• The Korean Journal of Applied Statistics
• /
• v.36 no.2
• /
• pp.115-127
• /
• 2023

Multinomial probit model is a popular model for multiclass classification and choice model. Markov chain Monte Carlo (MCMC) method is widely used for estimating multinomial probit model, but its computational cost is high. However, it is well known that variational Bayesian approximation is more computationally efficient than MCMC, because it uses subsets of samples. In this study, we describe multinomial probit model with Gaussian process classification and how to employ variational Bayesian approximation on the model. This study also compares the results of variational Bayesian multinomial probit model to the results of naive Bayes, K-nearest neighbors and support vector machine for the UCI mice protein expression level data.

• The Journal of the Acoustical Society of Korea
• /
• v.20 no.4
• /
• pp.12-16
• /
• 2001

To analyze the performance of array shape estimation techniques using auxiliary sensors, the appropriate number and the positions of auxiliary sensors are investigated. Also, a post-processing technique based on spline interpolation is proposed to improve the performance of array shape estimation. The simulation results showed that when auxiliary sensors are arranged uniformly, the performance of shape estimation is better than other arrangements of auxiliary sensors. Also, the proposed post-processing technique improved the performance of the existing shape estimation method, such as Kalman filter method.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.2
• /
• pp.169-175
• /
• 2021

The lot sizing problem(LSP) is a hard problem that classified as non-deterministic(NP)-complete because of the polynomial-time optimal solution algorithm is unknown yet. The well-known W-W algorithm can be obtain the solution within polynomial-time, but this algorithm is a very complex, therefore the heuristic approximated S-M algorithm is suggested. This paper suggests O(n) linear-time complexity algorithm that can be find not the approximated but optimal solution. This algorithm determines the lot size Xt∗ in period t to the sum of the demands of interval [t,t+k], the period t+k is determined by the holding cost will not exceed setup cost of t+k period. As a result of various experimental data, this algorithm finds the optimal solution about whole data.

• Journal of the Korea Society of Computer and Information
• /
• v.19 no.11
• /
• pp.175-181
• /
• 2014

This paper suggests O(m) polynomial time heuristic algorithm to obtain the solution for the driver scheduling problem, DSP, that has been classified as NP-complete problem. The proposed algorithm gets the initial assignment of n minimum number of drivers from given m schedules. Nextly, this algorithm gets the minimum total time (TC) using 5 rules of swap and insert for decrease of over times (OT) and idle times (IT). Although this algorithm is a heuristic polynomial time algorithm with O(m) time complexity rules to be find a optimal (or approximate) solution, this algorithm is equal to metaheuristic methods for the 5 experimental data. To conclude, this paper shows the DSP is not NP-complete problem but Polynomial time (P)-problem with polynomial time rules.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 2007.11a
• /
• pp.130-133
• /
• 2007

본 논문에서는 서로 다른 주문들의 일부를 일괄적으로 처리할 수 있을 때, 최대 개수의 작업 단위로 최대한 많은 수의 주문을 처리하는 문제를 다룬다. 무향그래프와 배치 크기 $\lambda$로 표현되는 이 문제의 일반적인 경우는 NP-hard이며, 나무일 때 다항시간 안에 최적해를 찾을 수 있음이 증명되어 있다. 본 논문에서는 이분 그래프의 경우에도 NP-hard임을 보이고, 이 경우에 절대근사 알고리즘과 상대근사 알고리즘을 제시한다.

• Tunnel and Underground Space
• /
• v.31 no.6
• /
• pp.480-493
• /
• 2021

Since the generalized Hoek-Brown criterion (GHB) provides an efficient way of identifying its strength parameter values with the consideration of in-situ rock mass condition via Geological Strength Index (GSI), this criterion is recognized as one of the standard rock mass failure criteria in rock mechanics community. However, the nonlinear form of the GHB criterion makes its mathematical treatment inconvenient and limits the scope of its application. As an effort to overcome this disadvantage of the GHB criterion, the explicit approximate analytical equations for the minimum principal stress, which is associated with the maximum principal stress at failure, are formulated based on the Taylor polynomial approximation of the original GHB criterion. The accuracy of the derived approximate formula for the minimum principal stress is verified by comparing the resulting approximate minimum principal stress with the numerically calculated exact values. To provide an application example of the approximate formulation, the equivalent friction angle and cohesion for the expected plastic zone around a circular tunnel in a GHB rock mass are calculated by incorporating the formula for the approximate minimum principal stress. It is found that the simultaneous consideration of the values of mi, GSI and far-field stress is important for the accurate calculation of equivalent Mohr-Coulomb parameter values of the plastic zone.

• The Korean Journal of Applied Statistics
• /
• v.4 no.2
• /
• pp.171-178
• /
• 1991

For the polynomial spline regression with fixed knots, some properties of the D-optimal design are discussed. Also the D-optimal design for some cases are found analytically by using a normalized B-spline basis for $S(P_m : k : \Delta)$. Based on the Kiefer-Wolfowitz equivalence theorem, the D-optimal design for some cases are found by numerical methods.

• Electronics and Telecommunications Trends
• /
• v.15 no.5 s.65
• /
• pp.86-93
• /
• 2000

지하 탐사용 레이더를 이용하여 지하에 매설된 구조물의 위치를 파악하고 그에 따른 근사 이미지의 추출 방법을 제안하였다. 기본원리는 구조물에 의해 산란되어 수신 안테나로 유입되는 펄스신호의 지연시간과 크기를 측정하는 데 있으며, 측정의 실용성을 위하여 레이더 탐색경로에 따른 수신신호의 절대치 적분 방법을 사용하였다. 일반적으로 지하매질은 침투 주파수에 따라서 다양한 분산 및 손실 특성을 나타내는데, 이러한 매질 특성은 다항 Debye 모델을 이용하여 기술되었다. 3차원 전파(電波) 전파(傳播)를 위한 시뮬레이션에는 FDTD(Finite Difference Time Domain) 방법을 사용하였다.

• Proceedings of the Acoustical Society of Korea Conference
• /
• autumn
• /
• pp.85-88
• /
• 2000

가늘고 긴 선배열을 해상에서 운용할 때 비선형 형상이 유도되므로 음원에 대한 정확한 탐지를 위하여 배열형상 추정이 필요하다. 방위센서를 이용한 배열형상 추정을 위하여 배열의 천 정도가 적은 경우에만 적용 가능한 다항 근사화 방법의 제한점을 극복하기 위하여 반복법을 제안하고, 수치 시뮬레이션을 통하여 반복회수에 따른 배열형상 추정결과를 분석하였다

• Journal for History of Mathematics
• /
• v.18 no.3
• /
• pp.39-54
• /
• 2005

In Chinese Mathematics, Jia Xian(要憲) introduced Zeng cheng kai fang fa(增乘開方法) to get approximations of solutions of Polynomial equations which is a generalization of square roots and cube roots in Jiu zhang suan shu. The synthetic divisions in Zeng cheng kai fang fa give ise to two concepts of Fan il(飜積) and Yi il(益積) which were extensively used in Chosun Dynasty Mathematics. We first study their history in China and Chosun Dynasty and then investigate the historical fact that Chosun mathematicians Nam Byung Gil(南秉吉) and Lee Sang Hyuk(李尙爀) obtained the sufficient conditions for Fan il and Yi il for quadratic equations and proved them in the middle of 19th century.