• 한국품질경영학회:학술대회논문집
• /
• 한국품질경영학회 1998년도 The 12th Asia Quality Management Symposium* Total Quality Management for Restoring Competitiveness
• /
• pp.696-704
• /
• 1998

Artificial neural networks (ANN) have successfully applied into various areas. But, How to effectively established network is the one of the critical problem. This study will focus on this problem and try to extensively study. Firstly, four different learning algorithms ANNs were constructed. The learning algorithms include backpropagation, simulated annealing, genetic algorithm, and tabu search. The experimental results of the above four different learning algorithms were tested by statistical analysis. The training RMS, training time, and testing RMS were used as the comparison criteria.

• 한국소음진동공학회논문집
• /
• 제12권6호
• /
• pp.478-487
• /
• 2002

This paper presents a hybrid method to compute the solutions of an optimization Problem. The present hybrid algorithm is the synthesis of an artificial life algorithm and the random tabu search method. The artificial life algorithm has the most important feature called emergence. The emergence is the result of dynamic interaction among the individuals consisting of the system and is not found in an individual. The conventional artificial life algorithm for optimization is a stochastic searching algorithm using the feature of artificial life. Emergent colonies appear at the optimum locations in an artificial ecology. And the locations are the optimum solutions. We combined the feature of random-tabu search method with the conventional algorithm. The feature of random-tabu search method is to divide any given region into sub-regions. The enhanced artificial life algorithm (EALA) not only converge faster than the conventional artificial life algorithm, but also gives a more accurate solution. In addition, this algorithm can find all global optimum solutions. The enhanced artificial life algorithm is applied to the optimum design of high-speed, short journal bearings and its usefulness is verified through an optimization problem.

• 한국경영과학회:학술대회논문집
• /
• 대한산업공학회/한국경영과학회 2004년도 춘계공동학술대회 논문집
• /
• pp.311-314
• /
• 2004

The 2 DBPP(Two-Dimensional Bin Packing Problem) is a problem of packing each item into a bin so that no two items overlap and the number of required bins is minimized under the set of rectangular items which may not be rotated and an unlimited number of identical rectangular bins. The 2 DBPP is strongly NP-hard and finds many practical applications in industry. In this paper we discuss a tabu search approach which includes tabu list, intensifying and diversification strategies. The HNFDH(Hybrid Next Fit Decreasing Height) algorithm is used as an internal algorithm. We find that use of the proper parameter and function such as maximum number of tabu list and space utilization function yields a good solution in a reduced time. We present a tabu search algorithm and its performance through extensive computational experiments.

• 디지털산업정보학회논문지
• /
• 제13권3호
• /
• pp.65-73
• /
• 2017

The fifth generation(5G) of wireless networks will connect not only smart phone but also unimaginable things. Therefore, 5G cellular network is facing the soaring traffic demand of numerous user devices. To solve this problem, a huge amount of 5G base stations will need to be installed. The base station positioning problem is an NP-hard problem that does not know how long it will take to solve the problem. Because, it can not find an answer other than to check the number of all cases. In this paper, to solve the NP hard problem, we compare the tabu search and the genetic algorithm using real maps for optimal cell planning. We also perform Monte Carlo simulations to study the performance of the Tabu search and Genetic algorithm for 5G cell planning. As a results, Tabu search required 2.95 times less computation time than Genetic algorithm and showed accuracy difference of 2dBm.

• 경영과학
• /
• 제12권3호
• /
• pp.177-185
• /
• 1995

This paper presents a Tabu Search method to minimize a number of tardy jobs in the nonidentical parallel machine scheduling. The Tabu Search method employs a restricted neighborhood for the reduction of computation time. In this paper, we use two different types of method for a single machine scheduling. One is Moore's algorithm and the other is insertion method. We discuss computational experiments on more than 1000 test problems.

• 한국정보시스템학회지:정보시스템연구
• /
• 제25권1호
• /
• pp.159-182
• /
• 2016

Purpose This paper aims to develop a novel tabu search algorithm for solving the sequencing problems with precedence constraints. Due to constraints, the traditional meta heuristic methods can generate infeasible solutions during search procedure, which must be carefully dealt with. On the contrary, the candidate order based tabu search (COTS) is based on a novel neighborhood structure that guarantees the feasibility of solutions, and can dealt with a wide range of sequencing problems in flexible manner. Design/methodology/approach Candidate order scheme is a strategy for constructing a feasible sequence by iteratively appending an item at a time, and it has been successfully applied to genetic algorithm. The primary benefit of the candidate order scheme is that it can effectively deal with the additional constraints of sequencing problems and always generates the feasible solutions. In this paper, the candidate order scheme is used to design the neighborhood structure, tabu list and diversification operation of tabu search. Findings The COTS has been applied to the single machine job sequencing problems, and we can see that COTS can find the good solutions whether additional constraints exist or not. Especially, the experiment results reveal that the COTS is a promising approach for solving the sequencing problems with precedence constraints. In addition, the operations of COTS are intuitive and easy to understand, and it is expected that this paper will provide useful insights into the sequencing problems to the practitioners.

• 전력전자학회:학술대회논문집
• /
• 전력전자학회 2010년도 하계학술대회 논문집
• /
• pp.51-52
• /
• 2010

In order to simplify the offline identification of induction motor parameters, a method based on optimization using a Tabu Search algorithm is proposed. The Tabu Search algorithm is used to minimize the error between the actual data and an estimated model. The robustness of the method is shown by identifying parameters of the induction motor in three different cases. The simulation results show that the method successfully estimates the motor parameters.

• 대한전기학회논문지:전력기술부문A
• /
• 제50권1호
• /
• pp.28-37
• /
• 2001

This paper presents an efficient algorithm for the loss minimization of distribution system by automatic sectionalizing switch operation in large scale distribution systems. Simulated annealing is particularly well suited for large combinational optimization problem, but the use of this algorithm is also responsible for an excessive computation time requirement. Tabu search attempts to determine a better solution in the manner of a greatest-descent algorithm, but it can not give any guarantee for the convergence property. The hybrid algorithm of two methods with two tabu lists and the proposed perturbation mechanism is applied to improve the computation time and convergence property Numerical examples demonstrate the validity and effectiveness of the proposed methodology using a KEPCO's distribution system.

• 한국정보통신학회논문지
• /
• 제21권5호
• /
• pp.929-935
• /
• 2017

일반적으로 수중 센서 네트워크에서 모든 센서 노드는 위치가 결정된 앵커 노드를 이용하여 자신의 위치를 결정한다. 본 논문에서는 수중 센서 네트워크에서 모든 센서 노드의 위치를 결정하기 위해 최소의 수를 가진 앵커 노드를 결정하기 위한 타부 서치 알고리즘을 제안한다. 네트워크에서 센서 노드의 수가 증가함에 따라 앵커 노드의 수를 결정하는 계산량은 급격히 늘어나게 된다. 본 논문에서는 밀집도가 높은 네트워크에서 적정한 시간 내에 최소의 앵커 노드수를 결정하는 타부 서치 알고리즘을 제안하며, 효율적인 검색을 위해 타부 서치 알고리즘의 효과적인 이웃해 생성 동작을 제안한다. 제안된 알고리즘은 최소 앵커 노드의 수와 실행시간 관점에서 성능을 평가하며, 평가 결과에서 제안된 알고리즘이 기존의 알고리즘에 비해 성능이 5-10% 우수함을 보인다.

• 대한기계학회:학술대회논문집
• /
• 대한기계학회 2000년도 춘계학술대회논문집A
• /
• pp.797-802
• /
• 2000

Flow shop scheduling problem involves processing several jobs on common facilities where a setup time Is incurred whenever there is a switch of jobs. Practical aspect of scheduling focuses on finding a near-optimum solution within a feasible time rather than striving for a global optimum. In this paper, a hybrid meta-heuristic method called tabu-genetic algorithm(TGA) is suggested, which combines the genetic algorithm(GA) with tabu list. The experiment shows that the proposed TGA can reach the optimum solution with higher probability than GA or SA(Simulated Annealing) in less time than TS(Tabu Search). It also shows that consideration of setup time becomes more important as the ratio of setup time to processing time increases.