• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 2008.10a
• /
• pp.1-7
• /
• 2008

The purpose of this paper is to develop a new classification method for predicting consumer choice based on genetic algorithm, and to validate its prediction power over existing methods. To serve this purpose, we propose a hybrid model, and discuss its methodological characteristics in comparison with other existing classification methods. Also, to assess the prediction power of the model, we conduct a series of experiments employing survey data of consumer choices of MP3 players. The results show that the suggested model in this paper is statistically superior to the existing methods such as logistic regression model, artificial neural network model and decision tree model in terms of prediction accuracy. The model is also shown to have an advantage of providing several strategic information of practical use for consumer choice.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.29 no.6 s.237
• /
• pp.809-814
• /
• 2005

The goal of this paper is to minimize the weight of the T-structure supporting steering system in reducing the vibration level on steering wheel which could be amplified by the resonance. Presently, requirements for reducing noise, vibration and harshness (NVH) in automotive area are more stringent than ever. One of them is the vibration of steering system which occurs sometimes at high speeds or when the engine is idling. Besides, the reduction of weight is also one of requirements for improvement of vehicle performance. This paper used the micro genetic algorithm as an optimization method to satisfy above two requirements. The whole T-structure assembly including steering column was used for frequency analysis.

• Computers and Concrete
• /
• v.21 no.5
• /
• pp.505-511
• /
• 2018

This paper investigates the potential of a hybrid model which combines the least squares support vector machine (LSSVM) and an improved particle swarm optimization (IMPSO) techniques for prediction of concrete compressive strength. A modified PSO algorithm is employed in determining the optimal values of LSSVM parameters to improve the forecasting accuracy. Experimental data on concrete compressive strength in the literature were used to validate and evaluate the performance of the proposed IMPSO-LSSVM model. Further, predictions from five models (the IMPSO-LSSVM, PSO-LSSVM, genetic algorithm (GA) based LSSVM, back propagation (BP) neural network, and a statistical model) were compared with the experimental data. The results show that the proposed IMPSO-LSSVM model is a feasible and efficient tool for predicting the concrete compressive strength with high accuracy.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.5 no.5
• /
• pp.877-883
• /
• 2001

In this paper, we propose a new Genetic Algorithm(GA)-based Multiuser Detector(MUD), and its performance is evaluated by computer simulation compared to both the optimum MUD and the Hopfield neural network(NN) -based MUD when the near-far problem exists. From the results of comprehensive simulation, it is shown that the proposed MUD in this paper can guarantee a close BER performance compared to both the optimum MUD and the Hopfield NN MUD with a considerable reduced complexity under the near-far condition. Furthermore, a more performance improvement than the Hopfield W MUD can be expected when the near-far problem does not exist.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2009.01a
• /
• pp.32-37
• /
• 2009

Recently, electronic mail(E-mail) is the most popular communication manner in our society. In such conventional environments, spam increasingly congested in Internet. In this paper, Chinese spam could be effectively detected using text and image features. Using text features, keywords and reference templates in Chinese mails are automatically selected using genetic algorithm(GA). In addition, spam containing a promotion image is also filtered out by detecting the text characters in images. Some experimental results are given to show the effectiveness of our proposed method.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2008.04a
• /
• pp.60-63
• /
• 2008

본 논문에서는 신경망 모델(neural network model)과 유전자 알고리즘(genetic algorithm)을 이용한 실시간 경로 계획(real-time path-planning)과 퍼지 룰(fuzzy rule)을 이용한 효율적인 다중경로계획(multiple path-planning)을 제안한다. 실시간 경로 계획은 빠른 시간 내에 최적 경로의 생성이 반드시 수행되어야 하므로, 본 논문에서는 경로 계획 중 장애물 지역과 비장애물 지역을 빠르게 확인하기 위해 신경망 모델을 이용하여, 이동 방향 및 최적경로 탐색을 위하여 유전자 알고리즘을 이용하였다. 또한 충돌 구역에서의 효율적인 다중 경로 계획을 위해, 퍼지를 이용하여 경로를 재계획 하였다. 퍼지의 경우, 현재 위치에서 목표 지점으로의 방향을 계산하기 위한 퍼지 소속 함수와 현재 위치와 충돌 구역까지의 거리 값을 가중치로 세우고 퍼지 룰을 결정하여 경로계획을 수행하였다. 시뮬레이션을 통해 실험해본 결과, 퍼지 룰을 사용했을 때 사용하지 않았을 때 보다 좋은 성능을 나타남을 확인할 수 있었다.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2006.05a
• /
• pp.563-564
• /
• 2006

In silicon wafer manufacturing process, the grinding process has been adopted to improve the flatness of water. The grinding of wafer is usually used by the infeed grinding machine. Grinding conditions are spindle speed, feed speed, rotation speed, grinding stone etc. But grinding condition selection and analysis is so difficult in grinding machine. In the intelligent grinding system based on knowledge many researchers have studied expert system, neural network, fuzzy etc. In this paper we deal grinding condition selection method, Taguchi method and Genetic Analysis.

• Proceedings of the KIEE Conference
• /
• 2000.07b
• /
• pp.1146-1150
• /
• 2000

We propose a new method to deal with the optimized auto-tuning for the PID controller which is used to the process-control in various fields. First of all, in this method, initial values are determined by the Switched Reluctance Motor of system and Ziegler-Nichols method. After deciding binary strings of parents generation using by the fitness values of genetic algorithms, we perform selection, crossover and mutation to generate the descendant generation. The advantage of this method is better than the neural network and multiple regression model method in characteristic of output, and has extent of applying without limit of initial parameters.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.35S no.12
• /
• pp.27-35
• /
• 1998

In this paper we will develope the immunized recurrent neural network control system with high robustness in dynamically changing environmental conditions. The variation of internal parameters of a system and external(or internal) disturbances can be considered as antigen, and the control input which can be regarded as antibody can be generated against uncertainties. The antibody will be generated from previous control informations and if a antibody for an antigen can not be generated from the corresponding information. the immune system produces another antibody by genetic operations. We apply this concept to a robot manipulator and evaluate the effectiveness of the above proposed system.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.14 no.1
• /
• pp.153-158
• /
• 2006

To optimize the combustion system in a HSDI diesel engine, a new analysis technology was developed. The in-cylinder 3-D combustion analysis was carried out by the modified KIVA-3V, and the spray characteristics for the high pressure injection system were analyzed by HYDSIM. The combustion design parameters were optimized by coupling the KIVA-3V and the iSIGHT. The optimization procedure consists of 3 steps. The $1^{st}$ step is the sampling method by the Design of Experiment(DOE), the $2^{nd}$ step is the approximation using the Neural Network method, and the $3^{rd}$ step is the optimization using the Genetic Algorithm. The developed procedures have been approved as very effective and reliable, and the computational results agree well with the experimental data. The analysis results show that the optimized combustion system in a HSDI diesel engine is capable of reducing NOx and Soot emissions simultaneously keeping a same level of the fuel consumption(BSFC).