• Proceedings of the KIEE Conference
• /
• 2008.10c
• /
• pp.86-89
• /
• 2008

There are some modified methods such as K-means Clustering Particle Swarm Optimization and Niching Particle Swarm Optimization based on PSO which aim to locate all optima in multimodal functions. K-means Clustering Particle Optimization could locate all optima of functions with finite number of optima. Niching Particle Swarm Optimization is able to locate all of optima but high computing time. Because of those disadvantages, we proposed a new method that could locate all of optima with reasonal time. We applied our method and others as well to analytic functions. By comparing the outcomes, it is shown that our method is significantly more effective than the two others.

• Applied Biological Chemistry
• /
• v.20 no.2
• /
• pp.175-181
• /
• 1977

Lysosomal enzyme latency was demonstrated for hydrolases from porcine leukocyte by suspending sediment sfrom differential centrifugation in 0.125 to 0.250 M sucrose. Specific activities pH optima and activation energies were determined for hydrolases distributed in various sedimentation fractions and for enzymes solubilized by n-butyl alcohol extraction. Specific activities of the hydrolases revealed the heterogeneity of the Iysosomal fractions relative to enzyme content. pH optima identified the enzyme as acid hydrolases with optima for cathepsin D and aryl sulfatase also at pH 6.8. Activation energies of some hydrolases were low revealing that these enzymes could function efficiently during low temperature aging of meat.

• Journal of Korean Society of Transportation
• /
• v.16 no.1
• /
• pp.151-164
• /
• 1998

본 논문은 통행배정과 교통신호제어기의 결합문제를 풀기 위한 새로운 해법의 제시를 목적으로 한다. 통행배정과 신호제어 결합모형은 네트웍 디자인 문제(Network Design Problem)로 비선형 비분리 목적함수(Nonlinear and Nonseparable Objective Function)와 비선형제약 및 비컴백스 집합(Nonlinear and Non-Convex Set)형태로 인해 다수의 국지해(Multiple Local Optima)를 갖는 특징이 있다. 따라서 이렇게 복잡하고 난해한 문제를 푸는 해법은 많은 국지해중에 가장 최소한 값(Global Optima)을 찾을수 있는 방법을 제공하여야한다. 전체최적해(Global Optima)를 찾 을 수 있는 기존의 방법들은 확률적최적화방법(Stochastic Optimization Methods)에 속한다. 본연구에서는 이러한 방법중 금속공학에서 발 견된 모의담금빌법(Simulated Annealing Method)에 근거한 해법을 제시한다. 이방법이 통행배정과 신호제어 결합문제에 적용되는지 검토하기 위해 이해법의 수렴성(Convergence)을 증명했으며 또한 실제 프로그램된 모형을 작은 고안된 네트워크에 적 용했다. 마지막으로는 개발된 해법의 실용성을 실험하기 위해 두 가지의 보다 큰 도로망에 적용 및 분석을 했다.

• Journal of Institute of Control, Robotics and Systems
• /
• v.6 no.12
• /
• pp.1061-1069
• /
• 2000

In this paper, a new genetic algorithm is proposed for solving multimodal function optimization problems that are not easily solved by conventional genetic algorithm(GA)s. This algorithm finds one of local optima first and another optima at the next iteration. By repeating this process, we can locate all the local solutions instead of one local solution as in conventional GAs. To avoid converging to the same optimum again, we devise a new genetic operator, called a Mendel operator which simulates the Mendels genetic law. The proposed algorithm remembers the optima obtained so far, compels individuals to move away from them, and finds a new optimum.

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.101.4-101
• /
• 2001

Evolutionary algorithm has been receiving a remarkable attention due to the model-free and population-based parallel search attributes and much successful results are coming out. However, there are some problems in most of the evolutionary algorithms. The critical one is that it takes much time or large generations to search the global optimum in case of the objective function with multimodality. Another problem is that it usually cannot search all the local optima because it pays great attention to the search of the global optimum. In addition, if the objective function has several global optima, it may be very difficult to search all the global optima due to the global characteristics of the selection methods. To cope with these problems, at first we propose a preprocessing process, grid-filtering algorithm(GFA), and propose a new distributed evolutionary ...

• Proceedings of the Korea Water Resources Association Conference
• /
• 2019.05a
• /
• pp.429-429
• /
• 2019

최근 들어 이상기후 등 다양한 환경적 요인으로 인해 국지적이고 집중적인 호우가 빈발하고 있으며 도로상의 교통체증과 도로재해가 사회적으로 큰 문제가 되고 있다. 이러한 문제를 해결하기 위해서는 실시간, 단기간 이동성 강우정보 기술과 도로 기상정보를 활용할 수 있는 방법에 대한 연구가 필요하다. 본 연구는 차량의 AW(AutoWiping) 기능을 위해 장착된 강우센서를 이용하여 강우정보를 생산하는 기술을 개발하고자 하였다. 강우센서는 총 4개의 채널로 이루어져있고, 초당 250개의 광신호 데이터를 수집하며, 1시간이면 약 360만 개의 데이터가 생산되게 된다. 5단계의 인공강우를 재현하여 실내 인공강우실험을 실시하고 이를 통해 강우센서 데이터와 강우량과의 상관성을 W-S-R관계식으로 정의하였다. 실내실험데이터와 비교하여 외부환경 및 데이터 생성조건이 다른 실외 데이터의 누적값을 계산하기 위해 Threshold Map 방식을 개발하였다. 강우센서에서 생산되는 대량의 데이터를 이용하여 실시간으로 정확한 강우정보를 생산하기 위해 빅 데이터 처리기법을 사용하여 계산된 실내 데이터의 Threshold를 강우강도 및 채널에 따라 평균값을 계산하고 $4{\times}5$ Threshold Map(4 = 채널, 5 = 강우정보 사상)을 생성하였고 강우센서 기반의 강우정보 생산에 적합한 빅데이터 처리기법을 선정하기 위하여 빅데이터 처리기법 중 Gradient Descent와 Optima Rainfall Intensity을 적용하여 분석하고 결과를 지상 관측강우와 비교검증을 하였다. 이 결과 Optima Rainfall Intensity의 적합도를 검증하였고 실시간으로 관측한 8개 강우사상을 대상으로 강우센서 강우를 생산하였다.

• Proceedings of the Korean Information Science Society Conference
• /
• 1999.10b
• /
• pp.9-11
• /
• 1999

조합 최적화 문제인 Traveling Salesman problems(TSP)을 Genetic Algorithm(GA)과 Local Search Heuristic인 Lin-Kernighan(LK) Heuristic[2]을 이용하여 접근하는 것은 최적해를 구하기 위해 널리 알려진 방법이다. 이 논문에서는 LK를 이용하여 주어진 TSP 문제에서 Local Optima를 찾고, GA를 이용하여 Local Optimal를 바탕으로 Global Optima를 찾는데 이용하게 된다. 여기서 이런 GA와 LK를 이용하여 TSP 문제를 풀 경우 해가 점점 수렴해가면서 중복된 유전자가 많이 생성된다. 이런 중복된 유전자를 제거함으로써 탐색의 범위를 보다 넓고 다양하게 검색하고, 더욱 효율적으로 최적화를 찾아내는 방법에 대해서 논하겠다. 이런 방법을 이용하여 rat195, gil262, lin318의 TSP문제에서 효율적으로 수행된다.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.34S no.5
• /
• pp.52-65
• /
• 1997

For the degradation of severe noise and ill-conditioned blur the optimization function has the solution spaces which have many local optima around global solution. General restoration methods such as inverse filtering or gradient methods are mainly dependent on the properties of degradation model and tend to be isolated into a local optima because their convergences are determined in the convex space. Hence we introduce genetic algorithm as a searching method which will search solutions beyond the convex spaces including local solutins. In this paper we introudce improved evaluation square error) and fitness value for gray scaled images. Finally we also proposed the local fine tunign of window size and visit number for delicate searching mechanism in the vicinity of th global solution. Through the experiental results we verified the effectiveness of the proposed genetic operators and evaluation function on noise reduction over the conventional ones, as well as the improved performance of local fine tuning.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.13 no.3
• /
• pp.587-592
• /
• 2018

An adaptive beam forming system using a phased array antenna improves communication quality by beam forming adaptively to a communication environment having an interference signal. For adaptive beam forming, a good combination of the phases of the excited signals to each radiating element of the phased array antenna should be calculated. In this paper, improved particle swarm optimization algorithm that adds a re-spreading procedure according to particle density was proposed to increase the probability of good phase shift combination output.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.5 no.1
• /
• pp.21-28
• /
• 2005

This paper proposes a new method for accelerating the search speed of genetic algorithms by taking derivative evaluation and conditional random selection into account in their evolution process. Derivative evaluation makes genetic algorithms focus on the individuals whose fitness is rapidly increased. This accelerates the search speed of genetic algorithms by enhancing exploitation like steepest descent methods but also increases the possibility of a premature convergence that means most individuals after a few generations approach to local optima. On the other hand, derivative evaluation under a premature convergence helps genetic algorithms escape the local optima by enhancing exploration. If GAs fall into a premature convergence, random selection is used in order to help escaping local optimum, but its effects are not large. We experimented our method with one combinatorial problem and five complex function optimization problems. Experimental results showed that our method was superior to the simple genetic algorithm especially when the search space is large.