• Proceedings of the Korean Information Science Society Conference
• /
• 2005.07b
• /
• pp.697-699
• /
• 2005

연속 변수 함수 최적화를 위한 진화 연산에서는 전통적으로 확률 분포를 도입하여 새로운 세대를 생성하는 기법을 사용하고 있다. 최근 들어 이러한 확률 분포를 개체군으로부터 추정하여 보다 효율적으로 최적화를 해결하려는 연구가 진행되고 있다. 본 논문에서는 variational 베이지안 혼합 인자 분석 기법(Bayesian mixtures of factor analyzers)을 사용한 개체군의 분포 추정을 통해 연속 변수 함수의 최적화 문제를 해결하는 방법을 제안한다. 이 기법은 혼합 분포의 개수 추정을 자동화하여 개체군의 다양성을 유지할 수 있기 때문에 지역 최적점으로 일찍 수렴하는 현상을 방지할 수 있으며, 세부 개체군 내의 분포 추정을 통해 탐색을 효율적으로 수행할 수 있다. 잘 알려진 평가 함수들에 대하여 다른 분포 추정 진화 연산과 비교하여 제안하는 방법의 우수성을 검증하였다.

• Proceedings of the KIEE Conference
• /
• 2001.07d
• /
• pp.2396-2398
• /
• 2001

Active contour로 알려져 있는 snake는 반복적인 계산으로 이미지상에서 찾고자 하는 물체의 외곽선에 수렴하는 contour로 이미지 상의 물체의 외곽선으로부터 발생하는 외부 에너지(external energy)와 contour 자체로부터 기인하는 내부 에너지(internal energy)를 최소화하는 방향으로 움직인다. 그러나 물체의 윤곽선으로부터 발생하는 외부 에너지는 찾고자 하는 물체뿐만 아니라 주위의 다른 물체로부터도 발생하므로 만일 추적하고자 하는 물체의 주변에 다른 물체들이 존재한다면 snake은 올바르게 동작하지 않게 된다. 본 논문에서는 이러한 단점을 극복하기 위하여 물체의 색상정보를 이용하는 방식을 제안하였다. 물체의 색상 정보는 물체의 고유한 특성 중의 하나로 본 논문에서는 색상정보를 이용하여 원래의 이미지를 찾고자 하는 물체의 색상과 얼마나 유사한가를 나타내는 확률 이미지로 변환하였다. 이렇게 변환된 확률 이미지 상에서 snake 알고리즘을 적용함으로써 배경의 다른 물체로부터 발생하는 외부 에너지를 효과적으로 제거할 수 있다. 또한 본 논문에서는 물체가 이동함에 따라 변화하는 색상 정보를 지속적으로 갱신함으로써 물체의 추적이 효과적으로 이루어지도록 하였다.

• Korean Journal of Cognitive Science
• /
• v.23 no.2
• /
• pp.205-224
• /
• 2012

How would people who buy an insurance policy respond to a low probability risk with a high future cost? Presented with a scenario describing a low probability accident of a chemical plant, participants in four experiments were asked to rate their perception of the risk and also their intention to buy an insurance of a given premium, an insurance, or a ratio insurance. Participants differently responded only to ratio insurance when rating their perception of risk, not to either premium or insurance. The pattern of results in four experiments converged to the conclusion that ratio insurance, an ecologically valid cue, makes people sensitive to the level of risk expressed in low probabilities of an accident. Our results were consistent with the prediction generated by the ecological cue hypothesis which empathizes the importance of frequency over probability in risk perception (Gigerenzer, 2000).

• Proceedings of the Korea Information Processing Society Conference
• /
• 2012.11a
• /
• pp.1728-1731
• /
• 2012

본 논문에서는 부모 개체의 해밍 거리에 기반하여 선택적 변이연산을 적용한 유전알고리즘을 제안한다. 유전자 형이 매우 유사한 개체들 간의 유전연산은 알고리즘의 탐색성능을 저하시키고 조기 수렴의 가능성을 증가시킨다. 본 논문에서는 이러한 현상을 극복하기 위하여, 교차연산 시 선택된 두 부모 개체간의 해밍 거리에 따라 그 값이 낮으면 교차연산 후 생성된 두 자식 개체 중 한쪽에게 높은 변이확률을 적용하고 다른 한쪽 자식은 부모와 비슷한 유전자 형으로 탐색을 계속하게 하여 조기 수렴을 방지하면서 해집단의 다양성 유지 기능을 향상 시켰다. 제안한 유전 알고리즘을 다차원 배낭 문제에 적용한 결과, 같은 조건에서 단순 유전 알고리즘(SGA) 보다 향상된 탐색 성능을 보여주었다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.16 no.12
• /
• pp.1274-1285
• /
• 1991

This paper presents a statistical convergence analysis of the normalized least mean square(NLMS)algorithm that employs a single-pole lowpass filter, In this algorithm the lowpass filter is used to adjust its output towards the estimated value of the input signal power recursively. The estimated input signal power so obtained at each time is then used to normalize the convergence parameter. Under the assumption that the primary and reference inputs to the adaptive filter are zero mean wide sense stationary, and Gaussian random processes, and further making use of the independence assumption. we derive expressions that characterize the mean and maen squared behavior of the filter coefficients as well as the mean squared estimation error. Conditions for the mean and mean squared convergence are explored. Comparisons are also made between the performance of the NLMS algorithm and that of the popular least mean square(LMS) algorithm Finally, experimental results that show very good agreement between the analytical and emprincal results are presented.

• Journal of Internet Computing and Services
• /
• v.15 no.4
• /
• pp.119-124
• /
• 2014

Blind adaptive systems based on the Euclidean distance (ED) between the distribution function of the output samples and that of a set of random symbols generated at the receiver matching with the distribution function of the transmitted symbol points estimate the ED at each iteration time to examine its convergence state or its minimum ED value. The problem is that this ED estimation obtained by block?data processing requires a heavy calculation burden. In this paper, a recursive ED estimation method is proposed that reduces the computational complexity by way of utilizing the relationship between the current and previous states of the datablock. The relationship provides a ground that the currently estimated ED value can be used for the estimation of the next ED without the need for processing the whole new data block. From the simulation results the proposed recursive ED estimation shows the same estimation values as that of the conventional method, and in the aspect of computational burden, the proposed method requires only O(N) at each iteration time while the conventional block?processing method does $O(N^2)$.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.39B no.11
• /
• pp.790-802
• /
• 2014

In cognitive radio technology, secondary users can determine the absence of PU by periodic sensing operation and cooperative sensing between SUs yields a significant sensing performance improvement. However, there exists a trade off between the gains in terms of probability of detection of the primary users and the costs of false alarm probability. Therefore, the cooperation group must maintain the suitable size. And secondary users should sense not only the currently using channels and but also other candidates channel to switch in accordance with sudden appearance of the primary user. In this paper, we propose an effective group cooperative sensing algorithm in distributed network situations that is considering both of inband and outband sensing using evolutionary game theory. We derived that the strategy group of secondary users converges to an ESS(Evolutionary sable state). Using a learning algorithm, each secondary user can converge to the ESS without the exchange of information to each other.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.20 no.4
• /
• pp.833-839
• /
• 2016

In this paper, we propose a selective feature extraction algorithm between Markov transition probability and co-occurrence probability for an effective image splicing detection. The Features used in our method are composed of the difference values between DCT coefficients in the adjacent blocks and the value of Kullback-Leibler divergence(KLD) is calculated to evaluate the differences between the distribution of original image features and spliced image features. KLD value is an efficient measure for selecting Markov feature or Co-occurrence feature because KLD shows non-similarity of the two distributions. After training the extracted feature vectors using the SVM classifier, we determine whether the presence of the image splicing forgery. To verify our algorithm we used grid search and 6-folds cross-validation. Based on the experimental results it shows that the proposed method has good detection performance with a limited number of features compared to conventional methods.

• Journal of the Korea Society for Simulation
• /
• v.28 no.4
• /
• pp.21-32
• /
• 2019

Inspired by the social behavior models of a bird flock or fish school, particle swarm optimization (PSO) is a popular metaheuristic optimization algorithm and has been widely used from solving a complex optimization problem to learning a artificial neural network. However, PSO is difficult to apply to many real-life optimization problems involving stochastic noise, since it is originated in a deterministic environment. To resolve this problem, this paper incorporates a resampling method called the uncertainty evaluation (UE) method into PSO. The UE method allows the particles to converge on the accurate optimal solution quickly in a noisy environment by selecting the particles' global best position correctly, one of the significant factors in the performance of PSO. The results of comparative experiments on several benchmark problems demonstrated the improved performance of the propose algorithm compared to the existing studies. In addition, the results of the case study emphasize the necessity of this work. The proposed algorithm is expected to be effectively applied to optimize complex systems through digital twins in the fourth industrial revolution.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.14 no.1
• /
• pp.97-107
• /
• 1989

In this study three types of aggregation methods such as the Estimate-Talk-Consensus (ETC) process, the Estimate-Talk-Estimate (ETE) process, and as a new approach the Estimate-Talk-Leader's Estimate (ETLE) process are compared to find which one of the three group processes considered is more effective than others. We, also, investigate the effect of group size on the performance of the group processes. Some experiments were conducted. It was shown that both the ETC and the ETLE processes performed better than the ETE process in approaching correct estimates in this judgmental task. As the size group increased, only the ETC and the ETC processes were shown to result in positive effect.