• 한국융합학회논문지
• /
• 제10권2호
• /
• pp.13-20
• /
• 2019

맞춤형 교육을 위해 학습자에 맞는 학습 경로를 탐색하는 것은 필수적이다. 유전 알고리즘은 해공간이 매우 커서 결정적 방법으로 해를 구하기 어려울 때 타당한 시간 내에 최적해를 찾게 해준다. 본 연구는 유전 알고리즘을 이용하여 200개 코드를 가진 악보 27개를 대상으로 학습자 부담을 최소화하고 단계별 학습량을 균등하게 분산함으로써 학습 효과를 최대화 할 수 있도록 학습 경로를 최적화하였다. 학습 컨텐츠가 27개만 되어도 학습 경로의 순열 크기는 $10^{28}$을 넘지만, 본 연구에서 구현한 도구로 평균 20분 이내에 최적해를 구할 수 있었다. 실험 결과는 유전 알고리즘이 다양한 목적의 맞춤형 교육을 위한 복잡한 학습 경로 설계에 효과적임을 보여주었다. 제안한 방법은 다른 교육 도메인에도 활용할 수 있을 것으로 기대된다.

• 전기학회논문지
• /
• 제62권5호
• /
• pp.705-711
• /
• 2013

In this paper, we introduce an design of multi-output fuzzy neural networks based on Interval Type-2 fuzzy set. The proposed Interval Type-2 fuzzy set-based fuzzy neural networks with multi-output (IT2FS-based FNNm) comprise the network structure generated by dividing the input space individually. The premise part of the fuzzy rules of the network reflects the individuality of the division space for the entire input space and the consequent part of the fuzzy rules expresses three types of polynomial functions with interval sets such as constant, linear, and modified quadratic inference for pattern recognition. The learning of fuzzy neural networks is realized by adjusting connections of the neurons in the consequent part of the fuzzy rules, and it follows a back-propagation algorithm. In addition, in order to optimize the network, the parameters of the network such as apexes of membership functions, uncertainty factor, learning rate and momentum coefficient were automatically optimized by using real-coded genetic algorithm. The proposed model is evaluated with the use of numerical experimentation.

• 한국음향학회지
• /
• 제31권1호
• /
• pp.51-61
• /
• 2012

본 연구에서는 등각, 등간격 및 측지선 돔 (geodesic dome)형태로 배열된 곡면 배열 트랜스듀서에 대해서, 음원 간격, 음원 개수 등과 같은 배열 구조 변수들에 따른 방사패턴의 변화 경향성을 분석하였다. 또한 그 결과를 바탕으로 통계적 기법인 다중 회귀 분석을 이용하여 부엽의 크기 및 빔 폭을 설계 변수들의 함수로 도출하였다. 나아가 최적화 기법인 GA (genetic algorithm)법을 이용하여 각 방향에 대한 빔폭이 주어진 조건을 만족하며 가장 작은 부엽의 크기를 가지도록 설계 변수들의 최적화를 수행하였다. 최적화 결과를 바탕으로 세 가지 곡면 배열 구조 가운데 곡면 배열 트랜스듀서의 최적 배열 구조로 등간격 배열구조를 선정하였다.

• 한국전자파학회논문지
• /
• 제16권1호
• /
• pp.40-48
• /
• 2005

본 논문에서는 NEC 코드와 Pareto 유전자 알고리즘 최적화 기법을 이용하여 초소형 유도결합 안테나를 설계하였다. 최적화된 유도결합 안테나 중 몇 가지 표본을 제작하고 성능을 측정하였다. 일반적으로 안테나의 크기가 작아질수록 입력 저항, 대역폭 및 효율이 감소하는데 비하여 제안된 방법으로 설계된 유도결합 안테나는 다른 부가적인 정합회로 없이 우수한 성능을 보인다. 간단한 회로 모델을 도입하여 제안된 유도결합 안테나의 동작원리를 설명하였고, Duroid 기판 위에 평면 구조로 제작하여 RFID 태그 안테나로써 성능을 입증하였다.

• Wind and Structures
• /
• 제18권3호
• /
• pp.253-265
• /
• 2014

The platform and floating structure of spar type offshore wind turbine systems should be designed in order for the 6-DOF motions to be minimized, considering diverse loading environments such as the ocean wave, wind, and current conditions. The objective of this study is to optimally design the platform and substructure of a 3MW spar type wind turbine system with the maximum postural stability in 6-DOF motions as well as the minimum material cost. Therefore, design variables of the platform and substructure were first determined and then optimized by a hydrodynamic analysis. For the hydrodynamic analysis, the body weight of the system was considered, and the ocean wave conditions were quantified to the wave forces using the Morison's equation. Moreover, the minimal number of computation analysis models was generated by the Design of Experiments (DOE), and the design variables of the platform and substructure were finally optimized by using a genetic algorithm with a neural network approximation.

• International Journal of Aeronautical and Space Sciences
• /
• 제7권1호
• /
• pp.106-117
• /
• 2006

The active vibration control of composite shell structure has been performed with the optimized sensor/actuator system. For the design of sensor/actuator system, a method based on finite element technique is developed. The nine-node Mindlin shell element has been used for modeling the integrated system of laminated composite shell with PVDF sensor/actuator. The distributed selective modal sensor/actuator system is established to prevent the effect of spillover. Electrode patterns and lamination angles of sensor/actuator are optimized using genetic algorithm. Continuous electrode patterns are discretized according to finite element mesh, and orientation angle is encoded into discrete values using binary string. Sensor is designed to minimize the observation spillover, and actuator is designed to minimize the system energy of the control modes under a given initial condition. Modal sensor/actuator for the first and the second mode vibration control of singly curved cantilevered composite shell structure are designed with the method developed on the finite element method and optimization. For verification, the experimental test of the active vibration control is performed for the composite shell structure. Discrete LQG method is used as a control law.

• 한국소음진동공학회:학술대회논문집
• /
• 한국소음진동공학회 2003년도 춘계학술대회논문집
• /
• pp.1205-1205
• /
• 2003

Rotary compressors are one of the most important parts of air-conditioners in the industry This device usually has noise problems during the circulation process of the refrigerant and muffler is used for the noise reduction. The acoustic performance of the muffler depends on its shape and its hole locations on the upper surface. Therefore finding the optimum location of the muffler holes is a topic of increasing importance in the compressor industry. In this research the optimization of the muffler hole locations and the importance of the resonator cavity on the lower surface of the muffler in acoustic point of view is studied. At first, the topology optimization for the 2 hole muffler is performed based on a model without resonator cavity by using genetic algorithm. The 2 hole muffler's acoustic analysis and experiment results are matching, however, the optimized model's results are not. By adding the resonator cavity and also by changing the cavity shape, the acoustic analysis and experiment result comparison is Performed for different cavity shapes. The topology optimization of the revised model with cavity is carried out for noise reduction. Finally, the optimized design is produced and tested for validation.

• Nuclear Engineering and Technology
• /
• 제39권4호
• /
• pp.337-348
• /
• 2007

A fuzzy neural network model is presented to predict residual stress for dissimilar metal welding under various welding conditions. The fuzzy neural network model, which consists of a fuzzy inference system and a neuronal training system, is optimized by a hybrid learning method that combines a genetic algorithm to optimize the membership function parameters and a least squares method to solve the consequent parameters. The data of finite element analysis are divided into four data groups, which are split according to two end-section constraints and two prediction paths. Four fuzzy neural network models were therefore applied to the numerical data obtained from the finite element analysis for the two end-section constraints and the two prediction paths. The fuzzy neural network models were trained with the aid of a data set prepared for training (training data), optimized by means of an optimization data set and verified by means of a test data set that was different (independent) from the training data and the optimization data. The accuracy of fuzzy neural network models is known to be sufficiently accurate for use in an integrity evaluation by predicting the residual stress of dissimilar metal welding zones.

• Journal of Information Processing Systems
• /
• 제18권3호
• /
• pp.374-388
• /
• 2022

Database systems usually have many parameters that must be configured by database administrators and users. RocksDB achieves fast data writing performance using a log-structured merged tree. This database has many parameters associated with write and space amplifications. Write amplification degrades the database performance, and space amplification leads to an increased storage space owing to the storage of unwanted data. Previously, it was proven that significant performance improvements can be achieved by tuning the database parameters. However, tuning the multiple parameters of a database is a laborious task owing to the large number of potential configuration combinations. To address this problem, we selected the important parameters that affect the performance of RocksDB using random forest. We then analyzed the effects of the selected parameters on write and space amplifications using analysis of variance. We used a genetic algorithm to obtain optimized values of the major parameters. The experimental results indicate an insignificant reduction (-5.64%) in the execution time when using these optimized values; however, write amplification, space amplification, and data processing rates improved considerably by 20.65%, 54.50%, and 89.68%, respectively, as compared to the performance when using the default settings.

• 한국항행학회논문지
• /
• 제27권5호
• /
• pp.502-509
• /
• 2023

본 논문는 유전자 알고리즘의 최적화 기법을 활용하여 최적의 재방문 성능을 달성하는 위성배치 방법을 제시한다. 보편적인 위성배치 기법인 Walker 방법은 글로벌 커버리지 개념으로 한반도의 전략적 환경을 고려한 표적 중심의 위성배치에는 제한사항이 존재한다. 이러한 제한사항을 극복하기 위하여, 북한의 주요 관심지역의 표적을 설정하고 표적별 최적의 재방문 성능을 갖는 궤도 요소를 탐색하여 이를 기반으로 각 표적에 대해 유전자 알고리즘으로 최적화된 위성수를 도출하였다. 연구 결과는 지상반복궤적의 위성배치 규칙을 적용하여 최적화된 위성군이 표적별 원하는 재방문 성능을 달성함으로써 그 성능이 입증된다.