• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1996년도 추계학술대회 학술발표 논문집
• /
• pp.227-233
• /
• 1996

The Inverted Pendulum has been one of most popular nonlinear dynamic systems for the exploration of control techniques. This paper presents a new linear optimal control techniques and nonlinear neural network learning methods. The multiayered neural networks are used to add nonlinear effects on the linear optimal regulator(LQR). The new regulator can compensate nonlinear system uncertainties that are not considered in the LQR design, and can tolerated a wider range of uncertainties than the LQR alone. The new regulator has two neural networks for modeling and control. The neural network for modeling is used to obtain a more accurate model than the given mathematical equations. The neural network for control is used to overcome deficiencies by adding corrections to the linear coefficients of the LQR and by adding nonlinear effects on the LQR. Computer simulations are performed to show the applicability and a more robust regulator than the LQR alone.

• 한국정밀공학회지
• /
• 제14권4호
• /
• pp.110-118
• /
• 1997

Multi-layer neural networks with error back-propagation algorithm have a great potential for identifying nonlinear systems with unknown characteristics. However, because they have a demerit that the speed of convergence is too slow, various methods for improving the training characteristics of backpropagition networks have been proposed. In this paper, a fuzzy division method is proposed to improve the convergence speed, which can find out an effective fuzzy division by the tuning of membership function and independently train each neural network after dividing the network model into several parts. In the simulations, the proposed method showed that the optimal fuzzy partitions could be found from the arbitray initial ones and that the convergence speed was faster than the traditional method without the fuzzy division.

• 한국디자인학회:학술대회논문집
• /
• 한국디자인학회 2004년도 추계 학술발표대회 논문집
• /
• pp.230-231
• /
• 2004

• Communications for Statistical Applications and Methods
• /
• 제7권1호
• /
• pp.87-96
• /
• 2000

Nonlinear time series prediction is derived and compared between statistic of modeling and neural network method. In particular mean squared errors of predication are obtained in generalized random coefficient model and generalized autoregressive conditional heteroscedastic model and compared with them by neural network forecasting.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1989년도 한국자동제어학술회의논문집; Seoul, Korea; 27-28 Oct. 1989
• /
• pp.513-519
• /
• 1989

Modeling of the network interface for MAP and its performance analysis is investigated in this study. The parameters for the network interface are selected and a special interest is concentrated on the parameters related to the performance of the network interface itself. A queueing model of the network interface is proposed and simulation is performed to validate the proposed model of the network interface.

• International Journal of Computer Science & Network Security
• /
• 제23권5호
• /
• pp.21-32
• /
• 2023

The design of complex man-made systems mostly involves a conceptual modeling phase; therefore, it is important to ensure an appropriate analysis method for these models. A key concept for such analysis is the development of a diagramming technique (e.g., UML) because diagrams can describe entities and processes and emphasize important aspects of the systems being described. The analysis also includes an examination of ontological concepts such as states and events, which are used as a basis for the modeling process. Studying fundamental concepts allows us to understand more deeply the relationship between these concepts and modeling frameworks. In this paper, we critically analyze the classic definition of a state utilizing the Thinging machine (TM) model. States in state machine diagrams are considered the appropriate basis for modeling system behavioral aspects. Despite its wide application in hardware design, the integration of a state machine model into a software system's modeling requirements increased the difficulty of graphical representation (e.g., integration between structural and behavioral diagrams). To understand such a problem, in this paper, we project (create an equivalent representation of) states in TM machines. As a case study, we re-modeled a state machine of an assembly line system in a TM. Additionally, we added possible triggers (transitions) of the given states to the TM representation. The outcome is a complicated picture of assembly line behavior. Therefore, as an alternative solution, we re-modeled the assembly line based solely on the TM. This new model presents a clear contrast between state-based modeling of assembly line behavior and the TM approach. The TM modeling seems more systematic than its counterpart, the state machine, and its notions are well defined. In a TM, states are just compound events. A model of a more complex system than the one in the assembly line has strengthened such a conclusion.

• International Journal of Control, Automation, and Systems
• /
• 제1권3호
• /
• pp.321-331
• /
• 2003

Experimental software datasets describing software projects in terms of their complexity and development time have been the subject of intensive modeling. A number of various modeling methodologies and modeling designs have been proposed including such approaches as neural networks, fuzzy, and fuzzy neural network models. In this study, we introduce the concept of the Rule-based fuzzy polynomial neural networks (RFPNN) as a hybrid modeling architecture and discuss its comprehensive design methodology. The development of the RFPNN dwells on the technologies of Computational Intelligence (CI), namely fuzzy sets, neural networks, and genetic algorithms. The architecture of the RFPNN results from a synergistic usage of RFNN and PNN. RFNN contribute to the formation of the premise part of the rule-based structure of the RFPNN. The consequence part of the RFPNN is designed using PNN. We discuss two kinds of RFPNN architectures and propose a comprehensive learning algorithm. In particular, it is shown that this network exhibits a dynamic structure. The experimental results include well-known software data such as the NASA dataset concerning software cost estimation and the one describing software modules of the Medical Imaging System (MIS).

• 한국도로학회논문집
• /
• 제19권4호
• /
• pp.1-7
• /
• 2017

PURPOSES : This study aims to improve complex modeling of multivariable, nonlinear, and overdispersion data with an artificial neural network that has been a problem in the civil and transport sectors. METHODS: Deep learning, which is a technique employing artificial neural networks, was applied for developing a large bus fuel consumption model as a case study. Estimation characteristics and accuracy were compared with the results of conventional multiple regression modeling. RESULTS : The deep learning model remarkably improved estimation accuracy of regression modeling, from R-sq. 18.76% to 72.22%. In addition, it was very flexible in reflecting large variance and complex relationships between dependent and independent variables. CONCLUSIONS : Deep learning could be a new alternative that solves general problems inherent in conventional statistical methods and it is highly promising in planning and optimizing issues in the civil and transport sectors. Extended applications to other fields, such as pavement management, structure safety, operation of intelligent transport systems, and traffic noise estimation are highly recommended.

• 한국전자파학회논문지
• /
• 제13권6호
• /
• pp.528-537
• /
• 2002

본 논문에서는 능동소자를 포함하는 마이크로파 회로의 주파수 특성을 해석하기 위하여 확장된 유한차분 시간영역법 (FDTD) 을 이용했다. R, L, C와 같은 집중소자가 전송선로에 삽입된 FDTD 집중소자 모델링을 통해 하이브리드 회로 해석에 대한 기초 연구를 수행하였고, 네트워크 모델링을 이용하여 기생 커패시턴스와 인덕턴스의 값을 추출함으로써 보다 정확한 기생, 방사, 결합까지 고려하는 FDTD만의 고유한 주파수 응답을 확인할 수 있었다. 또한 FDTD를 이용하여 모델링된 다이오드를 사용한 평형 혼합기를 설계하여 상용 회로 시뮬레이터보다 정확하고 실제적인 회로의 주파수 응답을 획득하였다.

• 대한전자공학회논문지TE
• /
• 제37권1호
• /
• pp.1-11
• /
• 2000

본 논문에서는 HEMT의 산란계수와 DC특성을 측정하여 모델링 변수들을 정확하게 추출하는 방법을 제안하였다, HEMT의 소신호 등가회로 모델링 변수들 중 extrinsic 직렬 저항은 측정한 DC특성을 이용하여 FUKUI 방법으로 구하였고, 다른 모델링 변수들은 HP 8510C Network Analyzer를 사용하여 여러 바이어스에서 측정한 S-parameter를 이용하여 변수 값을 결정하였다. 최적화 과정을 거쳐 얻은 등가 회로의 중요한 변수인 gm값은 실제 측정한 gm값과 0.078%오차만을 보인 반면, 제작자가 제공한 데이터를 이용하여 최적화하여 얻은 gm값은 실제 측정한 gm값과 175.38%나 오차를 보였다. 그러므로 반드시 정확하게 측정하여 얻은 초기 값을 가지고 정확한 변수를 측정할 수 있다는 것과 HEMT 모델링 변수들을 추출하는 과정을 자세하게 제시했다.