• Proceedings of the Korean Society for Quality Management Conference
• /
• 1998.11a
• /
• 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.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.12 no.6
• /
• 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.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 2004.05a
• /
• 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.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.13 no.3
• /
• 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.

• Korean Management Science Review
• /
• v.12 no.3
• /
• 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.

• The Journal of Information Systems
• /
• v.25 no.1
• /
• 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.

• Proceedings of the KIPE Conference
• /
• 2010.07a
• /
• 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.

• The Transactions of the Korean Institute of Electrical Engineers A
• /
• v.50 no.1
• /
• 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.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.21 no.5
• /
• pp.929-935
• /
• 2017

All sensor nodes generally determine their positions using anchor nodes that are located in underwater sensor networks. This paper proposes a Tabu search algorithm to determine the minimum number of anchor nodes for the location of all sensor nodes in underwater sensor networks. As the number of the sensor nodes increases in the network, the amount of calculation that determines the number of anchor nodes would be too much increased. In this paper, we propose a Tabu search algorithm that determines the minimum number of anchor nodes within a reasonable computation time in a high dense network, and propose an efficient neighborhood generating operation of the Tabu search algorithm for efficient search. The proposed algorithm evaluates those performances through some experiments in terms of the minimum number of anchor nodes and execution time. The proposed algorithm shows 5-10% better performance than the conventional algorithm.

• Proceedings of the KSME Conference
• /
• 2000.04a
• /
• 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.