• 응용통계연구
• /
• 제15권2호
• /
• pp.311-321
• /
• 2002

시계열 자료의 전이함수분석에 있어서 조건부 이분산성을 도입하고 기존의 선형 이분산모형인 Engle(1982)의 ARCH 모형과 더불어 비선형 모형인 베타-ARCH 및 분계점-ARCH모형을 고려하였다. 모형적합절차를 간략히 소개하였으며 제안된 모형을 미국 나스닥지수와 국내 종합주가지수에 적용시켜본 결과 비선형 ARCH 모형이 우수함을 알 수 있었다.

• 대한수학회지
• /
• 제45권3호
• /
• pp.631-644
• /
• 2008

In this paper, we present a new method for solving a nonlinear two-point boundary value problem with finitely many singularities. Its exact solution is represented in the form of series in the reproducing kernel space. In the mean time, the n-term approximation $u_n(x)$ to the exact solution u(x) is obtained and is proved to converge to the exact solution. Some numerical examples are studied to demonstrate the accuracy of the present method. Results obtained by the method are compared with the exact solution of each example and are found to be in good agreement with each other.

• 전자공학회논문지B
• /
• 제32B권5호
• /
• pp.812-820
• /
• 1995

This paper proposes an approach of identifying nonlinear mappings from input/output data. The approach is based on the universal approximation by the fuzzy integration of local affine mappings. A connectionist model realizing the universal approximator is suggested by using a processing unit based on both the radial basis function and the weighted sum scheme. In addition, a learning method with self-organizing capability is proposed for the identifying of nonlinear mapping relationships with the given input/output data. To show the effectiveness of our approach, the proposed model is applied to the function approximation and the prediction of Mackey-Glass chaotic time series, and the performances are compared with other approaches.

• 대한의용생체공학회:학술대회논문집
• /
• 대한의용생체공학회 1998년도 추계학술대회
• /
• pp.195-196
• /
• 1998

Nonlinear energy operator(NEO) is usually used to estimate energy content of linear oscillator. We applied the modified nonlinear energy operator (MNEO) to detect R-peak of ECG and analyzed variation of R-R interval during sleep with nonlinear methods, piecewise correlation dimension and approximate entropy (ApEn) which estimate complexity of time series. ApEn applied to R-R interval reveals trends as sleep state changes.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2000년도 하계학술대회 논문집 D
• /
• pp.3004-3006
• /
• 2000

In this paper, we propose an optimal design method of Fuzzy-Neural Networks model with parallel structure for complex and nonlinear systems. The proposed model is consists of a multiple number of FNN connected in parallel. The proposed FNNs with parallel structure is based on Yamakawa's FNN and it uses simplified inference as fuzzy inference method and Error Back Propagation Algorithm as learning rules. We use a HCM clustering and GAs to identify the structure and the parameters of the proposed model. Also, a performance index with a weighting factor is presented to achieve a sound balance between approximation and generalization abilities of the model. To evaluate the performance of the proposed model. we use the time series data for gas furnace and the numerical data of nonlinear function.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1995년도 하계학술대회 논문집 B
• /
• pp.804-806
• /
• 1995

This paper discusses Self-organized Distributed Networks(SODN) as identifier of nonlinear dynamical systems. The structure of system identification employs series-parallel model. The identification procedure is based on a discrete-time formulation. The learning with the proposed SODN is fast and precise. Such properties arc caused from the local learning mechanism. Each local networks learns only data in a subregion. Large number of memory requirements and low generalization capability for the untrained region, which are drawbacks of conventional local network learning, are overcomed in the SODN. Through extensive simulation, SODN is shown to be effective for identification of nonlinear dynamical systems.

• 한국통신학회논문지
• /
• 제22권4호
• /
• pp.696-705
• /
• 1997

This paper presents an efficient adaptive predistortion technique compensating linear and nonlinear distortions caused by high-power amplifier (HPA) with memory in OFDM systems. The efficient adaptive data predistortion techniques proposed for compensation of HPA with memory in single carrier systems cannot be applied to OFDM systems since the possible input levels for HPA is infinite in OFDM systems. Also, previous adaptive predistortion techniques, based on Volterra series modeling, are not suitable for real-time implementation due to high computational burden and slow convergence rate. In the proposed approach, the memoryless HPA preceded by a linear filter in OFDM systems is modeled by the Wiener system which is then precompensated by the proposed adaptive predistorter with a minimum number of filter taps. An adaptive algorithm for adjusting the proposed adaptive predistorter is derived using the stochastic gradient method. It is demonstrated by computer simulation that the performance of OFDM system suffering from nonlinear distortion can be greatly improved by the proposed efficient adaptive predistorter using a small number of filter taps.

• 한국조명전기설비학회지:조명전기설비
• /
• 제9권6호
• /
• pp.49-56
• /
• 1995

In this study, self-tuning adaptive control using state observer is developed. Self-tuning adaptive controller that estimates the parameters of the system in real time and generates the optimal control signals has robust characteristic about varying load and external disturbances. In addition, state observer without sensors is applied, thus the control can be performed more quickly and exactly. Since chopper is used commonly in practical drives, the characteristics of the chopper are included in state observer algorithm, which, in turn, makes the system exact estimation. Since series type DC motor has nonlinear models, linearizing approach are investigated. to realize the proposed algorithm it requires fast calculation in real time. TMS320C31, digital signal processor, is applied to realized the adaptive control algorithms.

• Earthquakes and Structures
• /
• 제16권3호
• /
• pp.311-320
• /
• 2019

Obelisks are historical monuments. There are several obelisks dating from ancient Egyptian period, located around various parts of the world. The city of Istanbul is a home to the Obelisk of Theodosius at the Hippodrome. Due to the expectation of a large event in the near future, the evaluation of seismic response of the Obelisk gets importance. Therefore, in this study structural dynamic behavior of the Obelisk was investigated using discrete element approach. Nonlinear dynamic analyses were performed using real and synthetic time series. Real and synthetic ground motions analyzed from this study seems consistent with the earthquake hazard levels that would be expected at the site of the Obelisk in the occurrence of an event of moment magnitude above 7.0 near Istanbul. Results are evaluated in terms of variation of displacement, relative displacement of adjacent blocks, normal stress and shear stress in time.

• 한국의학물리학회지:의학물리
• /
• 제8권1호
• /
• pp.75-82
• /
• 1997

인체의 생리기관의 운동은 매우 복잡하고 불규칙적인 운동을 보이고 있다. 특히 말초 혈관의 운동은 매우 민감하고 복잡한 운동특성을 보이고 있다. 그중에서도 당 (glucose)에 의한 운동은 매우 민감한 변화의 운동을 반응한다. 이런 운동을 분석하기에는 기존의 선형적인 분석방법으로 복잡한 혈류운동을 분석하고 예측하기에는 많은 문제점을 가지고 있다. 그래서 비선형적 운동계의 분석방법인 카오스이론의 시계열분석방법으로 분석하는 것이 적합하다. 이런 맥락으로 본 연구는 당의 주입에 의한 토끼의 말초혈류량의 스칼라적 데이터를 획득하여 시계열분석방법으로 다차원의 벡터로 재정의하여 말초혈관의 혈류운동이 카오스적 운동임을 재확인하고 비선형적분석방법의 적합성을 확인하고자 하였다. 그 결과 당 주입에 따른 혈당치의 변화에 따라 기존의 주파수분석 및 평균치분석에서 차이가 나타나지 않았지만 비선형적분석방법으로 분석한 결과 그 차이를 확인할수 있었고, 말초 혈류의운동이 카오스적현상을 보임을 확인하였다.