• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2000년도 하계종합학술대회 논문집(3)
• /
• pp.177-180
• /
• 2000

Recently, a feature extraction method based on decision boundary has been proposed for neural networks. The method is based on the fact that all the features necessary to achieve the same classification accuracy as in the original space can be obtained from the vectors normal to decision boundaries. However, the normal vector was estimated numerically. resulting in inaccurate estimation and a long computational time. In this paper. we propose a new method to calculate the normal vector analytically. Experiments show that the proposed method provides a better performance.

• Communications for Statistical Applications and Methods
• /
• 제12권2호
• /
• pp.323-333
• /
• 2005

In this paper, we develop a MCMC method for estimating the skew normal distributions. The method utilizing the data augmentation technique gives a simple way of inferring the distribution where fully parametric frequentist approaches are not available for small to moderate sample cases. Necessary theories involved in the method and computation are provided. Two numerical examples are given to demonstrate the performance of the method.

• Journal of Applied and Pure Mathematics
• /
• 제4권5_6호
• /
• pp.263-268
• /
• 2022

We derive an alternative proof of Marsaglia's method for generating a pair of independent standard normal random variables.

• 한국수학교육학회지시리즈D:수학교육연구
• /
• 제16권2호
• /
• pp.137-154
• /
• 2012

Comparative studies on mathematical modeling cognition feature were carried out between 15 excellent high school third-grade science students (excellent students for short) and 15 normal ones (normal students for short) in China by utilizing protocol analysis and expert-novice comparison methods and our conclusions have been drawn as below. 1. In the style, span and method of mathematical modeling problem representation, both excellent and normal students adopted symbolic and methodological representation style. However, excellent students use mechanical representation style more often. Excellent students tend to utilize multiple-representation while normal students tend to utilize simplicity representation. Excellent students incline to make use of circular representation while normal students incline to make use of one-way representation. 2. In mathematical modeling strategy use, excellent students tend to tend to use equilibrium assumption strategy while normal students tend to use accurate assumption strategy. Excellent students tend to use sample analog construction strategy while normal students tend to use real-time generation construction strategy. Excellent students tend to use immediate self-monitoring strategy while normal students tend to use review-monitoring strategy. Excellent students tend to use theoretical deduction and intuitive judgment testing strategy while normal students tend to use data testing strategy. Excellent students tend to use assumption adjustment and modeling adjustment strategy while normal students tend to use model solving adjustment strategy. 3. In the thinking, result and efficiency of mathematical modeling, excellent students give brief oral presentations of mathematical modeling, express themselves more logically, analyze problems deeply and thoroughly, have multiple, quick and flexible thinking and the utilization of mathematical modeling method is shown by inspiring inquiry, more correct results and high thinking efficiency while normal students give complicated protocol material, express themselves illogically, analyze problems superficially and obscurely, have simple, slow and rigid thinking and the utilization of mathematical modeling method is shown by blind inquiry, more fixed and inaccurate thinking and low thinking efficiency.

• Bulletin of the Korean Chemical Society
• /
• 제33권8호
• /
• pp.2499-2507
• /
• 2012

A novel and convenient electrochemical method has been developed for sensitive determination of melamine (MEL) using ascorbic acid (AA) as the recognition element. The working electrode employed in this method was modified with the nanocomposite of hydroxyapatite/carbon nanotubes to enhance the current signal of recognition element. The interaction between MEL and AA was investigated by fourier transform infrared spectroscopy and cyclic voltammetry, and the experimental results indicated that hydrogen bonding was formed between MEL and AA. Because of the existing hydrogen bonding and electrostatic interaction, the anodic peak current of AA was decreased obviously while the non-electroactive MEL added in. It illustrated that the MEL acted as an inhibitor to the oxidation of AA and the decreasing signals can be used to detect MEL. Under the optimal conditions, the decrease in anodic peak current of AA was proportional to the MEL concentrations ranging from 10 to 350 nM, with a detection limit of 1.5 nM. Finally this newly-proposed method was successfully employed to detect MEL in infant formula and milk, and good recovery was achieved.

• 대한산업공학회지
• /
• 제39권2호
• /
• pp.109-118
• /
• 2013

We propose a method for estimating coefficients of AR (autoregressive) model which named MLPAR (Maximum Likelihood of Pearson system for Auto-Regressive model). In the present method for estimating coefficients of AR model, there is an assumption that residual or error term of the model follows the normal distribution. In common cases, we can observe that the error of AR model does not follow the normal distribution. So the normal assumption will cause decreasing prediction accuracy of AR model. In the paper, we propose the MLPAR which does not assume the normal distribution of error term. The MLPAR estimates coefficients of auto-regressive model and distribution moments of residual by using pearson distribution system and maximum likelihood estimation. Comparing proposed method to auto-regressive model, results are shown to verify improved performance of the MLPAR in terms of prediction accuracy.

• 소음진동
• /
• 제9권5호
• /
• pp.975-983
• /
• 1999

This paper describes the dynamic characteristics of the joint structures in case of using the simplified beam model in the F. E. analysis. The modeling errors, when replace the shell with the beam, are investigated through F. E. normal modes analysis. Normal mode analysis were performed to obtain the natural frequencies of the L and T shaped joints with various type of channels. The results were analyzed to access the effects of the models on the accuracy of F.E. analysis by identifying the geometric factors which cause the error. The geometric factors considered are joint angle, channel length, thickness and area ratio of the hollow section to the filled one. The joint stiffness evaluation technique is developed in this study using normal modes analysis with Lumped Mass. With this method, the progressively improved results of F. E. analysis are obtained using the simplified beam model. The static and normal modes analysis are performed with the joint stiffness values obtained by the Kazunori Shimonkakis' virtual stiffness method and the proposed method and these simplified modeling errors are compared.

• 한국해양공학회지
• /
• 제2권2호
• /
• pp.51-60
• /
• 1988

A data transform is performed by using a point-electrode focusing method in order to obtain accurate and objective interpretation of the borehole normal resistivity data. Two new synthetic curves can be generated through the data transform. The one is an approximate apparent resistivity curve, which would be used to predict the true resistivity of the formation. The other one is a bed boundary coefficient curve, which would be used to distinguish bed boundaries. The accuracy of the normal data interpretation can be improved and this method takes much less computational time than a linear inversion technique. Moreover, this method does not require an initial guess model and limitation of number of unknown parameters. Since this algorithm can be run on a personal computer, an immediate interpretation would be possible at the field work site. If an additional set of electrodes(a=125cm)is attached to a normal resistivity tool which is being used (a=25cm, 50cm, 100cm), the apparent resistivity for the point-electrode focusing device can be calculated, and it would maximize the use of short and long normal resistivity data and promote the accuracy of the interpretation.

• 한국멀티미디어학회논문지
• /
• 제25권6호
• /
• pp.886-893
• /
• 2022

Outlier detection refers to the task of detecting data that deviate significantly from the normal data distribution. Most outlier detection methods compute an outlier score which indicates the degree to which a data sample deviates from normal. However, setting a threshold for an outlier score to determine if a data sample is outlier or normal is not trivial. In this paper, we propose a binary prediction method for outlier detection based on spectral clustering and one-class SVM ensemble. Given training data consisting of normal data samples, a clustering method is performed to find clusters in the training data, and the ensemble of one-class SVM models trained on each cluster finds the boundaries of the normal data. We show how to obtain a threshold for transforming outlier scores computed from the ensemble of one-class SVM models into binary predictive values. Experimental results with high dimensional text data show that the proposed method can be effectively applied to high dimensional data, especially when the normal training data consists of different shapes and densities of clusters.

• 한국CDE학회논문집
• /
• 제13권1호
• /
• pp.1-7
• /
• 2008

Data compression becomes increasingly an important issue for reducing data storage spaces as well as transmis-sion time in network environments. In 3D geometric models, the normal vectors of faces or meshes take a major portion of the data so that the compression of the vectors, which involves the trade off between the distortion of the images and compression ratios, plays a key role in reducing the size of the models. So, raising the compression ratio when the normal vector is compressed and minimizing the visual distortion of shape model's shading after compression are important. According to the recent papers, normal vector compression is useful to heighten com-pression ratio and to improve memory efficiency. But, the study about distortion of shading when the normal vector is compressed is rare relatively. In this paper, new normal vector compression method which is clustering normal vectors and assigning Representative Normal Vector (RNV) to each cluster and using the angular deviation from actual normal vector is proposed. And, using this new method, Visually Undistinguishable Lossy Compression (VULC) algorithm which distortion of shape model's shading by angular deviation of normal vector cannot be identified visually has been developed. And, being applied to the complicated shape models, this algorithm gave a good effectiveness.