• The Journal of the Korea institute of electronic communication sciences
• /
• v.18 no.6
• /
• pp.1331-1336
• /
• 2023

In text-based fish disease classification using machine learning, there is a problem that the input parameters of the machine learning model are too many, but due to performance problems, the input parameters cannot be arbitrarily reduced. This paper proposes a method of optimizing input parameters specialized for Paralichthys olivaceus disease classification using SHAP analysis techniques to solve this problem,. The proposed method includes data preprocessing of disease information extracted from the halibut disease questionnaire by applying the SHAP analysis technique and evaluating a machine learning model using AutoML. Through this, the performance of the input parameters of AutoML is evaluated and the optimal input parameter combination is derived. In this study, the proposed method is expected to be able to maintain the existing performance while reducing the number of input parameters required, which will contribute to enhancing the efficiency and practicality of text-based Paralichthys olivaceus disease classification.

• Journal of Korean Society of Steel Construction
• /
• v.18 no.6
• /
• pp.677-686
• /
• 2006

In this paper, a more practical and realistic method is proposed to establish the lifetime optimum maintenance strategies of the deteriorating bridges considering the life-cycle performance as well as life-cycle cost. The genetic algorithm is applied to generate the set of maintenance scenarios that is the multi-objective combinatorial optimization problem related to lifetime performance and cost as separate objective functions, and the technique to select optimum tradeoff maintenance scenario is presented. Optimum maintenance scenarios could be generated not only at the individual member level but also at the system level of the bridge. Through the analytical results of applying the proposed methodology to the existing bridge, it is expected that the methodology will be effectively used to determine the optimum maintenance strategy for introducing a real preventive maintenance system and overcoming the limits of existing maintenance methods.

• Microbiology and Biotechnology Letters
• /
• v.51 no.1
• /
• pp.99-108
• /
• 2023

Several challenges arise in DNA extraction and gene amplification for airborne fungal metagenome analysis from a particulate matter (PM) samples. In this study, various conditions were tested to optimize the DNA extraction method from PM samples and polymerase chain reaction (PCR) conditions with primer set and annealing temperature. As a result of comparative evaluation of DNA extraction under various conditions, chemical cell lysis using buffer and proteinase K for 20 minutes and bead beating treatment were followed by using a commercial DNA extraction kit to efficiently extract DNA from the PM filter samples. To optimize the PCR conditions, PCR was performed using 10 primer sets for amplifying the ITS2 gene region. The concentration of the PCR amplicon was relatively high when the annealing temperature was 58℃ with the ITS3tagmix3/ITS4 primer set. Even under these conditions, when the concentration of the PCR product was low, nested PCR was performed using the primary PCR amplicon as the template DNA to amplify the ITS2 gene at a satisfactory concentration. Using the methods optimized in this study, DNA extraction and PCR were performed on 15 filter samples that collected PM2.5 in Seoul, and the ITS2 gene was successfully amplified in all samples. The optimized methods can be used for research on analyzing and interpreting the fungal metagenome of atmospheric PM samples.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.47 no.12
• /
• pp.856-864
• /
• 2019

The weapon-target assignment (WTA) problem is a matter of effectively allocating weapons to a number of threats. The WTA in a rapidly changing dynamic environment of engagement must take into account both of properties of the threat and the weapon and the effect of the previous decision. We propose a method of applying the Greedy Randomized Adaptive Search Procedure (GRASP) algorithm, a kind of meta-heuristic method, to derive optimal solution for a dynamic WTA problem. Firstly, we define a dynamic WTA problem and formulate a mathematical model for applying the algorithm. For the purpose of the assignment strategy, the objective function is defined and time-varying constraints are considered. The dynamic WTA problem is then solved by applying the GRASP algorithm. The optimal solution characteristics of the formalized dynamic WTA problem are analyzed through the simulation, and the algorithm performance is verified via the Monte-Carlo simulation.

• Journal of the Korea Society of Computer and Information
• /
• v.13 no.3
• /
• pp.147-152
• /
• 2008

Ant System(AS) is new meta heuristic for hard combinatorial optimization problem. It is a population based approach that uses exploitation of positive feedback as well as greedy search. It was first proposed for tackling the well known Traveling Salesman Problem. In this paper, AS is applied to the Multicast Routing Problem. Multicast Routing is modeled as the NP-complete Steiner tree problem. This is the shortest path from source node to all destination nodes. We proposed new AS to resolve this problem. The proposed method selects the neighborhood node to consider all costs of the edge and the next node in state transition rule. Also, The edges which are selected elite agents are updated to additional pheromone. Simulation results of our proposed method show fast convergence and give lower total cost than original AS and $AS_{elite}$.

• Journal of Korea Society of Industrial Information Systems
• /
• v.29 no.4
• /
• pp.67-76
• /
• 2024

In this study, we address the problem of target detection using multiple agents. Specifically, the detection problem involving mobile agents necessitates additional strategies for path planning. The objective is to maximize the total utility derived from the detection process over a specific period. This detection problem incorporates realistic utility values by considering a stochastic process based on the Poisson process, which accounts for the changing probability of target event occurrence over time. The objective function is nonlinear and is classified as an NP-hard problem. To identify an effective solution within an efficient computation time, this study demonstrates that the objective function possesses the characteristic of submodularity. Using this property, we propose a heuristic algorithm designed to obtain a reasonable strategy with relatively low computational time. The proposed algorithm shows solution performance and the ability to generate solutions within an appropriate computation time through theoretical and experimental results.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.30 no.11A
• /
• pp.979-986
• /
• 2005

In optical networks, traffic demands often demonstrate periodic nature for which time-overlapping property can be utilized in routing and wavelength assignment (RWA). A RWA problem for scheduled lightpath demands (SLDs) has been solved by combinatorial optimal solution (COS) and graph coloring, or heuristic sequential RWA (sRWA). Such methods are very complex and incurs large computational overhead. In this paper, we propose an efficient RWA algorithm to utilize the time disjoint property as well as space disjoint property through fast grouping of SLDs. The computer simulation shows that our proposed algorithm indeed achieves up to $54\%$ faster computation with similar number of wavelengths than the existing heuristic sRWA algorithm.

• 수도
• /
• v.24 no.4 s.85
• /
• pp.39-46
• /
• 1997

실험실 규모의 연구를 확대한 Pilot-Plant연구는 Bromate 감소에 대한 다양한 수질 문제에 대응할 수 있었다. 이러한 연구를 통해 산성하에서 $Fe^{2+}$을 주입시 Bromate가 감소됨을 확인하였다. 그러나 이러한 반응은 느린 반응이었으며, 온도에 의존하는 반응이었다. 단독응집제로서 $Fe^{2+}$은 탁도를 증가시켰다. 따라서 탁도를 제어하기 위해 $Fe^{2+}$를 주입하였다. $Fe^{2+}$/$Fe^{3+}$응집제의 조합으로 TOC를 제거할 수 있었다. 초기 결과를 통해 이러한 공정은 매우 면밀히 추진되어야 하며, 모든 온도에서 적용될 수 없었다. 현재까지 얻어진 결과에 의하면 오존처리함으로서 발생되는 Bromate를 최소화하는 방안은 낮은 pH조건과 $Fe^{2+}$의 주입이다. 최종 처리수에서 입자상물질과 철을 최소화하기 위해서는 pH 등과 같은 조건들을 변화시켜 여과공정 이전에 잔류 $Fe^{2+}$를 산화시킬 수 있도록 초기에 최적화가 이루어 져야 한다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2005.11b
• /
• pp.418-420
• /
• 2005

본 연구에서는 각종 전문가 선정의 전문성, 공정성, 투명성 및 신뢰성 제공과 최적으로 전문가 그룹에 적합한 전문가를 구성하기 위한 전문가 선정 방법론을 제안한다. 이를 위해, 전문가를 3차원적으로 탐색 및 정량적인 값으로 평가할 수 있는 전문가 후보군 선정 알고리즘을 제시하였으며, 선정된 전문가 후보군들을 조합 최적화 문제에 많이 응용되고 있는 유전자 알고리즘을 이용하여 전문가 선정 방법을 보였다.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.25 no.1
• /
• pp.27-36
• /
• 2000

We perform a computational complexity analysis of a heuristic algotithm proposed in the literature for the combinatorial optimization problems extended with a single side-constraint. This algorithm, although such a view was not given in the original work, is a disguised version of an optimal Lagrangian dual solution technique. It also has been observed to be a very efficient heuristic producing near-optimal solutions for the primal problems in some experiments. Especially, the number of iterations grows sublinearly in terms of the network node size so that the heuristic seems to be particularly suitable for the applicatons such as routing with semi-real time requirements. The goal of this paper is to establish a polynomal worst-case complexity of the algorithm. In particular, the obtained complexity bound suports the sublinear growth of the required iterations.