• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2006.05a
• /
• pp.168-171
• /
• 2006

본 논문에서는 Particle Swarm Optimization 기법을 이용한 뉴로-퍼지 시스템의 파라미터 동정을 실시한다. PSO의 학습 및 군집 특성을 이용하여 시스템을 학습한다. 유전 알고리즘과 같은 무작위 탐색법을 이용하며 하나의 해 군집에 대해 다수 객체들이 탐색하는 기법을 통하여 최적해 부분의 탐색성능을 높여 전체 모델의 학습성능을 개선하고자 한다. 제안된 기법의 유용성을 시뮬레이션을 통하여 보이고자 한다.

• Proceedings of the Korean Statistical Society Conference
• /
• 2000.11a
• /
• pp.219-225
• /
• 2000

데이터 마이닝 분야에서 널리 사용되고 있는 신경망은 최근 많은 통계인들의 관심을 끌고 있다. 그러나 범용 근사성(universal approximator)이라는 성질에도 불구하고 초기치에 따라 적합 결과가 크게 좌우되는 단점이 있다. 본 논문에서는 붓스트랩 표본을 통해 초기치를 발견하는 bumping 기법이 신경망 분야에서 사용되고 있는 무작위 탐색법 보다 더 정확하고 안정적인 초기치를 제공하여 주는가를 살펴 보았다.

• Journal of the Korea Society of Computer and Information
• /
• v.10 no.4 s.36
• /
• pp.213-219
• /
• 2005

In order to move NPC's to target location at game maps, various algorithm including A* has been used. The most frequently used algorithm among them is A* with fast finding speed. But A* has the following problems. The first problem is that at randomly changing map, it is necessary to calculate all things again whenever there are any changes. And when calculation is wrong, it is not possible to search for target. The second problem is that it is difficult to move avoiding dangerous locations damaging NPC such as an obstruction. Although it is possible to avoid moving to locations with high weight by giving weight to dangerous factors. it is difficult to control in case NPC moves nearby dangerous factors. In order to solve such problems, in this thesis, the researcher applied Dynamic Programming to path-finding algorithm. As the result of its application, the researcher could confirm that the programming was suitable for changes at the map with random change and NPC's avoided the factors being dangerous to them far away. In addition. when compared to A*, there were good results.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.36S no.3
• /
• pp.97-105
• /
• 1999

본 논문에서는 기존의 깊이 복원 방법을 개선하기 위해서 유전 알고리즘을 이용한 새로운 스테레오 정합법을 제시하였고 다양한 영상에 적용하기 위해 영상의 영역 정보를 고려하였다. 유전 알고리즘은 자연선택과 개체군 유전학에 기반한 효율적인 탐색 기법인데, 이들의 염색체 교차와 돌연변이 같은 연산자를 정합 환경에 적합하도록 변형시켰다. 영상신호를 쉽게 다루기 위해서 2차원 염색체 구조를 사용하였으며, 스테레오 정합에 많이 사용되는 유사성과 연속성 제약 조건에 기반하여 적자를 선택하는 적응 함수를 정의하였다. 그리고 기존 유전 알고리즘의 수렴속도를 개선하기 위해서 무작위로 변이를 발생시키지 않고 휘도차를 이용하여 변이를 발생시키는 정보기반 변이 발생을 사용하였다. 실험을 통하여 본 방법은 이완처리를 포함한 정합법보다 계산 부하를 줄일 수 있었고 비교적 안정된 결과를 얻을 수 있었다.

• Journal of the Society of Naval Architects of Korea
• /
• v.42 no.3
• /
• pp.284-289
• /
• 2005

A structural design system is developed for the optimum design of double hull tankers based on the multi-objective function method. As a multi-objective function method, Pareto optimal based random search method is adopted to find the minimum structural weight and fabrication cost. The fabrication cost model is developed by considering the welding technique, welding poses and assembly stages to manage the fabrication man-hour and process. In this study, a new structural design is investigated due to the rapidly increased material cost. Several optimum structural designs on the basis of high material cost are carried out based on the Pareto optimal set obtained by the random search method. The design results are compared with existing ship, which is designed under low material cost.

• Proceedings of the Acoustical Society of Korea Conference
• /
• spring
• /
• pp.335-338
• /
• 2002

본 연구에서는 주파수 영역에서의 확산 스펙트럼 방식을 이용한 오디오 워터마킹 기법을 사용하고 있다. 워터마크 삽입은 오디오 신호를 MCLT(Modulated Complex Lapped Transform)로 분석한 후, 특정 주파수 영역의 진폭에 삽입되며 추출은 상관도를 이용하여 추출하게 된다. 워터마크 삽입은 44.1 kHz의 음악에 80 bits의 정보가 4초 단위로 반복적으로 삽입되며, 추출에서는 무작위로 추출된 8초 분량의 오디오 신호로부터 80 bits 비트 열과의 상관도를 계산하여 선정된 문턱 값을 초과하게 되면 워터마크가 존재하는 것으로 판단하게 된다 피치 스케일에 대응하기 위하여 120개 정도의 탐색을 수행하며, 시간 스케일에 대응하기 위하여 상관도의 지역 최대 점을 추출하고, 이러한 지역 최대 점들로부터 추출된 비트 열과 실제 비트 열과의 상관도를 계산하게 된다. 그러나 추출된 비트 열은 삽입 에러와 삭제 에러를 가질 수 있기 때문에 이러한 비트 열과의 최대 상관도를 구하기 위하여 본 연구에서는 동적계획법에 의한 최대 상관도 추출 알고리즘을 제시한다. 제안된 방법은 피치 및 시간 스케일링 변환 뿐만 아니라, 오디오 압축에도 견고함을 보인다.

• Journal of Korea Game Society
• /
• v.15 no.5
• /
• pp.109-118
• /
• 2015

The game of Go originated from ancient China is regarded as one of the most difficult challenges in the filed of AI. Over the past few years, the top computer Go programs based on MCTS have surprisingly beaten professional players with handicap. MCTS is an approach that simulates a random sequence of legal moves until the game is ended, and replaced the traditional knowledge-based approach. We applied the UCT algorithm which is a MCTS variant to the game of Tic-Tac-Toe for finding the best first move, and compared it with the result generated by a pure MCTS. Furthermore, we introduced and compared the performances of epsilon-Greedy algorithm and UCB algorithm for solving the Multi-Armed Bandit problem to understand the UCB.

• Composites Research
• /
• v.12 no.4
• /
• pp.42-54
• /
• 1999

FMLC(Fiber-Metal Laminate Composites) is a new structural material combining thin metal laminate with adhesive fiber prepreg, it nearly include all the advantage of metallic materials, for example: good plasticity, impact resistance, processibility, light weight and excellent fatigue properties. This research studied the optimum design of the FMLC subject to various loading conditions using genetic algorithm. The finite element method based on the shear deformation theory was used for the analysis of FMLC. Tasi-Hill failure criterion and Miser yield criterion were taken as fitness functions of the fiber prepreg and the metal laminate, respectively. The design variables were fiber orientation angles. In genetic algorithm, the tournament selection and the uniform crossover method were used. The elitist model was also used to be effective evolution strategy and the creeping random search method was adopted in order to approach a solution with high accuracy. Optimization results were given for various loading conditions and compared with CFRP(Carbon Fiber Reinforced Plastic). The results show that the FMLC is more excellent than the CFRP in point and uniform loading conditions and it is more stable to unexpected loading because the deviation of failure index is smaller than that of CFRP.

• The KIPS Transactions:PartB
• /
• v.11B no.2
• /
• pp.221-226
• /
• 2004

Ant Colony System(ACS) Algorithm is new meta-heuristic for hard combinational optimization problem. It is a population-based approach that uses exploitation of positive feedback as well as greedy search. Recently, various methods and solutions are proposed to solve optimal solution of graph coloring problem that assign to color for adjacency node($v_i, v_j$) that they has not same color. In this paper introducing ANTCOL Algorithm that is method to solve solution by Ant Colony System algorithm that is not method that it is known well as solution of existent graph coloring problem. After introducing ACS algorithm and Assignment Type Problem, show the wav how to apply ACS to solve ATP And compare graph coloring result and execution time when use existent generating functions(ANT_Random, ANT_LF, ANT_SL, ANT_DSATUR, ANT_RLF method) with ANT_XRLF method that use XRLF that apply Randomize to RLF to solve ANTCOL. Also compare graph coloring result and execution time when use method to add re-search to ANT_XRLF(ANT_XRLF_R) with existent generating functions.

• Journal of Korean Society of Environmental Engineers
• /
• v.31 no.9
• /
• pp.825-830
• /
• 2009

Pharmaceutical compounds enter the water environment through the diverse pathways. Because their concentration in the water environment was frequently detected in the level of ppt to ppb, the monitoring system should be optimized as much as possible for finding appropriate management policies and technical solutions. One Factor At a Time (OFAT) approach approximating the response with a single variable has been preferred for the optimization of LC-MS/MS operational conditions. However, it is common that variables in analytical instruments are interdependent. Therefore, the best condition could be found by using the statistical optimization method changing multiple variables at a time. In this research, response surface analysis (RSA) was applied to the LC-MS/MS analysis of emerging antibiotic compound, sulfamethoxazole, for the best sensitivity. In the screening test, fragmentation energy and collision voltage were selected as independent variables. They were changed simultaneously for the statistical optimization and a polynomial equation was fit to the data set. The correlation coefficient, $R^2$ valuerepresented 0.9947 and the error between the predicted and observed value showed only 3.41% at the random condition, fragmentation energy of 60 and collision voltage of 17 eV. Therefore, it was concluded that the model derived by RSA successfully predict the response. The optimal conditions identified by the model were fragmentation energy of 116.6 and collision voltage of 10.9 eV. This RSA can be extensively utilized for optimizing conditions of solid-phase extraction and liquid chromatography.