• 한국수자원학회논문집
• /
• 제35권5호
• /
• pp.541-552
• /
• 2002

본 연구에서는 전체탐색기법 중 Simplex법의 원리를 이용한 SCE-UA법과 Annealing-Simplex (A-S)법을 일유출량 추정 수문모형인 탱크모형의 매개변수 보정에 적용하여 국부탐색기법인 Downhill Simplex법의 결과와 비교하여 탐색능력을 평가하였다. 오차가 없는 합성자료를 사용한 보정에서 A-S법이 목적함수에 관계없이 전역최적해를 탐색하는 결과를 나타냈으며, SCE-UA법은 ABSERR를 목적함수로 사용할 경우에 전역최적해를 탐색하는 결과를 나타냈으며, 다른 목적함수를 사용하는 경우에는 최적해에 가까운 탐색결과를 나타냈다. Downhill Simplex법은 초기값에 따라 다근 탐색결과를 나타냈으며, 최적해에 가까운 초기값을 사용할 경우 전역 최적해를 탐색하는 결과를 나타냈다. 실측자료를 사용한 보정에서는 A-S법과 SCE-UA법이 목적함수에 관계없이 양호한 결과를 나타냈다. 두 개의 서로 다른 단일 목적함수를 조합하여 만든 목적함수 중 DRMS와 NS의 조합에 의해 만들어진 목적함수인 DN이 다른 목적함수보다 저유량에 비중을 더 둔 예측결과를 나타냈으며, 전체 자료기간에 대해서 양호한 예측결과론 나타냈다.

• 한국농공학회지
• /
• 제44권7호
• /
• pp.1-13
• /
• 2002

Two global optimization methods, the SCE-UA method and the Annealing-simplex (A-S) method for calibrating a daily rainfall-runoff model, a Tank model, was compared with that of the Downhill Simplex method. The performance of the four objective functions, DRMS (daily root mean square), HMLE (heteroscedastic maximum likelihood estimator), ABSERR (mean absolute error), and NS (Nash-Sutcliffe measure), was tested and synthetic data and historical data were used. In synthetic data study. 100% success rates for all objective functions were obtained from the A-S method, and the SCE-UA method was also consistently able to obtain good estimates. The downhill simplex method was unable to escape from local optimum, the worst among the methods, and converged to the true values only when the initial guess was close to the true values. In the historical data study, the A-S method and the SCE-UA method showed consistently good results regardless of objective function. An objective function was developed with combination of DRMS and NS, which putted more weight on the low flows.

• Industrial Engineering and Management Systems
• /
• 제8권1호
• /
• pp.29-36
• /
• 2009

We present two local-search based metaheuristics for the multi-source capacitated facility location problem. In such a problem, each customer's demand can be supplied by one or more facilities. The problem is NP-hard and the number of locations in the optimal solution is unknown. To keep the search process effective, the proposed methods adopt the following features: (1) a multi-exchange neighborhood structure, (2) a tabu list that keeps track of recently visited solutions, and (3) a multi-start to enhance the diversified search paths. The transportation simplex method is applied in an efficient manner to obtain the optimal solutions to neighbors of the current solution under the algorithm framework. Two in-and-out selection rules are also proposed in the algorithms with the purpose of finding promising solutions in a short computational time. Our computational results for some of the benchmark instances, as well as some instances generated using a method in the literature, have demonstrated the effectiveness of this approach.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제4권3호
• /
• pp.259-265
• /
• 2004

In this study, a hybrid genetic algorithm merged with simulated annealing is presented to solve nonlinear channel blind equalization problems. The equalization of nonlinear channels is more complicated one, but it is of more practical use in real world environments. The proposed hybrid genetic algorithm with simulated annealing is used to estimate the output states of nonlinear channel, based on the Bayesian likelihood fitness function, instead of the channel parameters. By using the desired channel states derived from these estimated output states of the nonlinear channel, the Bayesian equalizer is implemented to reconstruct transmitted symbols. In the simulations, binary signals are generated at random with Gaussian noise. The performance of the proposed method is compared with those of a conventional genetic algorithm(GA) and a simplex GA. In particular, we observe a relatively high accuracy and fast convergence of the method.

• 한국정보통신학회논문지
• /
• 제11권11호
• /
• pp.2158-2165
• /
• 2007

본 논문에서는 비선형 블라인드 채널등화기의 구현을 위하여 가우시안 가중치(gaussian weights)를 이용한 개선된 퍼지 클러스터(Modified Fuzzy C-Means with Gaussian Weights: MFCM_GW) 알고리즘을 제안한다. 제안된 알고리즘은 기존 FCM 알고리즘의 유클리디언 거리(Euclidean distance) 값 대신 Bayesian Likelihood 목적 함수(fitness function)와 가우시안 가중치가 적용된 멤버십 매트릭스(partition matrix)를 이용하여, 비선형 채널의 출력으로 수신된 데이터들로부터 최적의 채널 출력 상태 값(optimal channel output states)들을 직접 추정한다. 이렇게 추정된 채널 출력 상태 값들로 비선형 채널의 이상적 채널 상태(desired channel states) 백터들을 구성하고, 이를 Radial Basis Function(RBF) 등화기의 중심(center)으로 활용함으로써 송신된 데이터 심볼을 찾아낸다. 실험에서는 무작위 이진 신호에 가우시안 잡음이 추가된 데이터를 사용하여 기존의 Simplex Genetic Algorithm(GA), 하이브리드 형태의 GASA(GA merged with simulated annealing(SA)), 그리고 과거에 발표되었던 MFCM 등과 그 성능을 비교 분석하였으며, 가우시안 가중치가 적용된 MFCM_GW를 이용한 채널등화기가 상대적으로 정확도와 속도 면에서 우수함을 보였다.

• 한국국방경영분석학회지
• /
• 제17권1호
• /
• pp.146-158
• /
• 1991

In this paper, we deal with the TSP (Traveling Salesperson Problem) which is well-known as NP-complete optimization problem. the TSP is applicable to network routing. task allocation or scheduling. and VLSI wiring. Well known numerical methods such as Newton's Metheod. Gradient Method, Simplex Method can not be applicable to find Global Solution but the just give Local Minimum. Exhaustive search over all cyclic paths requires 1/2 (n-1) ! paths, so there is no computer to solve more than 15-cities. Heuristic algorithm. Simulated Annealing, Artificial Neural Net method can be used to get reasonable near-optimum with polynomial execution time on problem size. Therefore, we are able to select the fittest one according to the environment of problem domain. Three methods are simulated about symmetric TSP with 30 and 50-city samples and are compared by means of the quality of solution and the running time.

• 한국수자원학회논문집
• /
• 제38권12호
• /
• pp.1061-1072
• /
• 2005

본 연구에서는 영산호의 상류에 위치한 나주유역의 홍수시 유출량을 실시간으로 예측하기 위하여 Grey홍수 유출모형을 개발하였다. 나주유역의 유출량은 나주수위관측소에서 실시간으로 측정하고 있으며, 이곳은 영산호의 유입홍수량을 예측과 홍수관리를 위한 주관측소이다. 모형의 지배방정식은 Grey시스템 이론에 근거하여 구성되었으며, 모형의 매개변수는 Grey 시스템매개변수의 조합으로 구성하였다. 모형의 차수는 실측자료와 모의결과를 비교하여 다른 차수 보다 양호한 결과를 나타내는 5차로 하였다. 모형의 보정시 예측결과와 실측치간의 RMSE는 $3.1\~290.5m^{3}/sec$를 나타냈으며, $R^{2}$는 $0.909\~0.999$를 나타냈다. 모형의 검정시 예측결과와 실측치간의 RMSE는 $20.6\~147.4m^{3}/sec$를 나타냈으며, $R^{2}는\;0.940\~0.998$를 나타냈다. 매개변수가 추정된 모형을 이용하여 담수호의 유입량을 하천수위 상태에 따라 예측한 결과, 하천수위가 상승할 경우와 하강할 경우의 예측 홍수량은 예측시간이 증가할수록 커지는 경향을 나타냈다. 또한, 하천수위가 첨두에 가까운 시기의 홍수량은 예측시간에 관계없이 실측자료와 비슷한 결과를 나타냈다. 이와 같은 결과는 Grey 홍수유출모형을 홍수시 담수호 유입량을 실시간으로 정확하게 예측하는데 적용할 수 있음을 나타낸다.

• 한국멀티미디어학회논문지
• /
• 제9권12호
• /
• pp.1689-1699
• /
• 2006

A nonlinear channel blind equalizer by using a hybrid genetic algorithm, which merges a genetic algorithm with simulated annealing, and a RBF network is presented. In this study, a hybrid genetic algorithm is used to estimate the output states of a nonlinear channel, based on the Bayesian likelihood fitness function, instead of the channel parameters. From these estimated output states, the desired channel states of the nonlinear channel are derived and placed at the center of a RBF equalizer to reconstruct transmitted symbols. In the simulations, binary signals are generated at random with Gaussian noise. The performance of the proposed method is compared with those of a conventional genetic algorithm(GA) and a simplex GA, and the relatively high accuracy and fast convergence of the method are achieved.

• 음성과학
• /
• 제10권4호
• /
• pp.7-21
• /
• 2003

Sums-of-Products models were built for segment duration prediction of spoken Korean. An experiment for the modelling was carried out to apply the results to Korean text-to-speech synthesis systems. 670 read sentences were analyzed. trained and tested for the construction of the duration models. Traditional sequential rule systems were extended to simple additive, multiplicative and additive-multiplicative models based on Sums-of-Products modelling. The parameters used in the modelling include the properties of the target segment and its neighbors and the target segment's position in the prosodic structure. Two optimisation strategies were used: the downhill simplex method and the simulated annealing method. The performance of the models was measured by the correlation coefficient and the root mean squared prediction error (RMSE) between actual and predicted duration in the test data. The best performance was obtained when the data was trained and tested by ' additive-multiplicative models. ' The correlation for the vowel duration prediction was 0.69 and the RMSE. 31.80 ms. while the correlation for the consonant duration prediction was 0.54 and the RMSE. 29.02 ms. The results were not good enough to be applied to the real-time text-to-speech systems. Further investigation of feature interactions is required for the better performance of the Sums-of-Products models.

• 한국멀티미디어학회논문지
• /
• 제11권12호
• /
• pp.1625-1634
• /
• 2008

In this study, a modified Fuzzy C-Means algorithm with Gaussian weights (MFCM_GW) is presented for the problem of nonlinear blind channel equalization. The proposed algorithm searches for the optimal channel output states of a nonlinear channel based on received symbols. In contrast to conventional Euclidean distance in Fuzzy C-Means (FCM), the use of the Bayesian likelihood fitness function and the Gaussian weighted partition matrix is exploited in this method. In the search procedure, all possible sets of desired channel states are constructed by considering the combinations of estimated channel output states. The set of desired states characterized by the maxima] value of the Bayesian fitness is selected and updated by using the Gaussian weights. After this procedure, the Bayesian equalizer with the final desired states is implemented to reconstruct transmitted symbols. The performance of the proposed method is compared with those of a simplex genetic algorithm (GA), a hybrid genetic algorithm (GA merged with simulated annealing (SA):GASA), and a previously developed version of MFCM. In particular, a relative]y high accuracy and a fast search speed have been observed.