• Proceedings of the Korea Contents Association Conference
• /
• 2009.05a
• /
• pp.715-719
• /
• 2009

Incorrect deployment of RFID readers occurs reader-to-reader interferences in many applications using RFID technologies. Reader-to-reader interference occurs when a reader transmits a signal that interferes with the operation of another reader, thus preventing the second reader from communicating with tags in its interrogation zone. Interference detected by one reader and caused by another reader is referred to as a reader collision. In RFID systems, the reader collision problem is considered to be the bottleneck for the system throughput and reading efficiency. In this paper, we propose a novel RFID reader anti-collision algorithm based on evolutionary algorithm(EA). First, we analyze characteristics of RFID antennas and build database. Also, we propose EA encoding algorithm, fitness algorithm and genetic operators to deploy antennas efficiently. To show superiority of our proposed algorithm, we simulated our proposed algorithm. In the result, our proposed algorithm obtains 95.45% coverage rate and 10.29% interference rate after about 100 generations.

• Proceedings of the KAIS Fall Conference
• /
• 2009.12a
• /
• pp.715-718
• /
• 2009

The assembly line is one of the typical process hard to analyze with mathematical methods including even stochastic approaches, because it includes many manual operations varying drastically depending on operators' skills. In this paper, we suggest the simulation optimization method to design the optimal assembly line of a gas oven. To achieve the optimal design, firstly, we modeled the real gas oven assembly line with actual data, such as assembly procedures, operation rules, and other input parameters and so on. Secondly, we build some alternatives to enhance the line performance based on business rules and other parameters. The DOE(Design Of Experiment) techniques were used for testing alternatives under various situations. Each alternatives performed optimization process with evolution strategy; one of the GA(Genetic Algorithm) techniques. As a result, we can make about 7% of throughputs up with the same time and cost. By this process, we expect the assembly line can obtain the solution compatible with their own problems.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 2000.04a
• /
• pp.285-288
• /
• 2000

본 연구는 Heuristic 알고리즘 및 유전자알고리즘(GA)을 이용하여 수거(Pickup) 및 배달(Delivery)을 동시에 고려한 통합차량운송계획 모델의 개발이다. 본 연구는 기존의 TSP의 문제를 확장 응용하였으며, 이는 한 Route에서 수거지(Origin)와 운반지(Destination)를 포함하는 수요들을 만족하도록 운반되어야 하는 문제이다. 이러한 통합차량경로계획문제(VRP Vehicle Routing Problem)를 해결하기 위한 접근방법으로 Heuristic 방법을 사용하였으며, 기존의 Saving 알고리즘과 유전자알고리즘(Genetic Algorithm)의 각종 연산자(Operators)들을 계산하여 사용한 TSP문제의 해를 본 연구의 해의 초기해로 사용하였으며 수거 및 배달문제의 특성을 고려하여 해를 구하였다. 본 연구의 결과를 다양한 운송환경에서, 거리산정방법, 가용운송장비 대수, 운송시간의 제한, 물류센터 및 운송지점의 위치 및 수요량 등 다양한 인자들을 고려한 통합시스템으로 프로그램을 개발하고 Sample 문제를 통하여 응용결과를 보였다.

• Proceedings of the IEEK Conference
• /
• 1999.11a
• /
• pp.732-735
• /
• 1999

A GA-based optimization technique is adopted in the paper to obtain optimal future control inputs for predictive control systems. For reliable future predictions of a process, we identify the underlying process with an NNARX model structure and investigate to reduce the volume of neural network based on the Lipschitz index and a criterion. Since most industrial processes are subject to their constraints, we deal with the input-output constraints by modifying some genetic operators and/or using a penalty strategy in the GAPC. Some computer simulations are given to show the effectiveness of the GAPC method compared with the adaptive GPC algorithm.

• Proceedings of the Korean Society of Marine Engineers Conference
• /
• 2005.06a
• /
• pp.274-280
• /
• 2005

The system parameters of gas turbine engine tend to change remarkably in real operating condition. It means that operators have to consider environment and suitably control fuel flow. The conventional PID controller, however, can not guarantee good control performance in the aspect of system parameter change. This paper, therefore, proposes a scheme for integrating PID control and fuzzy technique to obtain the good performance of gas turbine engine speed control on the whole operating range. The effectiveness of the proposed fuzzy PID controller is verified through computer simulation.

• ETRI Journal
• /
• v.33 no.2
• /
• pp.240-250
• /
• 2011

To enable a relevance feedback paradigm to evolve itself by users' feedback, a reinforcement learning method is proposed. The feature space of the medical images is partitioned into positive and negative hypercubes by the system. Each hypercube constitutes an individual in a genetic algorithm infrastructure. The rules take recombination and mutation operators to make new rules for better exploring the feature space. The effectiveness of the rules is checked by a scoring method by which the ineffective rules will be omitted gradually and the effective ones survive. Our experiments on a set of 10,004 images from the IRMA database show that the proposed approach can better describe the semantic content of images for image retrieval with respect to other existing approaches in the literature.

• The Journal of the Korea Contents Association
• /
• v.9 no.10
• /
• pp.67-74
• /
• 2009

Incorrect deployment of RFID readers occurs reader-to-reader interferences in many applications using RFID technologies. Reader-to-reader interference occurs when a reader transmits a signal that interferes with the operation of another reader, thus preventing the second reader from communicating with tags in its interrogation zone. Interference detected by one reader and caused by another reader is referred to as a reader collision. In RFID systems, the reader collision problem is considered to be the bottleneck for the system throughput and reading efficiency. In this paper, we propose a novel RFID reader anti-collision algorithm based on evolutionary algorithm(EA). First, we analyze characteristics of RFID antennas and build database. Also, we propose EA encoding algorithm, fitness algorithm and genetic operators to deploy antennas efficiently. To show superiority of our proposed algorithm, we simulated our proposed algorithm. In the result, our proposed algorithm obtains 95.45% coverage rate and 10.29% interference rate after about 100 generations.

• Smart Media Journal
• /
• v.9 no.3
• /
• pp.31-40
• /
• 2020

Currently, black-box-based machine learning algorithms are used to analyze big data in manufacturing. This algorithm has the advantage of having high analytical consistency, but has the disadvantage that it is difficult to interpret the analysis results. However, in the manufacturing industry, it is important to verify the basis of the results and the validity of deriving the analysis algorithms through analysis based on the manufacturing process principle. To overcome the limitation of explanatory power as a result of this machine learning algorithm, we propose a manufacturing big data analysis method using genetic programming. This algorithm is one of well-known evolutionary algorithms, which repeats evolutionary operators such as selection, crossover, mutation that mimic biological evolution to find the optimal solution. Then, the solution is expressed as a relationship between variables using mathematical symbols, and the solution with the highest explanatory power is finally selected. Through this, input and output variable relations are derived to formulate the results, so it is possible to interpret the intuitive manufacturing mechanism, and it is also possible to derive manufacturing principles that cannot be interpreted based on the relationship between variables represented by formulas. The proposed technique showed equal or superior performance as a result of comparing and analyzing performance with a typical machine learning algorithm. In the future, the possibility of using various manufacturing fields was verified through the technique.

• Journal of the Korean Institute of Telematics and Electronics D
• /
• v.36D no.7
• /
• pp.56-65
• /
• 1999

In this paper, a pixelated binary phase grating to generate $5{\times}5$ spots in designed using simple Genetic Algorithm(sGA) composed of selection, crossover, and mutation operators, and it can be applied for the optical interconnection. So as to adapt that GA is a robust and efficient schema, a chromosome is coded as a binary integer of length $32{\times}32$, the ranking method for decreasing the stochastic sampling error is performed, and a single-point crossover having $16{\times}16$ block size is used. A designed grating when the probabillty of mutation is 0.001, the probability of crossover is 0.75 and the population size is 300 has a 74.7[%] high diffraction efficiency and a $1.73{\times}10^{-1}$ uniformity quantitatively.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.45 no.2
• /
• pp.127-136
• /
• 2008

This paper proposes the efficient system for automatic design of FSS(Frequency Selective Surface) with periodic pattern and frequency characteristics specified by operator. The proposed system derives optimal design parameters through tool for analysis of FSS with arbitrary pattern, DB(Data Base) implemented from limited simulation and measurement data of FSS, and GA(Genetic Algorithm) for optimizing design parameters. FSS analysis tool consists of two analysis tools. One is the simulator for analysis of monolayer FSS that using moment method, another is the tool with approximated analysis method of FSS with dielectric layer. Given pattern configuration and characteristics specified by operators, the DB system searches the best matching FSS, and provides initial genes to GA from the searched parameters, which drastically reduces running time of GA for finding the FSS design parameters. In this paper, the proposed design system is verified through simulation and measurement about FSS with various patterns.