• Journal of Intelligence and Information Systems
• /
• v.16 no.3
• /
• pp.1-14
• /
• 2010

The back-propagation neural network (BPN) has long been successfully applied in bankruptcy prediction problems. Despite its wide application, some major issues must be considered before its use, such as the network topology, learning parameters and normalization methods for the input and output vectors. Previous studies on bankruptcy prediction with BPN have shown that many researchers are interested in how to optimize the network topology and learning parameters to improve the prediction performance. In many cases, however, the benefits of data normalization are often overlooked. In this study, a genetic algorithm (GA)-based normalization transform, which is defined as a linearly weighted combination of several different normalization transforms, will be proposed. GA is used to extract the optimal weight for the generalization. From the results of an experiment, the proposed method was evaluated and compared with other methods to demonstrate the advantage of the proposed method.

• Journal of the Earthquake Engineering Society of Korea
• /
• v.10 no.6 s.52
• /
• pp.19-28
• /
• 2006

Most conventional model updating methods must use mathematical objective function with experimental modal matrices and analytical system matrices or must use information about the gradient or higher derivatives of modal properties with respect to each updating parameter. Therefore, most conventional methods are not appropriate for complex structural system such as bridge structures due to stability problem in inverse analysis with ill-conditions. Sometimes, moreover, the updated model may have no physical meaning. In this paper, a new FE model updating method based on a hybrid optimization technique using genetic algorithm (GA) and Holder-Mead simplex method (NMS) is proposed. The performance of hybrid optimization technique on the nonlinear problem is demonstrated by the Goldstein-Price function with three local minima and one global minimum. The influence of the objective function is evaluated by the case study of a simulated 10-dof spring-mass model. Through simulated case studies, finally, the objective function is proposed to update mass as well as stiffness at the same time. And so, the proposed hybrid optimization technique is proved to be an efficient method for FE model updating.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.38 no.5
• /
• pp.427-436
• /
• 2010

This paper deals with a task assignment problem of multiple UAVs performing multiple tasks on multiple targets. The task assignment problem of multiple UAVs is a kind of combinatorial optimization problems such as traveling salesman problem or vehicle routing problem, and it has NP-hard computational complexity. Therefore, computation time increases as the size of considered problem increases. To solve the problem efficiently, approximation methods or heuristic methods are widely used. In this study, the problem is formulated as a mixed integer linear program, and is solved by a mixed integer linear programming and a genetic algorithm, respectively. Numerical simulations for the environment of the multiple targets, multiple tasks, and obstacles were performed to analyze the optimality and efficiency of each method.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.39 no.3
• /
• pp.1-9
• /
• 2016

NSS (Navigation satellite system) provides the information for determining the position, velocity and time of users in real time using satellite-networking, and is classified into GNSS (Global NSS) and RNSS (Regional NSS). Although GNSS services for global users, the exactitude of provided information is dissatisfied with the degree required in modern systems such as unmanned system, autonomous navigation system for aircraft, ship and others, air-traffic control system. Especially, due to concern about the monopoly status of the countries operating it, some other countries have already considered establishing RNSS. The RNSS services for users within a specific area, however, it not only gives more precise information than those from GNSS, but also can be operated independently from the NSS of other countries. Thus, for Korean RNSS, this paper suggests the methodology to design the satellite constellation considering the regional features of Korean Peninsula. It intends to determine the orbits and the arrangement of navigation satellites for minimizing PDOP (Position dilution of precision). PGA (Parallel Genetic Algorithm) geared to solve this nonlinear optimization problem is proposed and STK (System tool kit) software is used for simulating their space flight. The PGA is composed of several GAs and iterates the process that they search the solution for a problem during the pre-specified generations, and then mutually exchange the superior solutions investigated by each GA. Numerical experiments were performed with increasing from four to seven satellites for Korean RNSS. When the RNSS was established by seven satellites, the time ratio that PDOP was measured to less than 5 (i.e. better than 'Good' level on the meaning of the PDOP value) was found to 94.3% and PDOP was always kept at 10 or less (i.e. better than 'Moderate' level).

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.38 no.11
• /
• pp.1215-1220
• /
• 2014

Breaking time is an important performance indicator of a circuit breaker. Thus, the operating mechanism of the circuit breaker should be optimized for reducing the breaking time. The operating mechanism in a gas circuit breaker is made up of several latches. Specifically, the geometry and relative positions of latches influence the dynamic behaviors of the operating mechanism. In this study, a three-stage latch operating mechanism is analyzed on the basis of the verified multibody dynamics model constructed using the MSC.ADAMS program. The relative positions and lengths of latches are selected as design variables. The dominant design variables are selected by a design study. Optimization is performed using a genetic algorithm (GA). The study results demonstrate that the performance of the circuit breaker improves by about 22.5.

• Journal of Energy Engineering
• /
• v.12 no.1
• /
• pp.42-48
• /
• 2003

In system planing and operation, voltage and reactive power control is very important. The voltage deviation and system losses can be reduced through control of reactive power sources. In general, there are several different reactive power sources, we used switched shunt capacitor to improve the voltage profile and to reduce system losses. Since there are many switched shunt capacitors in power system, so it if necessary to coordinate these switched shunt capacitors. In this study, Genetic Algorithm (GA) is used to find optimal coordination of switched shunt capacitors in a local area of power system. In case study, the effectiveness of the proposed method is demonstrated in KEPCO's power system. The simulation is performed by PSS/E and the results of simulation are compared with sensitivity method.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.37 no.2A
• /
• pp.83-94
• /
• 2012

Various wireless communication devices or network such as WRAN and WLAN will coexist in the TVWS(TV White Space). Because of this coexistence, the wireless devices which use the TVWS have to avoid interfering to not only licensed TV receiver and wireless microphone but also homogeneous or heterogeneous TVBD(TV Band Device)s. In this paper, we propose two frequency sharing methods for the coexistence of WLAN and WRAN in terms of interference reduction and throughput enhancement in both homogeneous and heterogeneous networks. One is the WRAN spectrum etiquette to provide more wide bandwidth for WLAN users and the other is the WLAN frequency selection methods to improve the throughput performance. The simulation results have confirmed the throughput improvement of the proposed methods. Moreover, the proposed methods is also applicable to improve the throughput performance and reduce interference of similar systems working in a cognitive manner.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.42 no.1
• /
• pp.91-97
• /
• 2005

In the mobile antenna systems for satellite multimedia communications, the active way antenna having a low sidelobe antenna pattern is described in this paper. This designed and fabricated array antenna is satisfied with international beam pattern regulation on moving states. The subarray of the proposed mobile antenna system is arranged with a stair-planar structure and non-periodic array spacing. This subarray is designed with three-layered microstrip patch as both receiving and transmitting radiator of which are improved with antenna gain and bandwidth. Also, the optimum subarray spacing is designed to make the lowest sidelobe pattern by genetic algorithm. In addition, the characteristics of a GA-perturbed array are investigated from simulated and measured beam pattern results.

• Journal of Ocean Engineering and Technology
• /
• v.29 no.5
• /
• pp.366-372
• /
• 2015

Ocean energy is one of the most promising renewable energy resources. In particular, South Korea is one of the countries where it is economically and technically feasible to develop tidal current power plants to use tidal current energy. In this study, based on the design code for HARP_Opt (Horizontal axis rotor performance optimizer) developed by NREL (National Renewable Energy Laboratory) in the United States, and applying the BEMT (Blade element momentum theory) and GA (Genetic algorithm), the optimal shape design and performance evaluation of the horizontal axis rotor for a 200-kW-class tidal current turbine were performed using different numbers of blades (two or three) and a pitch control method (variable pitch or fixed pitch). As a result, the VSFP (Variable Speed Fixed Pitch) turbine with three blades showed the best performance. However, the performances of four different cases did not show significant differences. Hence, it is necessary when selecting the final design to consider the structural integrity related to the fatigue, along with the economic feasibility of manufacturing the blades.

• Journal of the Institute of Convergence Signal Processing
• /
• v.3 no.4
• /
• pp.35-41
• /
• 2002

To solve the large scale optimization problem approximately, various approaches have been introduced. They are mainly based on recent research advancement of simulations for evolutions, flocking, annealing, and interactions among organisms on artificial environments. The typical ones are simulated annealing(SA), artificial neural network(ANN), genetic algorithms(GA), tabu search(TS), etc. Recently the particle swarm optimization(PSO) has been introduced. The PSO simulates the process of birds flocking or fish schooling for food, as with the information of each agent Is share by other agents. The PSO technique has been applied to various optimization problems of which variables are continuous. However, there are seldom trials for visualization of searching process. This paper proposes a new visualization tool for searching process particle swarm optimization(PSO) algorithm. The proposed tool is effective for understanding the searching process of PSO method and educational for students.