• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 2006.05a
• /
• pp.110-116
• /
• 2006

지금까지 대부분의 리던던시 할당문제(RAP: redundancy allocation problems) 관련 연구들에서는 최상위 수준에서의 시스템 리던던시보다는 최하위 수준인 부품의 리던던시를 고려하였다. 이는 최하위 수준에서의 리던던시가 최상위 수준의 리던던시보다 효과적이라고 알려진 일반적 원리 때문이었다. 최근 한 연구에서는 동일하지 않은 예비부품을 사용하여 리던던시를 실시하는 경우 직렬구조의 시스템에서도 일반적 원리와 다른 결과가 나타날 수 있음을 보이고, 시스템을 구성하는 모든 수준에서 리던던시가 가능한 다수준 리던던시 할당문제(MRAP: multi-level RAP)를 제시하였다. 그러나 MRAP는 모든 수준에서의 리던던시를 고려하지만 단지 한 수준을 선택하여 리던던시를 할 수 있다는 가정사항을 포함하고 있다. 본 연구에서는 MRAP의 이러한 가정사항을 완화하여 시스템을 구성하는 모든 수준에서 리던던시를 위한 수준을 복수로 선택 가능한 혼합 다수준 리던던시 할당문제(MMRAP: multiple MRAP)를 제시하고 모형화하며, 문제의 해법을 위한 유전자 알고리듬(GA: genetic algorithm)을 제시한다. 제시한 GA를 활용한 몇 가지 수치실험을 통해 모형이 기존의 RAP 경우보다 효과적임을 입증한다.

• Journal of the Korean Society for Precision Engineering
• /
• v.20 no.4
• /
• pp.189-196
• /
• 2003

Among the optimization method, GA (genetic algorithm) is a very powerful searching method enough to compete with design sensitivity analysis method. GA is very easy to apply, since it dose not require any design sensitivity information. However, GA has been computationally not efficient due to huge repetitive computation. In this study, parallel computation is adopted to improve computational efficiency. Paralleled GA is introduced on a clustered LINUX based personal computer system.

• Journal of Industrial Technology
• /
• v.20 no.B
• /
• pp.27-34
• /
• 2000

The definition of flatness is given by ISO, ANSI, KS, etc. but those standards don't mention about the specific methods for the flatness. So various solution models that are based on the Minimum Zone Method have been proposed as an optimization problem for the minimax curve fitting. But it has been rare to compare some optimization algorithms to make a guideline for choosing better algorithms in this field. Hence this paper examined and compared Genetic Algorithm and Simplex Method to the evaluation of flatness. As a result, Genetic Algorithm gave the better or equal flatness than Simplex Method but it has the inefficiency caused from the large number of iteration. Therefore, in the future, another researches about alternative algorithms including Hybrid Genetic Algorithm should be achieved to improve the efficiency of Genetic Algorithm for the evaluation of flatness.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.31 no.7
• /
• pp.75-84
• /
• 2003

To reduce the effects of the uncertainties due to the modeling error and aerodynamic coefficients, a nonlinear adaptive control system based on neural networks is proposed . Neural networks parameters are adjusted by using an adaptive law. The sliding mode control scheme is used to compensate for the effect of the approximation error of neural networks. Control parameters and neural networks structures are optimized to obtain better performance by using the genetic algorithm. By introducing the concept of multi-groups of populations, the genetic algorithm is modified so that individuals and groups can be simultaneously evolved . To verify the performance of the pro posed algorithm, the optimized neural networks control system is applied to an aircraft longitudinal dynamics.

• Journal of the Korea Society of Computer and Information
• /
• v.20 no.2
• /
• pp.137-147
• /
• 2015

This study proposes an algorithm for predicting breast cancer prognosis based on genetic network. We identify prognosis-specific network using gene expression data and PPI(protein-protein interaction) data. To acquire the network, we calculate Pearson's correlation coefficient(PCC) between genes in all PPI pairs using gene expression data. We develop a prediction model for breast cancer patients with estrogen-receptor-negative using the network as a classifier. We compare classification performance of our algorithm with existing algorithms on independent data and shows our algorithm is improved. In addition, we make an functionality analysis on the genes in the prognosis-specific network using GO(Gene Ontology) enrichment validation.

• IE interfaces
• /
• v.14 no.4
• /
• pp.374-384
• /
• 2001

The objective of this paper is to design the dynamic route guidance system(DRGS) and develop a genetic algorithm(GA) for finding the multiple shortest paths in real traffic network. The proposed GA finds a collection of paths between source and destination considering turn-restrictions, U-turn, and P-turn that are genetically evolved until an acceptable solution is reached. This paper also shows the procedure to find the multiple shortest paths in traffic network of Seoul.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.27 no.9
• /
• pp.1546-1554
• /
• 2003

Efficient layout in a fixed work volume reduces build time when multiple parts are built at once in stereolithography systems. An efficient algorithm is developed for 3D layout planning. And it reduces build time and increases efficiency of SLA system. Genetic algorithm is implemented to locate as many parts as possible in the fixed work volume. A 3D collision detection algorithm, k-DOPs Tree, is implemented for the fast evaluation of a layout plan.

• Proceedings of the IEEK Conference
• /
• 2000.09a
• /
• pp.345-348
• /
• 2000

본 논문에서는 웨이브릿 변환과 유전자 알고리즘을 이용한 하이브리드 영상복원 방법을 제안한다. 제안한 방법은 영상복원을 위한 전처리로써 분해 및 합성 필터의 이상적인 직교 특성을 가지는 웨이브릿 변환을 이용하여 잡음훼손영상으로부터 고주파성 잡음의 일부를 우선 제거하고 나머지 영상에 대해서는 국부적 최적해로의 고립을 벗어나 전역해 탐색이 가능한 유전자 알고리즘을 적용한다 제안한 하이브리드 방법의 성능평가를 위하여 이진 문자영상과 Lenna 영상을 입력영상으로 인가하여 기존의 단일 유전자 알고리듬을 이용한 방법과 비교실험을 수행하였다. 실험결과 제안한 하이브리드 영상 복원방법이 기존의 방법에 비하여 약 2dB 향상됨으로써 잡음훼손영상의 복원성능이 우수함을 확인하였다.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2000.11a
• /
• pp.99-101
• /
• 2000

DNA 컴퓨팅 기법은 실제 생체 분자(bio-molecule)를 계산의 도구로 사용하는 새로운 계산 방법으로, 진화 연산과 결합하여 인공지능의 새로운 분야로 부각되고 있다. 그러나, 실제 생체 분자를 계산의 도구로 사용하기 때문에 기존의 컴퓨터에 적용하기 어렵고, 단순히 합성과 분리라는 간단한 방법으로 해를 구하기 때문에 보다 효과적인 알고리즘을 개발하여야 할 필요성이 있다. 따라서, 본 논문에서는 DNA 컴퓨팅 기법을 컴퓨터에 적용하기 위한 방법으로 DNA 컴퓨팅에서의 코드 합성 기법과 유전자 알고리즘을 이용하여 NP-complete 문제중의 하나인 Sub-Set Sum 문제를 해결하여 그 결과를 분석한다. Sub-Set Sum 문제에서 단순 유전자 알고리듬보다 DNA 코드 유전자 알고리즘이 높은 성능을 보인다.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.25 no.4
• /
• pp.247-254
• /
• 2015

Ride comfort is one of the major factors in evaluating the performance of the vehicle. Tire is closely related to the ride comfort of the vehicle as the only parts in contact with the road surface directly. Vertical stiffness which is one of the parameters to evaluate the tire performance is great influence on the ride comfort. In general, the lower the vertical stiffness, the ride comfort is improved. Research for improving the ride comfort has been mainly carried out by optimizing the shape of the pneumatic tire. However, demand for safety of the vehicle has been increased recently such as a run-flat tire which is effective in safety improvement. But a run-flat tire have trouble in practical use because of poor ride comfort than general tire. Therefore, In this paper, the research was carried out for improving the ride comfort through the optimization of the SIR shape inside a run-flat tire. Meta-model was generated by using the design of experiment and it was able to reduce the time for the finite element analysis of optimization. In addition, Shape optimization for improving the ride comfort was performed by using the genetic algorithm which is one of the global optimization techniques.