• 한국지능시스템학회논문지
• /
• 제9권6호
• /
• pp.650-656
• /
• 1999

본논문에서는 라마르크 진화와 볼드윈 효과를 진화전략에 적용하여 진화전략의 수렴성에 대해서 고찰한다. 또한 진화전략의 탐색법으로 랜덤 지역탐색법과 강화 지역 탐색법을 제안한다. 랜덤지역탐색은 미리 정한 일정한 회수의 지역탐색을 랜덤하게 수행하는 것이고 강화 지역탐색은 주어진 범위내에 존재하는 모든개체의 적합도를 평가하여 가장 적합도가 높은 개체 주변을 탐색하는 것이다. 이러한 관점에서 라마르크 진화와 볼드윈 효과를 기본으로 하는 강화 지역탐색은 단순히 랜덤하게 주변개체의 적합도를 탐색하는 것이 아니라 해 공간상에서 적합도가 높아지는 방향으로 지역 탐색을 행함으로써 랜덤 지역탐색에 비해 보다 효과적으로 주변 개체를 탐색할 수 있어 전역적 탐색능력의 향상은 물론 수렴속도의 향상은 가져 올수 있었다. 결과적으로 진화과정에 학습을 도입함으로써 진화만으로 최적해를 탐색할때보다 그성능이 향상됨을 볼 수 있다, 제안한 방법은 다양한 함수최적화 문제에 적용하여 그 시뮬레이션을 통해 학습이 진화에 미치는 영향에 대해서 고찰한다.

• 대한기계학회논문집A
• /
• 제37권11호
• /
• pp.1397-1405
• /
• 2013

본 연구에서 탑승자 머리 보호를 위한 센터 필라 트림의 리브 패턴 최적설계는 두 가지 방법에 의해 수행된다. 첫째는 실험계획법과 반응표면법을 이용한 근사최적화 기법으로써, 상대적으로 큰 비중을 차지하는 해석비용 저감을 위하여 근사모델 구성에 필요한 최소한의 해석만을 수행하고 실제 최적화 과정에는 구성된 모델을 이용함으로써 근사적으로 최적 점을 찾아가는 방법이다. 하지만 이러한 방법은 시행착오적인 반복과정을 거쳐야 하는 단점이 있다. 따라서 저자들의 선행연구에서 제안한 순차적 실험계획법과 인공신경망을 이용하여 인자의 상한 또는 하한에 걸리지 않는 근사최적 해를 체계적인 반복과정을 통해 도출하고자 하며, 이를 수학적인 예제와 구조물 문제에 적용함으로써 실용성을 확인하고자 한다.

• 공학교육연구
• /
• 제23권3호
• /
• pp.49-58
• /
• 2020

In the era of the fourth industrial revolution, the world is undergoing rapid social change. The purpose of this study is to predict the expected changes and necessary competencies and desired curriculum and teaching methods in the field of mechanical engineering in the near future. The research method was a Delphi study. It was conducted three times with 20 mechanical engineering experts. The results of the study are as follows: In the field of mechanical engineering, it will be increased the situational awareness by the use of measurement sensors, development of computer applications, flexibility and optimization by user's needs and mechanical equipment, and demand for robots equipped with AI. The mechanical engineer's career perspectives will be positive, but if it is stable, it will be a crisis. Therefore active response is needed. The competencies required in the field of mechanical engineering include collaborative skills, complex problem solving skills, self-directed learning skills, problem finding skills, creativity, communication skills, convergent thinking skills, and system engineering skills. The undergraduate curriculum to achieve above competencies includes four major dynamics, basic science, programming coding education, convergence education, data processing education, and cyber physical system education. Preferred mechanical engineering teaching methods include project-based learning, hands-on education, problem-based learning, team-based collaborative learning, experiment-based education, and software-assisted education. The mechanical engineering community and the government should be concerned about the education for mechanical engineers with the necessary competencies in the era of the 4th Industrial Revolution, which will make global competitiveness in the mechanical engineering fields.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권8호
• /
• pp.4072-4089
• /
• 2018

This paper introduces a scheme for optimizing the material properties of mass-spring systems of different resolutions to provide coherent behavior for reduced level-of-detail in MSS(Mass-Spring System) meshes. The global optimal material coefficients are derived to match the behavior of provided reference mesh. The proposed method also gives us insight into levels of reduction that we can achieve in the systematic behavioral coherency among the different resolution of MSS meshes. We obtain visually acceptable coherent behaviors for cloth models based on our proposed error metric and identify that this method can significantly reduce the resolution levels of simulated objects. In addition, we have confirmed coherent behaviors with different resolutions through various experimental validation tests. We analyzed spring force estimations through triangular Barycentric coordinates based from the reference MSS that uses a Gaussian kernel based distribution. Experimental results show that the displacement difference ratio of the node positions is less than 10% even if the number of nodes of $MSS^{sim}$ decreases by more than 50% compared with $MSS^{ref}$. Therefore, we believe that it can be applied to various fields that are requiring the real-time simulation technology such as VR, AR, surgical simulation, mobile game, and numerous other application domains.

• Journal of Electrical Engineering and Technology
• /
• 제1권4호
• /
• pp.435-447
• /
• 2006

This paper presents an application of the parallel Adaptive Evolutionary Algorithm (AEA) to search an optimal solution of the service restoration in electric power distribution systems, which is a discrete optimization problem. The main objective of service restoration is, when a fault or overload occurs, to restore as much load as possible by transferring the de-energized load in the out of service area via network reconfiguration to the appropriate adjacent feeders at minimum operational cost without violating operating constraints. This problem has many constraints and it is very difficult to find the optimal solution because of its numerous local minima. In this investigation, a parallel AEA was developed for the service restoration of the distribution systems. In parallel AEA, a genetic algorithm (GA) and an evolution strategy (ES) in an adaptive manner are used in order to combine the merits of two different evolutionary algorithms: the global search capability of the GA and the local search capability of the ES. In the reproduction procedure, proportions of the population by GA and ES are adaptively modulated according to the fitness. After AEA operations, the best solutions of AEA processors are transferred to the neighboring processors. For parallel computing, a PC cluster system consisting of 8 PCs was developed. Each PC employs the 2 GHz Pentium IV CPU and is connected with others through switch based fast Ethernet. To show the validity of the proposed method, the developed algorithm has been tested with a practical distribution system in Korea. From the simulation results, the proposed method found the optimal service restoration strategy. The obtained results were the same as that of the explicit exhaustive search method. Also, it is found that the proposed algorithm is efficient and robust for service restoration of distribution systems in terms of solution quality, speedup, efficiency, and computation time.

• 상하수도학회지
• /
• 제29권3호
• /
• pp.395-406
• /
• 2015

This research carried out an analysis on input cost and leakage reduction effect by leakage reduction method, focusing on the project for establishing an optimal water pipe network management system in the Taebaek region, which has been executed annually since 2009. Based on the result, optimal cost-benefit analysis models for water distribution network rehabilitation project were developed using DEA(data envelopment analysis) and multiple regression analysis, which have been widely utilized for efficiency analysis in public and other projects. DEA and multiple regression analysis were carried out by applying 4 analytical methods involving different ratios and costs. The result showed that the models involving the analytical methods 2 and 4 were of low significance (which therefore were excluded), and only the models involving the analytical methods 1 and 3 were suitable. From the result it was judged that the leakage management method to be executed with the highest priority for the improvement of revenue water ratio was installation of pressure reduction valve, followed by replacement of water distribution pipe, replacement of water supply pipe, and then leakage detection and repair; and that the execution of leakage management methods in this order would be most economical. In addition, replacement of water meter was also shown to be necessary in case there were a large number of defective water meters.

• 한국수자원학회논문집
• /
• 제37권2호
• /
• pp.133-144
• /
• 2004

토양수분 저류구조를 갖는 4단 탱크모형에 SCE-UA전역최적화 기법을 사용하여 목적함수에 따라 보정자료 기간을 달리하여 대청댐 유역에 332회, 소양강댐 유역에 대해 472회의 보정 및 검증을 수행하였다. 그리고 증발산량 산정방법에 따른 매개변수 추정 영향을 검토하기 위해 소형 증발계 증발량, 1963 Penman, FAO-24 Penman-Monteith, FAO-56 Penman-Monteith 방법을 사용하였다. 토양수분 저류구조를 갖는 탱크모형은 표준 4단 모형보다 우수한 결과를 나타내었다. 토양수분 저류구조를 갖는 탱크모형의 매개변수 추정에 적합한 목적함수 두 가지를 확인하였다. 매개변수 추정을 위해 적절한 자료기간은 3년 정도이었으며, 평균강수량 이상인 해와 가물었던 해를 포함하는 것이좋은 결과를 보였다. 그리고 유출률이 적절하지 않은 해를 포함하는 경우에는 8년 이상으로 하는 것이 적절하다고 판단된다. 4가지 증발산량 산정 방법에 의해 추정된 증발산량을 입력으로 모형을 보정한 결과 유사한 매개변수를 나타내었으며, 1963 Penman 방법만이 근소하게 열등하였다.

• 한국우주과학회:학술대회논문집(한국우주과학회보)
• /
• 한국우주과학회 2009년도 한국우주과학회보 제18권2호
• /
• pp.48.1-48.1
• /
• 2009

In recent years, many candidates for extra-solar planet have been discovered from various measurement techniques. Fueled by such discoveries, new space missions for direct detection of earth-like planets have been proposed and actively studied. TPF instrument is a fair example of such scientific endeavors. One of the many technical problems that space missions such as TPF would need to solve is deconvolution of the collapsed (i.e. spatially and temporally) spectral signal arriving at the detector surface and the deconvolution computation may fall into a local minimum solution, instead of the global minimum solution, in the optimization process, yielding mis-interpretation of the spectral signal from the potential earth-like planets. To this extend, observational and theoretical understanding on the spectral bio-signal from the Earth serves as the key reference datum for the accurate interpretation of the planetary bio-signatures from other star systems. In this study, we present ray tracing computational model for the on-going simulation study on the Earth bio-signatures. A multi-layered atmospheric model and sea ice variation model were added to the existing target Earth model and a hypothetical space instrument (called AmonRa) observed the spectral bio-signals of the model Earth from the L1 halo orbit. The resulting spectrums of the Earth show well known "red-edge" spectrums as well as key molecular absorption lines important to harbor life forms. The model details, computational process and the resulting bio-signatures are presented together with implications to the future study direction.

• 대한전자공학회논문지SP
• /
• 제44권5호
• /
• pp.54-63
• /
• 2007

본 논문은 영상 완성(image completion)을 위해 계층적으로 적용되는 새로운 에너지 최적화 방식을 제안한다. 영상 완성의 목적은 영상의 특정 영역이 지워진 상태에서, 그 지워진 부분을 나머지 부분과 시각적으로 어울리도록 완성시키는 기법을 말한다. 본 논문에서는 전역적 특징의 탐지, 주변 환경 변화에 대한 유연성, 계산비용의 감소, 영상 인페인팅과 같은 관련기법들로의 확장성 문제들을 다룰 수 있도록 마르코프 랜덤 필드(Markov Random Field)로 모델링 된 예제 기반 방식(exampler-based mehtod) 접근법을 택한다. 그리고 MRF에서의 에너지 최적화를 위해 BP 알고리즘(Belief Propagation Algorithm)의 변형인 우선순위 BP 알고리즘(Priority-Belief Propagation Algorithm)을 적용하였다. 본 논문에서 제안한 계층적 우선순위 BP 알고리즘(Hierarchical Priority-Belief Propagation Algorithm)은 MRF의 정점의 수를 줄이고 메시지를 계층적으로 전파한다. 이렇게 계층적 우선순위 BP 알고리즘을 영상 완성에 적용하여 여러 영상들에서 바람직한 결과를 얻었다.

• 산업경영시스템학회지
• /
• 제40권4호
• /
• pp.203-210
• /
• 2017

Data clustering is one of the most difficult and challenging problems and can be formally considered as a particular kind of NP-hard grouping problems. The K-means algorithm is one of the most popular and widely used clustering method because it is easy to implement and very efficient. However, it has high possibility to trap in local optimum and high variation of solutions with different initials for the large data set. Therefore, we need study efficient computational intelligence method to find the global optimal solution in data clustering problem within limited computational time. The objective of this paper is to propose a combined artificial bee colony (CABC) with K-means for initialization and finalization to find optimal solution that is effective on data clustering optimization problem. The artificial bee colony (ABC) is an algorithm motivated by the intelligent behavior exhibited by honeybees when searching for food. The performance of ABC is better than or similar to other population-based algorithms with the added advantage of employing fewer control parameters. Our proposed CABC method is able to provide near optimal solution within reasonable time to balance the converged and diversified searches. In this paper, the experiment and analysis of clustering problems demonstrate that CABC is a competitive approach comparing to previous partitioning approaches in satisfactory results with respect to solution quality. We validate the performance of CABC using Iris, Wine, Glass, Vowel, and Cloud UCI machine learning repository datasets comparing to previous studies by experiment and analysis. Our proposed KABCK (K-means+ABC+K-means) is better than ABCK (ABC+K-means), KABC (K-means+ABC), ABC, and K-means in our simulations.