• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.6 no.9
• /
• pp.2086-2097
• /
• 2012

A terminal-based dynamic clustering algorithm is proposed in a multi-cell scenario, where the user could select the cooperative BSs from the predetermined static base stations (BSs) set based on dynamic channel condition. First, the user transmission rate is derived based on linear precoding and per-cell feedback scheme. Then, the dynamic clustering algorithm can be implemented based on two criteria: (a) the transmission rate should meet the user requirement for quality of service (QoS); (b) the rate increment exceeds the predetermined constant threshold. By adopting random vector quantization (RVQ), the optimized number of cooperative BSs and the corresponding channel conditions are presented respectively. Numerical results are given and show that the performance of the proposed method can improve the system resources utilization effectively.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.22 no.4
• /
• pp.555-566
• /
• 2019

In order to prepare for the future warfare environment, which requires a faster operational tempo, it is necessary to utilize the fourth industrial revolution technology in the field of military operations. This study propose a methodology, 'machine learning based dynamic targeting', which can contribute to reduce required man-hour for dynamic targeting. Specifically, a decision tree algorithm is considered to apply to dynamic targeting process. The algorithm learns target prioritization patterns from JIPTL(Joint Integrated Prioritized Target List) which is the result of the deliberate targeting, and then learned algorithm rapidly(almost real-time) determines priorities for new targets that occur during ATO(Air Tasking Order) execution. An experiment is performed with artificially generated data to demonstrate the applicability of the methodology.

• The Transactions of the Korea Information Processing Society
• /
• v.6 no.5
• /
• pp.1393-1402
• /
• 1999

This paper proposes an efficient principal feature extraction of the image data using neural networks of a new learning algorithm. The proposed learning algorithm is a backpropagation(BP) algorithm based on the steepest descent and dynamic tunneling. The BP algorithm based on the steepest descent is applied for high-speed optimization, and the BP algorithm based on the dynamic tunneling is also applied for global optimization. Converging to the local minimum by the BP algorithm of steepest descent, the new initial weights for escaping the local minimum is estimated by the BP algorithm of dynamic tunneling. The proposed algorithm has been applied to the 3 image data of 12${\times}$12pixels and the Lenna image of 128${\times}$128 pixels respectively. The simulation results shows that the proposed algorithm has better performances of the convergence and the feature extraction, in comparison with those using the Sanger method and the Foldiak method for single-layer neural networks and the BP algorithm for multilayer neural network.

• Journal of Korean Institute of Industrial Engineers
• /
• v.19 no.3
• /
• pp.71-79
• /
• 1993

Dynamic production planning problems are to determine the optimal production times and production quantities of product for discrete finite periods. In previous many researches, the solutions for these problems have been developed through the algorithms using dynamic programming. The purpose of this research is to suggest the new algorithm using linear programming. This research is to determine optimal production quantities of product in each period to satisfy dynamic for discrete finite periods, minimizing the total of production cost and inventory holding cost. Cost functions are concave, and no backlogging for product is allowed. The new algorithm for capacity constrained problem is developed.

• Communications for Statistical Applications and Methods
• /
• v.10 no.3
• /
• pp.795-804
• /
• 2003

In this article, a tomography for the estimation of the origin-destination(OD) traffic intensities in dynamic routing network is considered. Vardi(1996)'s approach based on fixed route is not directly applicable to dynamic routing protocols, which arises from the fact that we cannot access the route at every observation time. While it uses link-wise traffics as the observations, the proposed method considers the triple of ingress/outgress/relayed traffics data at each node so that we can transform the problem into a routing-independent tomography. An EM algorithm for implementation and some simulated experiments are provided.

• Journal of Korean Institute of Industrial Engineers
• /
• v.31 no.3
• /
• pp.194-200
• /
• 2005

A stochastic dynamic lot sizing problem for multi-item is suggested in the case that the distribution of the cumulative demand is known over finite planning horizons and all unsatisfied demand is fully backlogged. Each item is produced simultaneously at a variable ratio of input resources employed whenever setup is incurred. A dynamic programming algorithm is proposed to find the optimal production policy, which resembles the Wagner-Whitin algorithm for the deterministic case problem but with some additional feasibility constraints.

• Journal of Korean Institute of Industrial Engineers
• /
• v.36 no.1
• /
• pp.7-12
• /
• 2010

This paper considers a dynamic lot-sizing problem with backlogging under a minimum replenishment policy. For general concave production costs, we propose an O($T^5$) dynamic programming algorithm. If speculative motive is not allowed, in this case, a more efficient O($T^4$) algorithm is developed.

• 한국가시화정보학회:학술대회논문집
• /
• 2004.12a
• /
• pp.25-32
• /
• 2004

The new algorithm for higher performance of dynamic PIV has been proposed. Present study considered mathematical basis of PIV analysis for multiple-time-step images and it enables us to analyze the high time-resolution PIV, which is obtained by dynamic PIV system. Conventional single pair image PIV analysis gives us the velocity field data in each time step but it sometimes contains unnecessary information of target flow. Present technique utilize multi-time step correlation information, and it is analyzed.

• Journal of KIISE:Computer Systems and Theory
• /
• v.31 no.1_2
• /
• pp.95-101
• /
• 2004

The scheduling problem that maps independent tasks to heterogeneous resources in distributed computing systems is known as NP-complete［1］. GRID［2］ is an example of distributed systems that consisted of heterogeneous resources. Many algorithms to solve this problem have been presented［1,3,4,5］. The scheduling algorithm can be classified into static scheduling algorithms and dynmic scheduling algorithms. A dynamic scheduling algorithm can be used when we can not predict the priority of tasks. Moreover, a dynamic scheduling algorithm can be divided into on-line mode algorithm and batch mode algorithm according to the scheduling time［1,6］. In this paper, we propose a new on-line mode scheduling algorithm. By extensive simulation, we can see that our scheduling algorithm outperforms previous scheduling algorithms.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.33B no.4
• /
• pp.201-208
• /
• 1996

This paper proposes an efficient method for improving the training performance of the neural network using a hybrid of backpropagation algorithm and dynamic tunneling system.The backpropagation algorithm, which is the fast gradient descent method, is applied for high-speed optimization. The dynamic tunneling system, which is the deterministic method iwth a tunneling phenomenone, is applied for blobal optimization. Converging to the local minima by using the backpropagation algorithm, the approximate initial point for escaping the local minima is estimated by the pattern classification, and the simulation results show that the performance of proposed method is superior th that of backpropagation algorithm with randomized initial point settings.