• The KIPS Transactions:PartB
• /
• v.11B no.1
• /
• pp.77-82
• /
• 2004

Reinforcement learning takes reward about selecting action when agent chooses some action and did state transition in Present state. this can be the important subject in reinforcement learning as temporal-credit assignment problems. In this paper, by new meta heuristic method to solve hard combinational optimization problem, examine Ant-Q learning method that is proposed to solve Traveling Salesman Problem (TSP) to approach that is based for population that use positive feedback as well as greedy search. And, suggest Ant-TD reinforcement learning method that apply state transition through diversification strategy to this method and TD-error. We can show through experiments that the reinforcement learning method proposed in this Paper can find out an optimal solution faster than other reinforcement learning method like ACS and Ant-Q learning.

• The KIPS Transactions:PartB
• /
• v.16B no.3
• /
• pp.195-202
• /
• 2009

In this paper, we propose the regions segmentation method of the white matter and the gray matter for brain MR image by using the ant colony optimization algorithm. Ant Colony Optimization (ACO) is a new meta heuristics algorithm to solve hard combinatorial optimization problem. This algorithm finds the expected pixel for image as the real ant finds the food from nest to food source. Then ants deposit pheromone on the pixels, and the pheromone will affect the motion of next ants. At each iteration step, ants will change their positions in the image according to the transition rule. Finally, we can obtain the segmentation results through analyzing the pheromone distribution in the image. We compared the proposed method with other threshold methods, viz. the Otsu' method, the genetic algorithm, the fuzzy method, and the original ant colony optimization algorithm. From comparison results, the proposed method is more exact than other threshold methods for the segmentation of specific region structures in MR brain image.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.6
• /
• pp.778-785
• /
• 2020

Wireless mesh networks consist of mesh clients, mesh routers and mesh access points. The mesh router connects wireless network services to the mesh client, and the mesh access point connects to the backbone network using a wired link and provides Internet access to the mesh client. In this paper, a limited number of mesh routers and mesh access points are used to propose optimization algorithms for network design for wireless mesh networks. The optimization algorithm in this paper has been applied with a sub-subscription algorithm, which is one of the meta-heuristic methods, and is designed to minimize the transmission delay for the placement of mesh routers and mesh access points, and produce optimal results within a reasonable time. The proposed algorithm was evaluated in terms of transmission delay and time to perform the algorithm for the placement of mesh routers and mesh access points, and the performance evaluation results showed superior performance compared to the previous meta-heuristic methods.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.05a
• /
• pp.147-150
• /
• 2022

최근 들어 다양한 제약 조건이 있는 스마트 시티나 스마트 팩토리와 같은 도메인들 내에서 태스크들을 효과적으로 처리하기 위해서 MEC 기술이 많이 사용되고 있다. 그러나 이러한 도메인에서 발생하는 복잡하고 동적인 시나리오는 기존의 휴리스틱이나 메타 휴리스틱 기법을 이용하여 해결하기엔 계산 복잡도가 증가하는 문제점을 가지고 있다. 따라서 최근 들어 이러한 문제점을 해결하기 위한 방법 중 하나로 강화학습과 딥러닝이 결합된 DRL 기법이 주목을 받고 있다. 본 연구는 스마트 팩토리 환경에서 종속성을 가진 태스크들이 실행시간과 태스크가 처리되는 MEC 서버들의 로드 표준편차를 최소화하는 태스크 스케줄링 기법을 제안한다. 모의실험을 통하여 제안 기법은 태스크가 증가하는 동적인 환경에서도 좋은 성능을 보임을 증명하였다.

• Journal of the Korea Safety Management & Science
• /
• v.11 no.4
• /
• pp.213-220
• /
• 2009

The minimum latency problem, also known as the traveling repairman problem and the deliveryman problem is to minimize the overall waiting times of customers, not to minimize their routing times. In this research, a genetic algorithm, a clonal selection algorithm and a population management genetic algorithm are introduced. The computational experiment shows the objective value of the clonal selection algorithm is the best among the three algorithms and the calculating time of the population management genetic algorithm is the best among the three algorithms.

• Journal of Korean Institute of Industrial Engineers
• /
• v.33 no.1
• /
• pp.86-98
• /
• 2007

This paper presents a heuristic algorithm for the traveling salesman problem with time windows (TSPTW). Aniterative insertion algorithm as a constructive search heuristic and a hybrid meta heuristic combining simulatedannealing and tabu search with the randomized selection of 2-interchange and a simple move operator as animproving search heuristic are proposed, Computational tests performed on 400 benchmark problem instancesshow that the proposed algorithm generates optimal or near-optimal solutions in most cases. New best knownheuristic values for many benchmark problem sets were obtained using the proposed approach.

• Journal of Korean Institute of Industrial Engineers
• /
• v.38 no.4
• /
• pp.262-275
• /
• 2012

This paper develops a multistage scheduling algorithm for the module operation of the LCD(Liquid Crystal Display) production systems and tests the efficiency of the proposed algorithm. The module operation is a multistage form composed of multiple sub operations of processes, and each stage is consists of multiple lines with the same kinds of machines. This paper presents a mathematical modeling reflecting the constraints of the LCD module operation and develops a multistage scheduling algorithm based on tabu search metaheuristic approach. For this purpose, an production order is assigned to a line of the sub operations and a sequence of the assigned order is rearranged to draw an efficient schedule. Simulation experiments test performance measures and show the efficiency of the proposed algorithm.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 2004.05a
• /
• pp.319-322
• /
• 2004

물류/택배업계의 공급사슬관리에서 차량에 의한 고객의 요구 서비스 시간대 만족은 고객의 재고수준을 낮추고 또한 서비스 수준의 향상에 매우 중요한 제약조건이다. 최근에 소개된 메타휴리스틱인 개미해법(Ant Colony Optimization: ACO)은 NP-hard 문제의 해공간 탐색에 있어서 상당한 장점을 가지고 있으나, 시간대 제약이 있는 차량경로문제(Vehicle Routing Problems with Time Windows: VRPTW)에 대한 적용은 아주 미비한 실정이다. 따라서, 본 연구에서는 ACO 를 VRPTW에 적용하여 최선의 차량경로 해를 구하기 위한 여러 변형을 제시하고, 이들의 영향을 다양한 실험문제를 이용하여 분석하고자 한다. 계산실험 결과, 기본 ACO 에 여러 설계 요소들을 추가함에 따라 계산시간이 다소 증가하지만 보다 우수한 차량경로 해를 구할 수 있었다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2011.06b
• /
• pp.470-473
• /
• 2011

본 논문에서는 첫째, 기존 HW/SW partitioning문제의 접근 방식 모델에서 다루지 못하였던 시간 의존적인 개발 기간, 판매 가격, 판매량, time-to-market 등의 요소들을 반영하는 multi-objective 최적화문제 형태의 새로운 "Sequential HW/SW Partitioning Optimization Framework(SPOF)"를 제시하고 둘째, 그 모델로 형식화된 NP-hard 문제를 일반적으로 해결하기위한 해법으로 SPOF의 형태에 맞게끔 변형한 chromosome과 genetic operation을 사용하는 메타휴리스틱 "Fast and Elitist Multi-objective Genetic Algorithm(NSGA-II)"을 제시한다. 실험을 통하여 NSGA-II의 최적 솔루션에의 수렴성을 보인다.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 2006.05a
• /
• pp.1178-1185
• /
• 2006

컨테이너 터미널에서의 생산성은 본선작업의 효율성과 밀접한 관련이 있다. 효율적인 본선작업을 위한 첫 번째 단계는 선석에서 컨테이너를 취급하는 장비인 안벽크레인(Quay Crane : QC)에 대하여 효율적인 작업일정계획을 수립하는 것이다. 일반적으로 안벽크레인의 작업일정계획은 선박내의 장치계획에 관한 정보와 장치장의 장치현황정보등 많은 정보를 활용해야 하며, 선박의 안정성과 크레인의 작업용이성 등 다양한 제약사항을 고려하여야 한다. 따라서 본 연구에서는 인공지능기법 중 최적에 가까운 해를 찾아주는 탐색기법인 GRASP(Greedy Randomized Adaptive Search Procedure)를 적용하여 실제 현장에서 적용 가능한 안벽크레인 작업일정계획기법을 제안하였다. 또한, 컨테이너 터미널의 실제 자료를 수집하여 제안된 메타휴리스틱 알고리즘의 성능을 분석하였다.