• Journal of the military operations research society of Korea
• /
• v.35 no.3
• /
• pp.47-59
• /
• 2009

A hybrid Genetic Algorithm is applied to military resource allocation problem. Since military uses many resources in order to maximize its ability, optimization technique has been widely used for analysing resource allocation problem. However, most of the military resource allocation problems are too complicate to solve through the traditional operations research solution tools. Recent innovation in computer technology from the academy makes it possible to apply heuristic approach such as Genetic Algorithm(GA), Simulated Annealing(SA) and Tabu Search(TS) to combinatorial problems which were not addressed by previous operations research tools. In this study, a hybrid Genetic Algorithm which reinforces GA by applying local search algorithm is introduced in order to address military optimization problem. The computational result of hybrid Genetic Algorithm on Missile Interceptor Allocation problem demonstrates its efficiency by comparing its result with that of a simple Genetic Algorithm.

• Communications for Statistical Applications and Methods
• /
• v.14 no.3
• /
• pp.507-516
• /
• 2007

Multinomial logistic regression is probably the most popular representative of probabilistic discriminative classifiers for multiclass classification problems. In this paper, a kernel variant of multinomial logistic regression is proposed by combining a Newton's method with a bound optimization approach. This formulation allows us to apply highly efficient approximation methods that effectively overcomes conceptual and numerical problems of standard multiclass kernel classifiers. We also provide the approximate cross validation (ACV) method for choosing the hyperparameters which affect the performance of the proposed approach. Experimental results are then presented to indicate the performance of the proposed procedure.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.10 no.2
• /
• pp.193-200
• /
• 2002

Simple spring-damper-mass models have been widely used to investigate whole-body vortical biodynamic response characteristics of the seated vehicle driver. Most previous models have not considered the effect of wobbling masses; i.e. heart, lungs, liver, intestine, etc. In this study, 4 -DOF seated driver model including one non-rigid mass representing wobbling visceral mass, 5-DOF model including intestine, and 10-DOF model including five lumbar vertebral masses were proposed. The model parameters were identified by a combinatorial optimization technique. simulated annealing method. The objective function was chosen as the sum of error between model response of seat-to-head transmissibility and driving point mechanical impedance and those of experimental data for subjects seated erect without backrest support. The model response showed a good agreement with the experimental response characteristics. Using a 10-DOF model, calculated resonance frequency of lumbar spine at 4Hz was matched well with experimental results of Panjabi et al.

• Proceedings of the IEEK Conference
• /
• summer
• /
• pp.400-404
• /
• 2004

There are many methods to find solutions for Integer Programming problems (IPs) such as the Branch-Bound philosophy or the Cutting Plane algorithm. However, most of them have a problem that is the explosion of sets in the computing process. In addition, GA is known as a heuristic search algorithm for solutions of optimization problems. It is started from a random initial guess solution and attempting to find one that is the best under some criteria and conditions. The paper will study an artificial intelligent method to solve IPs by using Genetic Algorithms (GAs). The original solution of this was presented in the papers of Fabricio Olivetti de Francaand and Kimmo Nieminen [2003]. However, both have several limitations which causes could be operations in GAs. The paper proposes a method to upgrade these operations and computational results are also shown to support these upgrades.

• Journal of the Korean Institute of Navigation
• /
• v.18 no.2
• /
• pp.57-67
• /
• 1994

This paper treats the optimization analysis of tactical ship scheduling problems in the world seaborne bulk trade. The authors use the term 'tactial' to describe the ship scheduling problem where the owners should employ skillful tactics as an expedient toward gaining the higher profits per period in short term. Relevent research and related problems on ship scheduling problems are reviewed briefly and a model for the tactical ship scheduling problem formulated as Set Problem is introduced by modifying the previous work of Fisher(1989). The reality and practicability of the model is validated by some ship-ping statistics. Proper solution approaches are outlined in the context of computational tractability in tackling the Mixed Integer Propramming. Some underlying consideration for the computational experiment is also mentioned. The authors conclude the paper with the remarks on the need of user-friendly Decision Support System for ship scheduling under varying decision environment.

• Journal of Ship and Ocean Technology
• /
• v.12 no.4
• /
• pp.7-19
• /
• 2008

In preliminary ship design, a parametric study is a more realistic way to explore design space and analyze design problem than an optimization technique due to time-consuming computational work or a difficulty in incorporating all constraints into the optimization formulation. In the parametric study, feasible alternatives are examined in various aspects; the best one can be selected. Among the aspects, the strength assessment by FE analysis is an essential process in the ship design. This paper proposes a system to facilitate a parametric study for FE model based on design of experiment (DOE). It works on a FE pre-processor environment and assists a user to define a parametric study by interacting with FE model. It also provides an interface module with a FE solver in order to control the input file and extract predefined FE results from the output file. Based on the proposed system, a better understating and a better design are expected to be achieved.

• ETRI Journal
• /
• v.36 no.4
• /
• pp.625-634
• /
• 2014

This paper studies a dual-hop multiple-access relay network where two independent source nodes transmit information to a common destination node with the aid of multiple single-antenna amplify-and-forward relays. Each relay node is subject to an individual power constraint. We focus on the design of distributed beamforming schemes for the relays to support the transmission rate requirements of the two sources. To this end, we first characterize the achievable rate region for this network via solving a sequence of corner point optimization problems proposed in this paper. We also develop several low-complexity suboptimal schemes in closed form. Two inner bounds of the achievable rate region are theoretically shown to be approximately optimal in two special scenarios. Finally, numerical results demonstrate the effectiveness of our proposed approaches.

• Proceedings of the Computational Structural Engineering Institute Conference
• /
• 1997.04a
• /
• pp.139-146
• /
• 1997

The main purpose of this paper is to investigate the near-optimal parameters of continuous beam subject to a moving load. The computer-aided optimization technique is used to obtain the near-optimal parameters. The computer program is developed to obtain the natural frequency parameters and the forced vibration responses to a transit point load for the continuous beam with variable support spacing, mass and stiffness. The optimization function to describe the design efficiency is defined as a linear combination of four dimensionless span characteristics: the maximum dynamic stress; the stress difference between span segments; the rms deflection under the transit point load; and the total span mass. Studies of three span beams show that the beam with near-optimal parameters can improve design efficiency by 12 to 24 percent when compared to a reference configuration beams of the same total span length.

• Journal of the Korean Geophysical Society
• /
• v.4 no.3
• /
• pp.205-217
• /
• 2001

Time pasges could deteriorate the flow ability and hold the folw in the water distribution facilities because of their erosion and breakdown. It is necessary that the study to determine the optimal change time and the improvement plan for the continuous management using optimization methods or decision support systems. But, the present study tendency only aware the changes of hydraulie characteristics without industrial management plans. This study shows the pipe replacement program in these two concepts and the elementary process to apply it to Daejeon city.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.34 no.2
• /
• pp.112-120
• /
• 2011

The early phase of design intrinsically contains multiple sources of uncertainty in describing design, and nevertheless the decision-making process at this phase exerts a critical effect upon drawing a successful design. This paper proposes a set-based design approach for multi-objective design problem under uncertainty. The proposed design approach consists of four design processes including set representation, set propagation, set modification, and set narrowing. This approach enables the flexible and robust design while incorporating designer's preference structure. In contrast to existing optimization techniques, this approach generates a ranged set of design solutions that satisfy changing sets of performance requirements.