• Journal of the Korean Institute of Intelligent Systems
• /
• v.16 no.4
• /
• pp.499-505
• /
• 2006

Regularlization approach to regression can be easily found in Statistics and Information Science literature. The technique of regularlization was introduced as a way of controlling the smoothness properties of regression function. In this paper, we have presented a new method to evaluate linear and non-linear fuzzy regression model based on Tanaka's model using the idea of regularlization technique. Especially this method is a very attractive approach to model non -linear fuzzy data.

• Journal of KSNVE
• /
• v.10 no.3
• /
• pp.531-535
• /
• 2000

A three-parameter model of viscoelastic damper which has a non-linear spring as an element is incorporated into an oscillator. The behavior of the damper model shows non-linear hysteresis curves which is qualitatively similar to those of real viscoelastic materials. The motion is governed by get analytic solutions of the system. The frequency-response curves show that multiple solutions co-exist and that the jump phenomena can occur. In addition it is shown that separate solution branch exists and that it can merge with the primary response curve. Saddle-node bifurcation sets explain the occurences of such non-linear phenomena. A direct time intergration of the original equation of motion validifies the use of the harmonic balance method to this sort of problem.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1997.10a
• /
• pp.115-120
• /
• 1997

System identification is the task of inferring a mathematical description of a dynamic system from a series of measurements of the system. There are several motives for establishing mathematical descriptions of dynamic systems. Typical applications encompass simulation, prediction, fault diagnostics, and control system design. The paper demonstrates that neural networks can be used effective for the identification of nonlinear dynamical systems. The content of this paper concerns dynamic neural network models, where not all inputs to and outputs from the networks are measurable. Only one model type is treated, the well-known Innovation State Space model(Kalman Predictor). The identification is based only on input/output measurements, so in fact a non-linear Extended Kalman Filter problem is solved. Even for linear models this is a non-linear problem without any assurance of convergence, and in spite of this fact an attempt is made to apply the principles from linear models, an extend them to non-linear models. Computer simulation results reveal that the identification scheme suggested are practically feasible.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.17 no.4
• /
• pp.163-172
• /
• 2017

In recent days, the Non-Linear Editing is mainly used in the field of broadcasting. In comparison to conventional editing, Non-Linear Editing can immediately access the image of the desired position and facilitate the insertion and deletion of video frame. Furthermore, it directly apply a title and transition effect to video frame. Moreover, it has an advantage of preview and easy modification in title effect, transition and editing prior to export. However, students who learn Non-Linear Editing first time are not easy to learn it. In this paper, we propose a new learning model based on Reciprocal Peer Teaching (RPT), which helps NLE beginners to understand Non-Linear editing more clearly. We divide the students into two groups i.e. control group and experimental group. The control group students do not apply proposed method while experimental group performs evaluation over our model. Furthermore, we carry out the experiments, which include the overall average of the two groups, academic achievement of students with low grades, standard deviation, T-test and satisfaction surveys. The experimental group shows the superiority in performed experiments and higher satisfaction ratings than the control group.

• The Korean Journal of Applied Statistics
• /
• v.13 no.2
• /
• pp.541-562
• /
• 2000

The generalized linear mixed model framework is for handling count-type categorical data as well as for clustered or overdispersed non-Gaussian data, or for non-linear model data. In this study, we review its general formulation and estimation methods, based on quasi-likelihood and Monte-Carlo techniques. The current research areas and topics for further development are also mentioned.

• Communications for Statistical Applications and Methods
• /
• v.30 no.2
• /
• pp.163-178
• /
• 2023

GARCH-X(1, 1) model specifies that conditional variance follows an AR(1) process and includes a past exogenous variable. This study proposes a new class from that model by allowing a more general (non-linear) variance function to follow an AR(1) process. The functions applied to the variance equation include exponential, Tukey's ladder, and Yeo-Johnson transformations. In the framework of normal and student-t distributions for return errors, the empirical analysis focuses on two stock indices data in developed countries (FTSE100 and SP500) over the daily period from January 2000 to December 2020. This study uses 10-minute realized volatility as the exogenous component. The parameters of considered models are estimated using the adaptive random walk metropolis method in the Monte Carlo Markov chain algorithm and implemented in the Matlab program. The 95% highest posterior density intervals show that the three transformations are significant for the GARCHX(1, 1) model. In general, based on the Akaike information criterion, the GARCH-X(1, 1) model that has return errors with student-t distribution and variance transformed by Tukey's ladder function provides the best data fit. In forecasting value-at-risk with the 95% confidence level, the Christoffersen's independence test suggest that non-linear models is the most suitable for modeling return data, especially model with the Tukey's ladder transformation.

• Transactions of Materials Processing
• /
• v.22 no.6
• /
• pp.303-309
• /
• 2013

Spring-back of MS1470 steel sheets was numerically predicted using a non-linear kinematic hardening material behavior based on the Yoshida-Uemori model. From uniaxial tension and uniaxial tension-compression-tension data as well as the uniaxial tension-unloading-tension data, the parameters of the Yoshida-Uemori model were obtained. For the numerical simulations, the Yoshida-Uemori model was implemented into the commercial finite element program, ABAQUS/Explicit and ABAQUS/Standard using the user-defined material subroutines. The model performance was validated against the measured spring-back from the benchmark problems of NUMISHEET 2008 and NUMISHEET 2011, the 2-D draw bending test and the S-rail forming test, respectively.

• Earthquakes and Structures
• /
• v.4 no.3
• /
• pp.241-264
• /
• 2013

Since the beginning of the twentieth century, the progressive and rapid spread of reinforced concrete (RC) has led to the adoption of mixed masonry-RC solutions, such as the confined masonry. However, together with structures conceived with a definite role for earthquake behaviour, the spreading of RC technology has caused the birth of mixed solutions inspired more by functional aspects than by structural ones, such as: internal masonry walls replaced by RC frames, RC walls inserted to build staircases or raising made from RC frames. Usually, since these interventions rise from a spontaneous build-up, any capacity design or ductility concepts are neglected being designed only to bear vertical loads: thus, the vulnerability assessment of this class becomes crucial. To investigate the non-linear seismic response of these structures, suitable models and effective numerical tools are needed. Among the various modelling approaches proposed in the literature and codes, the authors focus their attention on the equivalent frame model. After a brief description of the adopted model and its numerical validation, the authors aim to point out some specific peculiarities of the seismic response of mixed masonry-RC structures and their repercussions on safety verification procedures (referring in particular way to the non-linear static ones). In particular, the results of non-linear static analyses performed parametrically to various configurations representative of different interventions are discussed.

• Structural Engineering and Mechanics
• /
• v.17 no.6
• /
• pp.751-766
• /
• 2004

This paper extends the use of the hierarchic degenerated shell element to geometric non-linear analysis of composite laminated skew plates by the p-version of the finite element method. For the geometric non-linear analysis, the total Lagrangian formulation is adopted with moderately large displacement and small strain being accounted for in the sense of von Karman hypothesis. The present model is based on equivalent-single layer laminate theory with the first order shear deformation including a shear correction factor of 5/6. The integrals of Legendre polynomials are used for shape functions with p-level varying from 1 to 10. A wide variety of linear and non-linear results obtained by the p-version finite element model are presented for the laminated skew plates as well as laminated square plates. A numerical analysis is made to illustrate the influence of the geometric non-linear effect on the transverse deflections and the stresses with respect to width/depth ratio (a/h), skew angle (${\beta}$), and stacking sequence of layers. The present results are in good agreement with the results in literatures.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2003.11a
• /
• pp.498-503
• /
• 2003

Dynamic analysis of a plate with non-linearity due to large deformation is performed in the study. There have been many researches about the non-linear dynamic behavior of plates examining by means of theoretical or numerical analyses. But it is important how exactly model the actual system. In this respect, the Continuous-Time system identification technique is used to generate non-linear models, for stiffness and damping terms, to explain the observed behaviors with single mode assumptions for the simplicity after comparing the experimental results with the numerical results of a linear plate model.