• 한국지능시스템학회논문지
• /
• 제26권1호
• /
• pp.87-92
• /
• 2016

본 논문에서는 일반적인 신경회로망의 단점인 느린 학습속도를 획기적으로 개선한 네트워크인 Extreme Learning Machine과 전문가들의 언어적 정보들을 기술 할 수 있는 퍼지 이론을 접목한 퍼지 Extreme Learning Machine을 최적화하기 위하여 Particle Swarm Optimization 알고리즘을 이용하였다. 퍼지 Extreme Learning Machine의 활성화 함수를 일반적인 시그모이드 함수를 사용하지 않고, 퍼지 C-Means 클러스터링 알고리즘의 활성화 레벨 함수를 이용하였다. Particle Swarm Optimization 알고리즘과 같은 최적화 알고리즘을 통하여 퍼지 Extreme Learning Machine의 활성화 함수의 파라미터들을 최적화 한다. Particle Swarm Optimization과 같은 최적화 알고리즘을 통한 제안된 모델의 최적화 하고 최적화된 모델의 분류성능을 평가하기 위하여 다양한 머신 러닝 데이터 집합을 사용하여 평가한다.

• Advances in Computational Design
• /
• 제1권3호
• /
• pp.235-251
• /
• 2016

We have performed a design optimization of a stiffened panel with curvilinear stiffeners using an artificial neural network (ANN) residual kriging based surrogate modeling approach. The ANN residual kriging based surrogate modeling involves two steps. In the first step, we approximate the objective function using ANN. In the next step we use kriging to model the residue. We optimize the panel in an iterative way. Each iteration involves two steps-shape optimization and size optimization. For both shape and size optimization, we use ANN residual kriging based surrogate model. At each optimization step, we do an initial sampling and fit an ANN residual kriging model for the objective function. Then we keep updating this surrogate model using an adaptive sampling algorithm until the minimum value of the objective function converges. The comparison of the design obtained using our optimization scheme with that obtained using a traditional genetic algorithm (GA) based optimization scheme shows satisfactory agreement. However, with this surrogate model based approach we reach optimum design with less computation effort as compared to the GA based approach which does not use any surrogate model.

• 전기학회논문지
• /
• 제58권8호
• /
• pp.1485-1495
• /
• 2009

This paper presents a novel approach to economic dispatch (ED) with nonconvex fuel cost function as combinatorial optimization problems (COP) while most of the conventional researches have been developed as function optimization problems (FOP). One nonconvex fuel cost function can be divided into several convex fuel cost functions, and each convex function can be regarded as a generation type (G-type). In that case, ED with nonconvex fuel cost function can be considered as COP finding the best case among all feasible combinations of G-types. In this paper, a genetic algorithm is applied to solve the COP, and the ${\lambda}-P$ function method is used to calculate ED for the fitness function of GA. The ${\lambda}-P$ function method is reviewed briefly and the GA procedure for COP is explained in detail. This paper deals with two kinds of ED problems, namely ED with multiple fuel units (EDMF) and ED with prohibited operating zones (EDPOZ). The proposed method is tested for all the ED problems, and the test results show an improvement in solution cost compared to the results obtained from conventional algorithms.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2004년도 추계학술대회 논문집
• /
• pp.902-907
• /
• 2004

In this paper, a multi-step optimization using a G.A. (Genetic Algorithm) with variable penalty function is introduced to the structural design optimization of a 5-head route machine. Our design procedure consist of two design optimization stage. The first stage of the design optimization is static design optimization. The following stage is dynamic design optimization stage. In the static optimization stage, the static compliance and weight of the structure are minimized simultaneously under some dimensional constraints and deflection limits. On the other hand, the dynamic compliance and the weight of the machine structure are minimized simultaneously in the dynamic design optimization stage. As the results, dynamic compliance of the 5-head router machine was decreased by about 37％ and the weight of the structure was decreased by 4.48％ respectively compared with the simplified structure model.

• Journal of applied mathematics & informatics
• /
• 제28권5_6호
• /
• pp.1527-1534
• /
• 2010

In this paper, we consider nonsmooth optimization problem of which objective and constraint functions are locally Lipschitz. We establish sufficient optimality conditions and duality results for nonsmooth vector optimization problem given under nearly strict invexity and near invexity-infineness assumptions.

• 한국광학회지
• /
• 제12권2호
• /
• pp.109-114
• /
• 2001

광학설계의 최적화에서는 광학수차를 줄이면서 광학계의 제한조건을 유지시켜야하며, 이를 위하여 Lagrange 부정승수법이 사용되고 있다. 이 과정에서 제한조건이 merit function의 error 항보다 우선적으로 보정된다. 본연구에서는 이를 이용하여 merit function에서 절대값이 큰 error의 보정조건을 제한조건으로 변경하여 우선적으로 보정하는 최적화의 능동적 제어법을 제안하고 이를 사진렌즈계의 최적화에 적용하였다.

• 대한기계학회논문집A
• /
• 제21권10호
• /
• pp.1561-1570
• /
• 1997

This study explores the treatment of the max-value cost function over a parameter interval in parametric optimization. To avoid the computational burden of the transformation treatment using an artificial variable, a direct treatment of the original max-value cost function is proposed. It is theoretically shown that the transformation treatment results in demanding an additional equality constraint of dual variables as a part of the Kuhn-Tucker necessary conditions. Also, it is demonstrated that the usability and feasibility conditions on the search direction of the transformation treatment retard convergence rate. To investigate numerical performances of both treatments, typical optimization algorithms in ADS are employed to solve a min-max steady-state response optimization. All the algorithm tested reveal that the suggested direct treatment is more efficient and stable than the transformation treatment. Also, the better performing of the direct treatment over the transformation treatment is clearly shown by constrasting the convergence paths in the design space of the sample problem. Six min-max transient response optimization problems are also solved by using both treatments, and the comparisons of the results confirm that the performances of the direct treatment is better than those of the tranformation treatment.

• 한국컴퓨터정보학회논문지
• /
• 제25권7호
• /
• pp.75-83
• /
• 2020

셀룰라 시스템에서 D2D 유틸리티 최적화 문제를 연구하도록 한다. 구체적으로, Non-Convex 최적화 문제의 복잡도를 완화하도록 해주는 오목함수 결정규칙을 제안하고자 한다. 일반적으로, 유틸리티 함수는 신호와 간섭의 함수이며, 해법이 복잡한 Non-Convex 형태를 가진다. 본 논문에서는 간단한 해법을 찾고자 유틸리티 함수를 간섭관점에서 분석한다. 먼저 D2D 수신단에서의 간섭 레벨을 의미하는 '상대간섭'과 간섭을 주요간섭으로 간략화하는 '간섭주요화'를 수식적으로 정의한다. 정의한 간섭주요화를 바탕으로 간단한 해법의 기반이 되는 오목함수 결정규칙과 최적화 해법이 간단한 Convex Optimization 해법을 제안하도록 한다. 실험결과를 통하여 유틸리티 함수는 D2D 적용시나리오에 해당하는 수치인 상대간섭 0.1 이하에서는 오목함수임을 확인하였다. 또한, 제안하는 Convex Optimization 해법은 상대간섭 수치 0.1 이하에서 적용이 가능함을 확인하였다.

• 한국지능시스템학회논문지
• /
• 제19권3호
• /
• pp.432-436
• /
• 2009

We have developed a new optimization algorithm termed simple bacteria cooperative optimization (sBCO) based on bacteria behavior patterns [1]. In [1], we have introduced the algorithm with basic operations and showed its feasibility with some function optimization problems. Since the sBCO was the first version with only basic operations, its performance was not so good. In this paper, we adopt a new operation, rank replacement, to the sBCO for improving its performance and compare its results to those of the simple genetic algorithm (sGA) which has been well known and widely used as an optimization algorithm. It was found from the experiments with four function optimization problems that the sBCO with rank replacement was superior to the sGA. This shows that our algorithm can be a good optimization algorithm.

• East Asian mathematical journal
• /
• 제34권1호
• /
• pp.1-16
• /
• 2018

We study an optimization problem for hyperbolic absolute risk aversion (HARA) utility function under two-factor Heston's stochastic volatility model. It is not possible to obtain an explicit solution because our financial market model is complicated. However, by using asymptotic analysis technique, we find the explicit forms of the approximations of the optimal value function and the optimal strategy for HARA utility function.