• 융합신호처리학회 학술대회논문집
• /
• 한국신호처리시스템학회 2000년도 하계종합학술대회논문집
• /
• pp.1-4
• /
• 2000

In this paper, A useful nonlinear function for the RBF(Radial Basis Function) equalization is proposed. This proposed function need not calculate an exponential function that is generally used for conventional RBF equalizer and uses the only four rules of arithmetic. Therefore the computational requirement for the RBF equalizer with the proposed function is decreased. As a computer simulation result, the equalizer with the proposed function effectively reduce nonlinear intersymbol interference, caused by nonlinear communication channel.

• 대한수학회논문집
• /
• 제29권3호
• /
• pp.479-487
• /
• 2014

In this paper, we obtain some theorems on certain Euler type integrals involving generalized Mittag-Leffler function. Further, we deduce some special cases involving Wiman function, Prabhakar function and exponential and binomial functions.

• East Asian mathematical journal
• /
• 제3권
• /
• pp.33-46
• /
• 1987

• 한국산학기술학회논문지
• /
• 제15권3호
• /
• pp.1724-1733
• /
• 2014

본 논문에서는 비모노톤함수(non-monotone function)인 CosExp(cosine-modulated symmetric Exponential function) 함수와 모노톤함수(monotone function)인 시그모이드 함수를 캐스케이드 코릴레이션 알고리즘(Cascade Correlation algorithm)의 학습에 병행해서 사용하여 이중나선문제(two spirals problem)의 패턴인식에 어떠한 영향이 있는지 분석하고 이어서 알고리즘의 최적화를 시도한다. 첫 번째 실험에서는 알고리즘의 후보뉴런에 CosExp 함수를 그리고 출력뉴런에는 시그모이드 함수를 사용하여 나온 인식된 패턴을 분석한다. 두 번째 실험에서는 반대로 CosExp 함수를 출력뉴런에서 사용하고 시그모이드 함수를 후보뉴런에 사용하여 실험하고 결과를 분석한다. 세 번째 실험에서는 후보뉴런을 위한 8개의 풀을 구성하여 변형된 다양한 시그모이드 활성화 함수(sigmoidal activation function)를 사용하고 출력뉴런에는 CosExp함수를 사용하여 얻게 된 입력공간의 인식된 패턴을 분석한다. 네 번째 실험에서는 시그모이드 함수의 변위를 결정하는 세 개의 파라미터 값을 유전자 알고리즘을 이용하여 얻는다. 이 파라미터 값들이 적용된 시그모이드 함수들은 후보뉴런의 활성화를 위해서 사용되고 출력뉴런에는 CosExp 함수를 사용하여 실험한 최적화 된 결과를 분석한다. 이러한 알고리즘의 성능평가를 위하여 각 학습단계 마다 입력패턴공간에서 인식된 이중나선의 형태를 그래픽으로 보여준다. 최적화 과정에서 은닉뉴런(hidden neuron)의 숫자가 28에서 15로 그리고 최종적으로 12개로 줄어서 학습 알고리즘이 최적화되었음을 확인하였다.

• 한국학교수학회논문집
• /
• 제15권2호
• /
• pp.299-316
• /
• 2012

본 연구에서는 이차함수, 유리함수, 무리함수, 지수함수, 로그함수, 삼각함수와 같이 고등학교 수학 교육과정에서 이미 배운 기본적인 함수들의 모양 그리기와 해석하는 능력을 분석하였다. 00 고등학교의 인문반 2개반(64명)과 자연반 2개반(64명)을 대상으로 조사한 결과 주어 진 함수들의 모양을 그리지 못한 학생이 50% 이상이었다. 또한 함수가 지닌 중요한 성질인 정의역, 치역, 최솟값, 최댓값, 주기 등에 대한 해석하는 능력이 부족한 것으로 나타났다. 본 연구에서는 함수단원이 고등학교 수학이나 대학 교양 수학에서 기초가 되는 내용이므로 함수의 개념과 함수의 모양 그리기, 함수의 모양 오류 데이터 분석 등의 수학학습에 관하여 연구하였다.

• 대한기계학회:학술대회논문집
• /
• 대한기계학회 2000년도 춘계학술대회논문집B
• /
• pp.252-257
• /
• 2000

An efficient method is developed for mold thermal cycle analysis in repeated forming process, which is well suited to the analysis in TV glass production. plunger, which is a mold to press-form the glass, undergoes temperature fluctuation during a cycle due to the repeated contact and separation from the glass, which attains a cyclic steady state in the end. If analyzed straightforwardly of this problem, it leads to more than 80 cycles to get reasonable solution, and it is yet hard to setup stopping creteria due to extremely slow convergence. An exponential fitting method is proposed to solve the problem, where an exponential function is found to best approximate temperature values of 3 consecutive cycles, and new cycle is restarted with the function value at infinite time. From numerical implementation, it is found that the method reduces the number of cycles dramatically to only $6{\sim}15$ cycles to reach accurate solution within $1^{\circ}$ error. A system for the analysis is contructed, in which the thermal analysis is performed by commercial software ANSYS, and the fitting of the result is done by IMSL library.

• Industrial Engineering and Management Systems
• /
• 제8권4호
• /
• pp.257-263
• /
• 2009

Focusing on the idea that the equation of exponential smoothing method (ESM) is equivalent to (1, 1) order ARMA model equation, new method of estimation of smoothing constant in exponential smoothing method is proposed before by us which satisfies minimum variance of forecasting error. Theoretical solution was derived in a simple way. Mere application of ESM does not make good forecasting accuracy for the time series which has non-linear trend and/or trend by month. A new method to cope with this issue is required. In this paper, combining the trend removal method with this method, we aim to improve forecasting accuracy. An approach to this method is executed in the following method. Trend removal by a linear function is applied to the original shipping data of consumer goods. The combination of linear and non-linear function is also introduced in trend removal. For the comparison, monthly trend is removed after that. Theoretical solution of smoothing constant of ESM is calculated for both of the monthly trend removing data and the non monthly trend removing data. Then forecasting is executed on these data. The new method shows that it is useful especially for the time series that has stable characteristics and has rather strong seasonal trend and also the case that has non-linear trend. The effectiveness of this method should be examined in various cases.

• Journal of Advanced Marine Engineering and Technology
• /
• 제29권8호
• /
• pp.877-882
• /
• 2005

This paper discusses the lateral vibration of a bar which has its tip free. The uniform bar has a solution by summation of some simple exponential functions But if its shape is not uniform, its solution could be by Bessel's function, or mathematical solution could not be existed. Enen if the solution of Bessel's function exists. as Bessel function is a series function. we must got the solution by numerical method Hereby the author Proposes the ununiform beam solution of the matrix method by Ritz's method. and Proposes a new deflection shape function.

• 호남수학학술지
• /
• 제26권4호
• /
• pp.463-469
• /
• 2004

In this paper we establish some recurrence relations satisfied by quotient moments of upper record values from the exponential distribution. Let $\{X_n,\;n{\geq}1\}$ be a sequence of independent and identically distributed random variables with a common continuous distribution function F(x) and probability density function(pdf) f(x). Let $Y_n=max\{X_1,\;X_2,\;{\cdots},\;X_n\}$ for $n{\geq}1$. We say $X_j$ is an upper record value of $\{X_n,\;n{\geq}1\}$, if $Y_j>Y_{j-1}$, j > 1. The indices at which the upper record values occur are given by the record times {u(n)}, $n{\geq}1$, where u(n)=min\{j{\mid}j>u(n-1),\;X_j>X_{u(n-1)},\;n{\geq}2\} and u(1) = 1. Suppose $X{\in}Exp(1)$. Then $\Large{E\;\left.{\frac{X^r_{u(m)}}{X^{s+1}_{u(n)}}}\right)=\frac{1}{s}E\;\left.{\frac{X^r_{u(m)}}{X^s_{u(n-1)}}}\right)-\frac{1}{s}E\;\left.{\frac{X^r_{u(m)}}{X^s_{u(n)}}}\right)}$ and $\Large{E\;\left.{\frac{X^{r+1}_{u(m)}}{X^s_{u(n)}}}\right)=\frac{1}{(r+2)}E\;\left.{\frac{X^{r+2}_{u(m)}}{X^s_{u(n-1)}}}\right)-\frac{1}{(r+2)}E\;\left.{\frac{X^{r+2}_{u(m-1)}}{X^s_{u(n-1)}}}\right)}$.

• Journal of the Korean Data and Information Science Society
• /
• 제6권1호
• /
• pp.97-103
• /
• 1995

In this paper, we propose estimators of Gini index of the exponential distribution. We also obtain the distribution and the moments of the proposed estimators. The moments of the proposed estimators are derived by special function. We compare the maximum likelihood estimator (MLE) of Gini index with the proposed estimator of Gini index in the sense of MSE through Monte Carlo Method.