• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.67 no.3
• /
• pp.460-466
• /
• 2018

For the efficient energy consumption in an urban railway station, it is necessary to know the patterns of electrical loads for each usage in detail. The electrical loads in an urban railway station have different characteristics from other normal electrical load, such as the peak load timing during a day. The lighting, HVAC, communication, and commercial loads make up large amount of electrical load for equipment in an urban railway station, and each of them has the unique specificity. These loads for each usage were estimated without measuring device by the polynomial regression method with big data such as total amount of electrical load and weather data. In the simulation with real data, the optimal polynomial regression model was third order polynomial regression model with 9 or 10 independent variables.

• Nuclear Engineering and Technology
• /
• v.31 no.2
• /
• pp.172-181
• /
• 1999

Series expansion methods to compute the exponential of a matrix have been compared by applying them to fuel depletion calculations. Specifically, Taylor, Pade, Chebyshev, and rational Chebyshev approximations have been investigated by approximating the exponentials of bum matrices by truncated series of each method with the scaling and squaring algorithm. The accuracy and efficiency of these methods have been tested by performing various numerical tests using one thermal reactor and two fast reactor depletion problems. The results indicate that all the four series methods are accurate enough to be used for fuel depletion calculations although the rational Chebyshev approximation is relatively less accurate. They also show that the rational approximations are more efficient than the polynomial approximations. Considering the computational accuracy and efficiency, the Pade approximation appears to be better than the other methods. Its accuracy is better than the rational Chebyshev approximation, while being comparable to the polynomial approximations. On the other hand, its efficiency is better than the polynomial approximations and is similar to the rational Chebyshev approximation. In particular, for fast reactor depletion calculations, it is faster than the polynomial approximations by a factor of ∼ 1.7.

• Journal of the Korean Statistical Society
• /
• v.23 no.1
• /
• pp.115-134
• /
• 1994

Polynomial errors-in-variables model with one predictor variable and one response variable is defined and an estimator of model is derived following the Booth's linear model estimation procedure. Since polynomial model is nonlinear function of the unknown regression coefficients and error-free predictors, it is nonlinear model in errors-in-variables model. As a result of applying linear model estimation method to nonlinear model, some additional assumptions are necessary. Hence, an estimator is derived under the assumption that the error variances are decrasing as sample size increases. Asymptotic propoerties of the derived estimator are provided. A simulation study is presented to compare the small sample properties of the derived estimator with those of OLS estimator.

• Transactions of the Korean Society of Mechanical Engineers
• /
• v.18 no.12
• /
• pp.3219-3226
• /
• 1994

A model is constructed to evaluate the stress intensity factors for a center crack subjected to polynomial anti-symmetric loading in a layered material. A Fredholm integral equation is derived by Fourier integral transform method. The integral equation is numerically analyzed to evaluate the effects of the ratios of shear modulus, Poisson's ratio and crack length to layer thickness as well as the number of layers on the stress intensity factor. The stress intensity factors are approached to constant values as the number of layers increase and decrease as the polynomial power of the loading increase. In case of the E-glass/Epoxy composite, dimensionless stress intensity factor is affected by cracked-resin layer thickness.

• Communications of the Korean Mathematical Society
• /
• v.35 no.2
• /
• pp.533-546
• /
• 2020

Since Sheffer introduced the so-called Sheffer polynomials in 1939, the polynomials have been extensively investigated, applied and classified. In this paper, by using matrix algebra, specifically, some properties of Pascal and Wronskian matrices, we aim to present certain interesting identities involving the 2-variable truncated exponential based Sheffer polynomial sequences. Also, we use the main results to give some interesting identities involving so-called 2-variable truncated exponential based Miller-Lee type polynomials. Further, we remark that a number of different identities involving the above polynomial sequences can be derived by applying the method here to other combined generating functions.

• Proceedings of the KIEE Conference
• /
• 2005.10b
• /
• pp.155-157
• /
• 2005

We propose a new category of hybrid multi-layer neural networks with hetero nodes such as Fuzzy Set based Polynomial Neurons (FSPNs) and Polynomial Neurons (PNs). These networks are based on a genetically optimized multi-layer perceptron. We develop a comprehensive design methodology involving mechanisms of genetic optimization and genetic algorithms, in particular. The augmented genetically optimized HFPNN (namely gHFPNN) results in a structurally optimized structure and comes with a higher level of flexibility in comparison to the one we encounter in the conventional HFPNN. The GA-based design procedure being applied at each layer of HFPNN leads to the selection of preferred nodes (FPNs or PNs) available within the HFPNN. In the sequel, two general optimization mechanisms are explored. First, the structural optimization is realized via GAs whereas the ensuing detailed parametric optimization is carried out in the setting of a standard least square method-based learning. The performance of the gHFPNNs quantified through experimentation where we use a number of modeling benchmarks-synthetic and experimental data already experimented with in fuzzy or neurofuzzy modeling.

• Proceedings of the IEEK Conference
• /
• 2009.05a
• /
• pp.261-263
• /
• 2009

본 연구에서는 복잡한 비선형 모델링 방법인 RBF 뉴럴 네트워크(Radial Basis Function Neural Network)와 PNN(Polynomial Neural Network)을 접목한 새로운 형태의 Radial Basis Function Polynomial Neural Network(RPNN)를 제안한다. RBF 뉴럴 네트워크는 빠른 학습 시간, 일반화 그리고 단순화의 특징으로 비선형 시스템 모델링 등에 적용되고 있으며, PNN은 생성된 노드들 중에서 우수한 결과값을 가진 노드들을 선택함으로써 모델의 근사화 및 일반화에 탁월한 효과를 가진 비선형 모델링 방법이다. 제안된 RPNN모델의 기본적인 구조는 PNN의 형태를 이루고 있으며, 각각의 노드는 RBF 뉴럴 네트워크로 구성하였다. 사용된 RBF 뉴럴 네트워크에서의 커널 함수로는 FCM 클러스터링을 사용하였으며, 각 노드의 후반부는 다항식 구조로 표현하였다. 또한 각 노드의 후반부 파라미터들은 최소자승법을 이용하여 최적화 하였다. 제안한 모델의 적용 및 유용성을 비교 평가하기 위하여 비선형 데이터를 이용하여 그 우수성을 보인다.

• Journal of Electrochemical Science and Technology
• /
• v.8 no.2
• /
• pp.115-123
• /
• 2017

Electrochemical noise signals in many cases exhibit a DC drift that should be removed prior to further data analysis. Polynomial fitting and moving average removal method have been used to remove trends of electrochemical noise (EN) in time domain. The corrosion inhibition of synthesized schiff base N,N'-bis(3,5-dihydroxyacetophenone)-2,2-dimethylpropandiimine on API-5L-X70 steel in hydrochloric acid solutions were used to study the effects of drifts removal methods on noise resistance calculation. Also, electrochemical impedance spectroscopy (EIS) was used to study the corrosion inhibition property of the inhibitor. The results showed that for the calculation of $R_n$, both methods were effective in trend removal and the polynomial with m=4 and MAR with p=40 were in agreement.

• Journal of the Korean School Mathematics Society
• /
• v.9 no.2
• /
• pp.121-139
• /
• 2006

This study identified the problems of teaching quadratic functions using a translation and a vertex form by completing squares of which method make teaching contents not to be interconnected and tend to interfere students' conceptual understanding. This seems to generated from which the current mathematics curriculum is not organized to deliver the related contents of quadratic functions from polynomial expressions students have already known. To resolve it this study investigates the properties of quadratic functions from a polynomial perspective and discusses classroom implications with a couple of concrete applications.

• Proceedings of the KIEE Conference
• /
• 1999.07g
• /
• pp.2863-2865
• /
• 1999

In this paper we present the modeling of ozone prediction system using polynomial neural network. The Polynomial Neural Network is a useful tool for data learning, nonlinear function estimation and prediction of dynamic system. The mechanism of ozone concentration is highly complex, nonlinear, nonstationary. The purposed method shows that the prediction to the ozone concentration based upon a polynomial neural network gives us a good performance for ozone prediction with ability of superior data approximation.