• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1997년도 하계학술대회 논문집 B
• /
• pp.739-742
• /
• 1997

This paper proposes the structure and parameter optimization technique of fuzzy neural networks using genetic algorithm. Fuzzy neural network has advantages of both the fuzzy inference system and neural network. The determination of the optimal parameters and structure of the fuzzy neural networks, however, requires special efforts. To solve these problems, we propose a new learning method for optimization of fuzzy neural networks using genetic algorithm. It can optimize the structure and parameters of the entire fuzzy neural network globally. Numerical example is provided to show the advantages of the proposed method.

• Advances in nano research
• /
• 제11권6호
• /
• pp.641-648
• /
• 2021

In this article, the dynamic parameters (frequencies, mode shapes, damping ratios) of the scaled concrete structure and the dynamic parameters (frequencies, mode shapes, damping ratios) of the entire outer surface of titanium dioxide, 80 micron in thickness are compared using operational modal analysis method. Ambient excitation was provided from micro tremor ambient vibration data on ground level. Enhanced Frequency Domain Decomposition (EFDD) was used for the output only modal identification. From this study, a good correlation between mode shapes was found. Titanium dioxide applied to the entire outer surface of the scaled concrete structure has an average of 11.78% difference in frequency values and 10.15% in damping ratios, proving that nanomaterials can be used to increase rigidity in structures, in other words, for reinforcement. Another important result determined in the study was the observation of the adherence of titanium dioxide and similar nanomaterials mentioned in the introduction to concrete structure surfaces was at the highest level.

• 한국전자통신학회논문지
• /
• 제3권4호
• /
• pp.276-281
• /
• 2008

배전계통은 여러 가지 이유로 잦은 고장을 경험하기 때문에 고장위치 추정은 전력공급 신뢰도 측면에서 매우 중요하다. 그렇지만 배전계통은 주 선로에서 분기되는 3상 및 단상 분기선을 가지는 수지상 구조로 설계되며 각 구간 상에 수개의 로드 탭을 가지기 때문에 고장점 표정이 어렵다. 따라서 본 연구에서는 기존의 전력계통 고장점 표정기법에 대해서 조사, 분석하여 배전자동화시스템의 중앙제어장치에서 효과적으로 실행할 수 있는 고장거리 계산 기법을 결정한다. 그리고 EMTP 모의 결과를 통해 결정된 방법의 유효성을 검증한다.

• Journal of Mechanical Science and Technology
• /
• 제19권8호
• /
• pp.1529-1543
• /
• 2005

Recently an unmanned aerial vehicle (UAV) has been widely used for military and civil applications. The role of a navigation system in the UAV is to provide navigation data to the flight control computer (FCC) for guidance and control. Since performance of the FCC is highly reliant on the navigation data, a fault in the navigation system may lead to a disastrous failure of the whole UAV. Therefore, the navigation system should possess a fault detection and isolation (FDI) algorithm. This paper proposes an attitude determination GPS/INS integrated navigation system with an FDI algorithm for a UAV. Hardware for the proposed navigation system has been developed. The developed hardware comprises a commercial inertial measurement unit (IMU) and the integrated navigation package (INP) which includes an attitude determination GPS (ADGPS) receiver and a navigation computer unit (NCU). The navigation algorithm was implemented in a real-time operating system with a multi-tasking structure. To evaluate performance of the proposed navigation system, a flight test has been performed using a small aircraft. The test results show that the proposed navigation system can give accurate navigation results even in a high dynamic environment.

• 통상정보연구
• /
• 제6권1호
• /
• pp.51-74
• /
• 2004

The virtual space of internet has changed the existed market structure as more and more internet users have highly increased. And this situation has given a golden opportunity to the internet service firms that are supposed to meet their customers through the internet web sites. So, it is becoming a critical issues to construct and keep better web sites than their competitors to the internet service firms. This paper is intented as an investigation of determination factors of internet web site quality further, which of them are more important factors to the consumer satisfaction. For this purpose, empirical approach using factor analysis, regression analysis was used to develop dimensions of internet web site quality and to explore more important factors that internet service firms should choice to have competitiveness. Empirical results of the study presented that the determination factors of internet web site quality were composed of five factors like Responsiveness, Accessibility, Ease of use, System Performance, Communication. And we found that Communication and Ease of use are more important factors than other ones. Therefore, the internet service firms that are plan to have more competitiveness than their competitors should choice these important factors and concentrate on these ones to build excellent internet web sites.

• 한국공간구조학회논문집
• /
• 제24권2호
• /
• pp.83-90
• /
• 2024

Machine learning is widely applied to various engineering fields. In structural engineering area, machine learning is generally used to predict structural responses of building structures. The aging deterioration of reinforced concrete structure affects its structural behavior. Therefore, the aging deterioration of R.C. structure should be consider to exactly predict seismic responses of the structure. In this study, the machine learning based seismic response prediction model was developed. To this end, four machine learning algorithms were employed and prediction performance of each algorithm was compared. A 3-story coupled shear wall structure was selected as an example structure for numerical simulation. Artificial ground motions were generated based on domestic site characteristics. Elastic modulus, damping ratio and density were changed to considering concrete degradation due to chloride penetration and carbonation, etc. Various intensity measures were used input parameters of the training database. Performance evaluation was performed using metrics like root mean square error, mean square error, mean absolute error, and coefficient of determination. The optimization of hyperparameters was achieved through k-fold cross-validation and grid search techniques. The analysis results show that neural networks and extreme gradient boosting algorithms present good prediction performance.

• 수산경영론집
• /
• 제46권2호
• /
• pp.1-11
• /
• 2015

Due to the environmental changes such as decreasing and aging fishing population and increasing imported marine products, improvement of fishing business competitiveness has become one of important issues. This study aimed to analyze the coastal fishing business units in Busan region and compare their business performances in order to find out success factors. The logistic regression analysis between 4 determination factors of competitiveness and business performances showed that the ship tonnage in the factor conditions, catch of species of fishing types'kg per price in the demand conditions, cooperative sales ratio in the related & supporting industries, and net per cost in the firm strategy, and structure & rivalry had the positive(+) impacts on business performances.

• 물과 미래
• /
• 제12권1호
• /
• pp.60-71
• /
• 1979

In general, the lock structure is built at place of having great deal range for dealing with effective ships operation such as in the west coast of Korea. In Inchon harbour, the two locks of 10 KT and 50 KT tonnage class in total has been constructed for several years age, however, it has been recorded many waiting vessels at outer harbour due to the increment of oceangoing vessels & shortage of berthing facilities in accordance with beyond expectation of cargo amount increment. This paper attempts to solves the waiting vessels problem at outer harbour by simulation in applying queing theory. It is found that the simulation results such as average queue time, service time, and queue length during lock operation can be applied to find the minimum of the cost function for determination of optimum Lock Size

• Journal of Astronomy and Space Sciences
• /
• 제15권1호
• /
• pp.111-118
• /
• 1998

A method to determine normal vectors for boundaries of plasmas with a series of data acquired from a single spacecraft is investigated. The determination of the normal vector is possible through a set of Rankine-Hugoniot(R-H) relations that are conser-vation relations of plasmas across a boundary. It is assumed that the boundary is planar and that the structure of the boundary is not varing in the rest frame of plasmas. The present method utilizes a complete set of R-H relations and provieds self-consistent predictions of the plasma densities, bulk velocities, and temperatures a s well as mag-netic fields. It is expected that the present method provides a more accurate normal vector than the previous methods which employ only subsets of the available R-H relations.

• 한국전기전자재료학회:학술대회논문집
• /
• 한국전기전자재료학회 2002년도 하계학술대회 논문집
• /
• pp.236-239
• /
• 2002

The electron-atom collision studies has been essentially use\ulcorner for testing and developing suitable theories of the scattering and collision processes, and for providing a tool for obtaining detailed information on the structure of the target atoms and molecules and final collision products. And, the development of that has also been strongly motivated by the need for electron collision data in such fields as laser physic and development, astrophysics, plasma devices, upper atmospheric processes and radiation physics. Therefore, we explains the concept and the principle of determination of the electron collision cross sections for atoms and molecules by using the present electron swarm method.