• Journal of Institute of Control, Robotics and Systems
• /
• v.6 no.1
• /
• pp.98-103
• /
• 2000

This paper suggests a method to recognize the various defect patterns of a cold mill strip using a binary decision tree automatically constructed by a genetic algorithm(GA). In classifying complex patterns with high similarity like the defect patterns of a cold mill stirp, the selection of an optimal feature set and an appropriate recognizer is important to achieve high recognition rate. In this paper a GA is used to select a subset of the suitable features at each node in the binary decision tree. The feature subset with maximum fitness is chosen and the patterns are classified into two classes using a linear decision function. This process is repeated at each node until all the patterns are classified into individual classes. In this way, the classifier using the binary decision tree is constructed automatically. After constructing the binary decision tree, the final recognizer is accomplished by having neural network learning sits of standard patterns at each node. In this paper, the classifier using the binary decision tree is applied to the recognition of defect patterns of a cold mill strip, and the experimental results are given to demonstrate the usefulness of the proposed scheme.

• The KIPS Transactions:PartC
• /
• v.15C no.1
• /
• pp.51-60
• /
• 2008

Micro-mobility protocols have been developed to reduce the control message overhead due to movements of mobile nodes. With the spread of mobile devices, services using mobile nodes are increasing and multicast services are becoming more important in providing multimedia services. In this paper we propose a new multicast protocol suitable for micro-mobility environments. The proposed protocol is designed to maintain optimal multicast routing paths and continue to provide multicast services without disruption in spite of frequent handoffs due to movements of mobile nodes. We used simulation to evaluate the proposed protocol, compared its performance with existing multicast protocols for mobile environments including bi-directional tunneling, remote subscription, and MMA, and observed that the proposed protocol exhibited better performance in terms of transmission success ratio and overhead on the network.

• Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
• /
• 2004.07a
• /
• pp.33-36
• /
• 2004

The process modeling for the growth rate in pulsed laser deposition(PLD)-grown ZnO thin films is investigated using neural networks(NNets) and the process recipes is optimized via genetic algorithms(GAs). D-optimal design is carried out and the growth rate is characterized by NNets based on the back-propagation(BP) algorithm. GAs is then used to search the desired recipes for the desired growth rate. The statistical analysis is used to verify the fitness of the nonlinear process model. This process modeling and optimization algorithms can explain the characteristics of the desired responses varying with process conditions.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2017.05a
• /
• pp.198-198
• /
• 2017

Climate change causes unpredictable and erratic climatic patterns which affects crop production in agriculture and threatens public health. To cope with the challenges of climate change, sustainable and sound growth environment for crop production should be secured. Recent attention has been given to the development of smart irrigation system using sensors and wireless network as a solution to achieve water conservation as well as improvement in crop yield and quality with less water and labor. This study developed the smart irrigation technique for farmlands by monitoring the soil moisture contents and real-time climate condition for decision-making support. Central to this design is micro-controller which monitors the farm condition and controls the distribution of water on the farm. In addition, a series of laboratory studies were conducted to determine the optimal irrigation pattern, one time versus plug time. This smart technique allows farmers to reduce water use, improve the efficiency of irrigation systems, produce more yields and better quality of crops, reduce fertilizer and pesticide application, improve crop uniformity, and prevent soil erosion which eventually reduce the nonpoint source pollution discharge into aquatic-environment.

• ETRI Journal
• /
• v.40 no.6
• /
• pp.736-744
• /
• 2018

This study considers zone-based registration (ZBR), which is adopted by most mobile cellular networks. In ZBR, a user equipment (UE) registers its location area (or zone) in a network database (DB) whenever it enters a new zone. Even though ZBR is implemented in most networks for a UE to keep only one zone (1ZR), it is also possible for a UE to keep multiple zones. Therefore, a ZBR with two zones (2ZR) is investigated, and some mathematical models for 2ZR are presented. With respect to ZBR with three zones (3ZR), several studies have been reported, but these employed computer simulations owing to the complexity of the cases, and there have been no reports on a mathematical 3ZR model to analyze its performance. In this study, we propose a new mathematical model for 3ZR for the first time, and analyze the performance of 3ZR using this model. The numerical results for various scenarios show that, as the UE frequently enters zones, the proposed 3ZR model outperforms 1ZR and 2ZR. Our results help determine the optimal number of zones that a UE keeps, and minimize the signaling cost for radio channels in mobile cellular networks.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2017.05a
• /
• pp.158-158
• /
• 2017

상수관망을 통한 용수 공급에서는 송수펌프, 배수지 등의 수리 시설물이 중요한 역할을 수행한다. 우리나라의 송 배수 방식은 송수펌프를 통해 고지대의 배수지에 물을 확보하고, 이를 자연유하 방식으로 공급하는 것이 일반적이며, 따라서 송 배수시스템의 운영이란 송수펌프의 가동과 그에 따른 배수지의 수위 현황을 관리하는 것을 의미한다. 이 때, 펌프의 가동을 위한 전력소모에 많은 비용이 발생되므로 효율적인 펌프 운영을 위한 최적화 연구의 필요성이 제기되었다. 기존 연구를 통해 송 배수시스템의 운영을 모의하고, 펌프 가동비용을 최소화 하는 실시간 최적 펌프운영 모형이 개발되었으나, 미리 결정된 펌프와 배수지를 바탕으로 송 배수시스템을 모의하기 때문에 계획 및 설계 단계에서 이를 활용할 수 없는 한계점이 존재하였다. 본 연구에서는 최적화 알고리즘 중 하나인 유전자 알고리즘(Genetic Algorithm, GA)을 사용하여, 실시간 펌프운영뿐만 아니라 송수펌프와 배수지의 효율적인 용량을 제시할 수 있는 최적화 모형을 개발하였다. 특히, 개발 모형은 펌프와 배수지의 설계/운영 시, 국내 설계기준, 시설물 비용, 시간별 전력단가 등을 제약조건으로 고려하여 현실적인 결과를 도출할 수 있도록 개발되었다. 본 연구는 실제 운영 중인 S시의 광역상수도 시스템을 바탕으로 개발 모형을 적용하였으며, 또한 송 배수시스템의 계획 및 관리에 활용할 수 있을 것으로 기대된다.

• Journal of Korean Association for Spatial Structures
• /
• v.23 no.3
• /
• pp.87-94
• /
• 2023

Chloride is one of the most common threats to reinforced concrete (RC) durability. Alkaline environment of concrete makes a passive layer on the surface of reinforcement bars that prevents the bar from corrosion. However, when the chloride concentration amount at the reinforcement bar reaches a certain level, deterioration of the passive protection layer occurs, causing corrosion and ultimately reducing the structure's safety and durability. Therefore, understanding the chloride diffusion and its prediction are important to evaluate the safety and durability of RC structure. In this study, the chloride diffusion coefficient is predicted by machine learning techniques. Various machine learning techniques such as multiple linear regression, decision tree, random forest, support vector machine, artificial neural networks, extreme gradient boosting annd k-nearest neighbor were used and accuracy of there models were compared. In order to evaluate the accuracy, root mean square error (RMSE), mean square error (MSE), mean absolute error (MAE) and coefficient of determination (R2) were used as prediction performance indices. The k-fold cross-validation procedure was used to estimate the performance of machine learning models when making predictions on data not used during training. Grid search was applied to hyperparameter optimization. It has been shown from numerical simulation that ensemble learning methods such as random forest and extreme gradient boosting successfully predicted the chloride diffusion coefficient and artificial neural networks also provided accurate result.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.35 no.6
• /
• pp.367-374
• /
• 2022

This papter presents the use of the automatic differential method based on the backpropagation method to obtain the design sensitivity and its application to topology optimization considering the stress constraints. Solving topology optimization problems with stress constraints is difficult owing to singularities, the local nature of stress constraints, and nonlinearity with respect to design variables. To solve the singularity problem, the stress relaxation technique is used, and p-norm for stress constraints is applied instead of local stresses for global stress measures. To overcome the nonlinearity of the design variables in stress constraint problems, it is important to analytically obtain the exact design sensitivity. In conventional topology optimization, design sensitivity is obtained efficiently and accurately using the adjoint variable method; however, obtaining the design sensitivity analytically and additionally solving the adjoint equation is difficult. To address this problem, the design sensitivity is obtained using a backpropagation technique that is used to determine optimal weights and biases in the artificial neural network, and it is applied to the topology optimization with the stress constraints. The backpropagation technique is used in automatic differentiation and can simplify the calculation of the design sensitivity for the objectives or constraint functions without complicated analytical derivations. In addition, the backpropagation process is more computationally efficient than solving adjoint equations in sensitivity calculations.

• Journal of Korea Water Resources Association
• /
• v.30 no.5
• /
• pp.441-447
• /
• 1997

Rainfall observation using rain gage network or satellites includes the sampling error depending on the observation methods or plans. For example, the sampling using rain gages is continuous in time but discontinuous in space, which is nothing but the source of the sampling error. The sampling using satellites is the reverse case that continuous in space and discontinuous in time. The sampling error may be quantified by use of the temporal-spatial characteristics of rainfall and the sampling design. One of recent works on this problem was done by North and Nakamoto (1989), who derived a formulation for estimating the sampling error based on the temporal-spatial rainfall spectrum and the design scheme. The formula enables us to design an optimal rain gage network or a satellite operation plan providing the statistical characteristics of rainfall. In this paper the formula is reviewed and applied for the sampling error problems using several multi-dimensional precipitation models. The results show the limitation of the formulation, which cannot distinguish the model difference in case the model parameters can reproduce similar second order statistics of rainfall. The limitation can be improved by developing a new way to consider the higher order statistics, and eventually the probability density function (PDF) of rainfall.

• Journal of the Korean Society of Hazard Mitigation
• /
• v.9 no.1
• /
• pp.1-7
• /
• 2009

Most developed models are designed to determine pipe diameter, slope and overall layout in order to minimize the cost for the design rainfall for the optimal sewer layout. However, these models are not capable of considering the superposition effect of runoff hydrographs in the sewer pipes. The flow characteristics in the sewer pipes, such as the sewer layout, pipe diameter and slope, vary according to the design of the sewer system. In particular, when the sewer network is modified, the shapes of the runoff hydrographs in the sewer pipes also change because of the superposition effect. In this study, the sewer layout is designed to control and distribute the flows in the sewer pipes, while considering the runoff superposition effect, in order to reduce the inundation risk at each junction. This is accomplished by separating the inflows that enter into each junction by changing the way in which pipes are connected between junctions. And this model combines SWMM (Storm Water Management Model) to perform the hydraulic analysis for the flows in the sewer network. The current sewer layout was modified to minimize the peak outflow at outlet in Garak basin, Seoul, South Korea. As the results, the peak outflows at the outlet were decreased by approximately 20% for the design rainfall during 30 minutes and the total overflows were also decreased for the excessive rainfalls.