• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.16 no.6 s.111
• /
• pp.665-673
• /
• 2006

This paper proposes a RSM-based hybrid evolutionary Algorithm (RHEA) which combines the merits of the popular programs such as genetic algorithm (GA), tabu search method and response surface methodology (RSM). This algorithm, for improving the convergent speed that is thought to be the demerit of genetic algorithm, uses response surface methodology and simplex method. The mutation of GA offers random variety to finding the optimum solution. In this study, however, systematic variety can be secured through the use of tabu list. Efficiency of this method has been proven by applying traditional left functions and comparing the results to GA. It was also proved that the newly suggested algorithm is very effective to find the global optimum solution to minimize the weight for avoiding the resonance of fresh water tank that is placed in the after body area of ship. According to the study, GA's convergent speed in initial stages is improved by using RSM method. An optimized solution is calculated without the evaluation of additional actual objective function. In a summary, it is concluded that RHEA is a very powerful global optimization algorithm from the view point of convergent speed and global search ability.

• The Journal of the Korea Contents Association
• /
• v.7 no.1
• /
• pp.58-64
• /
• 2007

In pattern recognition field, there are many optimization problems having exponential search spaces. To solve of sequential search algorithms seeking sub-optimal solutions have been used. The algorithms have limitations of stopping at local optimums. Recently lots of researches attempt to solve the problems using genetic algorithms. This paper explains the huge search spaces of typical problems such as feature selection, classifier ensemble selection, neural network pruning, and clustering, and it reviews the genetic algorithms for solving them. Additionally we present several subjects worthy of noting as future researches.

• Journal of KIISE:Computer Systems and Theory
• /
• v.32 no.8
• /
• pp.399-410
• /
• 2005

This paper Proposes a novel adaptive genetic algorithm (GA) extrapolated by an ant colony optimization. We first prove that the algorithm converges to the unique global optimal solution with probability arbitrarily close to one and then, by experimental studies, show that the algorithm converges faster to the optimal solution than GA with elitism and the population average fitness value also converges to the optimal fitness value. We further discuss controlling the tradeoff of exploration and exploitation by a parameter associated with the proposed algorithm.

• Korean Journal of Optics and Photonics
• /
• v.18 no.3
• /
• pp.179-184
• /
• 2007

In order to extract more accurate skin parameters, this study was focused on the improvement of the efficiency of a previous inverse fitting algorithm based on genetic algorithms. The algorithm provides the best fitting result of the diffusion approximation model to a VRS (visual reflectance spectroscopy) curve of skin. Simplex and wavelength selection methods were applied to the previous algorithm. Nine skin parameters were inversely extracted from the modeling studies. The revised inverse fitting algorithm was determined to produce an 83% reduction of computation time and a 0.64% reduction of sum of square error, compared to the previous algorithm. In conclusion, we confirmed that the new algorithm provides faster and more accurate solutions for the diffusion approximation model.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.5
• /
• pp.294-302
• /
• 2020

In a genetic algorithm, computer simulations are performed based on the natural evolution process of life, such as selection, crossover, and mutation. The genetic algorithm searches the approximate optimal solution by the parallel arrangement of Schema, which has a short definition length, low order, and high adaptability. This study examined the possibility of improving the efficiency of the optimal solution by considering the characteristics of the building block hypothesis, which are one of the key operating principles of a genetic algorithm. This study evaluated the efficiency of the optimization results according to the gene sequence for the implementation in solving problems. The optimal design problem of the water pipe was selected, and the genetic arrangement order reflected the engineering specificity by dividing into the existing, the network topology-based, and the flowrate-based arrangement. The optimization results with a flowrate-based arrangement were, on average, approximately 2-3% better than the other batches. This means that to increase the efficiency of the actual engineering optimization problem, a methodology that utilizes clear prior knowledge (such as hydraulic properties) to prevent such excellent solution characteristics from disappearing is essential. The proposed method will be considered as a tool to improve the efficiency of large-scale water supply network optimization in the future.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2002.11a
• /
• pp.502-509
• /
• 2002

Maximal Covering 문제(MCP)란 행렬 상에서 n개의 열(column) 중 p개를 선택하여 m개의 행(row)중 최대한 많은 행을 cover하는 문제로 정의된다. 본 논문에서는 MCP를 유전 알고리즘(Genetic Algorithm)으로 해결하기 위해 문제에 적합하게 설계된 교차 연산자(crossover operator)와 비발현 유전인잔(unexpressed gene)를 가진 새로운 염색체 구조를 제시한다. 해결하고자 하는 대상 MCP의 규모가 매우 큰 경우 전통적인 임의교차(random crossover) 방법으로는 좋은 결과를 얻기가 힘들다. 따라서 본 연구에서는 그리디 교차(greedy crossover) 방법을 제시하여 문제를 해결한다. 그러나 이러한 그리디 교차를 사용하더라도 조기 수렴 등의 문제로 인해 타부 탐색 등의 이웃해 탐색 방법에 비해 그리 좋은 결과를 얻기가 힘들다. 본 논문은 이러한 조기 수렴 문제를 해결하고 다른 이웃에 탐색 방법보다 더 좋은 결과를 얻기 위해 비발현 유전인자(unexpressed gene)를 가진 염색체를 도입하여 해결함을 특징으로 한다. 비발현 유전인자는 교차 과정에서 자식 염색체의 유전인자로 전달되지 않은 정보 중 나중에라도 유용할 가능성이 보이는 정보를 보존하는 역할을 하여 조기 수렴 문제를 해결하는데 도움을 주어 보다 나은 결과를 얻을 수 있게 해준다. 대규모 MCP를 해결하는 실험에서 새로운 비발현 유전인자를 적용한 유전 알고리즘이 기존의 유전 알고리즘뿐만 아니라 다른 탐색 기법에 비해 더욱 좋은 성능을 보여줌을 확인하였다.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.26 no.1
• /
• pp.1-8
• /
• 2016

The Korea Meteorological Administration has operated the Automatic Weather Stations, of the average 13 km horizontal resolution, to observe rainfall. However, an additional RADAR network also has been operated in all-weather conditions, because AWS network could not observed rainfall over the sea. In general, the rain rate is obtained by estimating the relationship between the radar reflectivity (Z) and the rainfall (R). But this empirical relationship needs to be optimized on the rainfall over the Korean peninsula. This study was carried out to optimize the Z-R relationship in the summer of 2014 using a parallel Micro Genetic Algorithm. The optimized Z-R relationship, $Z=120R^{1.56}$, using a micro genetic algorithm was different from the various Z-R relationships that have been previously used. However, the landscape of the fitness function found in this study looked like a flat plateau. So there was a limit to the fine estimation including the complex development and decay processes of precipitation between the ground and an altitude of 1.5km.

• Journal of the Korea Convergence Society
• /
• v.12 no.1
• /
• pp.49-55
• /
• 2021

Recently, with the development of database, it is possible to store a lot of data generated in finance, security, and networks. These data are being analyzed through classifiers based on machine learning. The main problem at this time is data imbalance. When we train imbalanced data, it may happen that classification accuracy is degraded due to over-fitting with majority class data. To overcome the problem of data imbalance, oversampling strategy that increases the quantity of data of minority class data is widely used. It requires to tuning process about suitable method and parameters for data distribution. To improve the process, In this study, we propose a strategy to explore and optimize oversampling combinations and ratio based on various methods such as synthetic minority oversampling technique and generative adversarial networks through genetic algorithms. After sampling credit card fraud detection which is a representative case of data imbalance, with the proposed strategy and single oversampling strategies, we compare the performance of trained classifiers with each data. As a result, a strategy that is optimized by exploring for ratio of each method with genetic algorithms was superior to previous strategies.

• Journal of the Korea Convergence Society
• /
• v.11 no.4
• /
• pp.11-16
• /
• 2020

As a plan for oil spill accidents, research to collect and analyze optimal equipment assignments is essential. However, studies that have diversified and analyzed the optimal equipment assignments for responding to oil spill accidents have not been preceded. In response to the need for analyzing optimal equipment assignments study, we devised a genetic algorithm for optimal equipment assignments. The designed genetic algorithm yielded 10,000 optimal equipment assignments. We clustered using the k-means algorithm. As a result, the two clusters of Yeosu, Daesan, and Ulsan, which are expected to be the largest spills, were clearly identified. We also projected 16-dimensional data in two dimensions via Sammon's mapping. The projected data were analyzed for distribution. We confirmed that results of the simulation were better than those of optimal equipment assignments included in the cluster.In the future, it will be possible to implement an approximate model with excellent performance based on this study.

• Journal of Korea Society of Industrial Information Systems
• /
• v.20 no.6
• /
• pp.57-65
• /
• 2015

Manufacturing optimization problem is to find the optimal solution under satisfying various and complicated constraints with the design variables of nonlinear types. To achieve the objective, this paper proposes a hybrid approach. The proposed hybrid approach is consist of genetic algorithm(GA), cuckoo search(CS) and hill climbing method(HCM). First, the GA is used for global search. Secondly, the CS is adapted to overcome the weakness of GA search. Lastly, the HCM is applied to search precisely the convergence space after the GA and CS search. In experimental comparison, various types of manufacturing optimization problems are used for comparing the efficiency between the proposed hybrid approach and other conventional competing approaches using various measures of performance. The experimental result shows that the proposed hybrid approach outperforms the other conventional competing approaches.