization based on multidimensional scaling (MDS) in spite of the existence of incomplete and noisy data. While the traditional algorithms for MDS work on the full-rank distance matrix, there might be many missing data in the real world due to occlusions. Moreover, it has no considerations to dealing with the uncertainty due to noisy observations. We propose a robust MDS to handle both the incomplete and noisy data, which is applied to solve the multi-robot localization problem. To deal with the incomplete data, we use the Nystr$\ddot{o}$m approximation which approximates the full distance matrix. To deal with the uncertainty, we formulate a Bayesian framework for MDS which finds the posterior of coordinates of objects by means of statistical inference. We not only verify the performance of MDS-based multi-robot localization by computer simulations, but also implement a real world localization of multi-robot team. Using extensive empirical results, we show that the accuracy of the proposed method is almost similar to that of Monte Carlo Localization(MCL).

• ETRI Journal
• /
• v.33 no.6
• /
• pp.914-923
• /
• 2011

This paper concerns robust and reliable speaker model training for text-independent speaker verification. The baseline speaker modeling approach is the Gaussian mixture model (GMM). In text-independent speaker verification, the amount of speech data may be different for speakers. However, we still wish the modeling approach to perform equally well for all speakers. Besides, the modeling technique must be least vulnerable against unseen data. A traditional approach for GMM training is expectation maximization (EM) method, which is known for its overfitting problem and its weakness in handling insufficient training data. To tackle these problems, variational approximation is proposed. Variational approaches are known to be robust against overtraining and data insufficiency. We evaluated the proposed approach on two different databases, namely KING and TFarsdat. The experiments show that the proposed approach improves the performance on TFarsdat and KING databases by 0.56% and 4.81%, respectively. Also, the experiments show that the variationally optimized GMM is more robust against noise and the verification error rate in noisy environments for TFarsdat dataset decreases by 1.52%.

• Coupled systems mechanics
• /
• v.11 no.1
• /
• pp.43-54
• /
• 2022

In order to analyse the thermal performance of battery systems in electric vehicles complex simulation models with high computational cost are necessary. Using reduced order methods, real-time applicable model can be developed and used for on-board monitoring. In this work a data driven model of the cooling plate as part of the battery system is built and derived from a computational fluid dynamics (CFD) model. The aim of this paper is to create a meta model of the cooling plate that estimates the temperature at the boundary for different heat flow rates, mass flows and inlet temperatures of the cooling fluid. In order to do so, the cooling plate is simulated in a CFD software (ANSYS Fluent ®). A data driven model is built using the design of experiment (DOE) and various approximation methods in Optimus ®. The model can later be combined with a reduced model of the thermal battery system. The assumption and simplification introduced in this paper enable an accurate representation of the cooling plate with a real-time applicable model.

• Journal of the Korean Data and Information Science Society
• /
• v.8 no.2
• /
• pp.163-171
• /
• 1997

Function approximation from a set of input-output pairs has numerous applications in scientific and engineering areas. Multilayer feedforward neural networks have been proposed as a good approximator of nonlinear function. The back propagation(BP) algorithm allows multilayer feedforward neural networks to learn input-output mappings from training samples. It iteratively adjusts the network parameters(weights) to minimize the sum of squared approximation errors using a gradient descent technique. However, the mapping acquired through the BP algorithm may be corrupt when errorneous training data we employed. When errorneous traning data are employed, the learned mapping can oscillate badly between data points. In this paper we propose a robust BP learning algorithm that is resistant to the errorneous data and is capable of rejecting gross errors during the approximation process, that is stable under small noise perturbation and robust against gross errors.

• The KIPS Transactions:PartD
• /
• v.19D no.2
• /
• pp.151-160
• /
• 2012

Most of the distributed high-dimensional indexing structures provide a reasonable search performance especially when the dataset is uniformly distributed. However, in case when the dataset is clustered or skewed, the search performances gradually degrade as compared with the uniformly distributed dataset. We propose a method of improving the k-nearest neighbor search performance for the distributed vector approximation-tree based on the strongly clustered or skewed dataset. The basic idea is to compute volumes of the leaf nodes on the top-tree of a distributed vector approximation-tree and to assign different number of bits to them in order to assure an identification performance of vector approximation. In other words, it can be done by assigning more bits to the high-density clusters. We conducted experiments to compare the search performance with the distributed hybrid spill-tree and distributed vector approximation-tree by using the synthetic and real data sets. The experimental results show that our proposed scheme provides consistent results with significant performance improvements of the distributed vector approximation-tree for strongly clustered or skewed datasets.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1997.10a
• /
• pp.435-438
• /
• 1997

This paper presents the process generating a SAC(Sectional Area Cure) by using ASMOD(Adaptive Spline Modeling of Observation Data). That is, we define SACs of real ships as B-spline curves by a hybrid cure approximation(which is the combination method of a B-spline fitting method and a genetic algorithm) and accumulate a database of control points. Then we let ASMOD learn from the correlation principal dimensions with control points.

• 한국데이터정보과학회:학술대회논문집
• /
• 2003.05a
• /
• pp.109-119
• /
• 2003

In this paper we propose a local smoothing of the Nelson type estimator for the survival function based on an approximation by the Weibull distribution function. It appears that Mean Square Error and Bias of the smoothed estimator of the Nelson type survival function estimator is significantly smaller then that of the smoothed estimator of the Kaplan-Meier survival function estimator.

• Proceedings of the KSEEG Conference
• /
• 2003.04a
• /
• pp.150-153
• /
• 2003

High-resolution imaging of electrical conductivity has been the subject of many studies in crosshole tomography using electromagnetic (EM) fields (Zhou et al., 1993; Wilt et al., 1995; Alumbaugh and Morrison, 1995; Newman, 1995; Alumbaugh and Newman, 1997). Although the theoretical understanding and associated field practices for crosshole EM methods are relatively mature, fast and stable imaging of crosshole EM data is still a challenging problem. (omitted)

• Korean Journal of Geomatics
• /
• v.4 no.1
• /
• pp.31-37
• /
• 2004

The aim of this research is comparing the existing approximation models (e.g. Affine Transformation and Direct Linear Transformation) with Rational Function Model as a substitute of rigorous sensor model of linear array scanner, especially push-broom sensor. To do so, this research investigates the mathematical model of each approximation method. This is followed by the assessments of accuracy of transformation from object space to image space by using simulated data generated by collinearity equations which incorporate or depict the physical aspects of linear array sensor.