• Communications for Statistical Applications and Methods
• /
• v.7 no.1
• /
• pp.97-106
• /
• 2000

In time series analysis we generally use Box-Cox power transformation for variance stabilization. In this paper we show that order estimator and one step ahead forecast of transformed AR(1) model are approximately invariant to those of the original model under some assumptions. A small Monte-Carlo simulation is performed to support the results.

• Communications for Statistical Applications and Methods
• /
• v.2 no.2
• /
• pp.115-125
• /
• 1995

This paper deals with the Bayesian estimation for the NLAR(1) model with Laplacian marginals. Assuming the independent uniform priors for two parameters of the NLAT(1) model, the griddy Gbbs sampler by Ritter and Tanner(1992) is used to obtain the Bayesian estimates. Random numbers generated form the uniform priors ate used as the grids for each parameter. Some simulations are conducted and compared with the maximum likelihood estimation result.

• Journal of the Korean Statistical Society
• /
• v.21 no.1
• /
• pp.47-58
• /
• 1992

The autocorrelation function structures of bilinear time series model BL(p, q, r, s), $r \geq s$ are obtained and shown to be analogous to those of ARMA(p, l), l=max(q, s). Simulation studies are performed to investigate the adequacy of Akaike information criteria for identification between ARMA(p, l) and BL(p, q, r, s) models and for determination of orders of BL(p, q, r, s) models. It is suggested that the model of having minimum Akaike information criteria is selected for a suitable model.

• Proceedings of the Korean Society for Technology of Plasticity Conference
• /
• 2002.05a
• /
• pp.173-176
• /
• 2002

Viscoplastic deformation and sheet forming behavior of multicomponent Zr-based bulk metallic glass alloy has been investigated. From a series of mechanical test results, basic processing maps based on Dynamic Materials Model have been constructed to establish feasible forming conditions. Stamping in laboratory scale was then performed at the various stroke speeds and temperatures using a hydraulic press. Failure in macroscopic level was examined to check the validity of constructed processing maps.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1993.06a
• /
• pp.1238-1241
• /
• 1993

A fuzzy mathematical model is presented that can be applied to support the inspection of organizations by an internal or external evaluation group. The model offers the opportunity to deal with the situation of common practice in which such evaluations are considered as a time series rather than single events. A hypothetical but realistic example is given to illustrate the computational procedure involved.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1993.06a
• /
• pp.1013-1016
• /
• 1993

This paper describes a new type of neuron model, the inputs of which are interfered with one another. It has a high mapping ability with only single unit. The learning speed is considerably improved compared with the conventional linear type neural networks. The proposed neuron model was successfully applied to the prediction problem of chaotic time series signal.

• Journal of Microbiology and Biotechnology
• /
• v.11 no.5
• /
• pp.776-780
• /
• 2001

Based on the static and dynamic adsorption of Streamline DEAE, a modified tank-in-series model including particle size distribution was used to describe the adsorption performance of bovine serum albumin in an expanded bed. The calculated results indicated that the suggested model was able to simulate breakthrough curves under various conditions.

• Membrane and Water Treatment
• /
• v.9 no.5
• /
• pp.373-383
• /
• 2018

Fouling by solids and microorganisms is the major obstacle limiting the efficient use of membrane wastewater treatment. In our previous study, two stages microalgae/membrane filtration system was proposed to treat anaerobic digested palm oil mill effluent (AnPOME). This two stages microalgae/membrane filtration system had showed great potential for the treatment of AnPOME with high removal of COD, $NH_3-N$, $PO_4{^{3-}}$, TSS, turbidity, and colour. However, fouling behavior of the membrane in this two stages microalgae/membrane filtration system was still unknown. In this study, empirical models that describe permeate flux decline for dead-end filtration (pore blocking - complete, intermediate, and standard; and cake layer formation) presented by Hermia were used to fit the experimental results in identifying the fouling mechanism under different experimental conditions. Both centrifuged and non-centrifuged samples were taken from the medium with 3 days RT intervals, from day 0 to day 12 to study their influence on fouling mechanisms described by Hermia for ultrafiltration (UF), nanofiltration (NF), and reverse osmosis (RO) filtration mode. Besides, a more detailed study on the use of resistance-in-series model for deadend filtration was done to investigate the fouling mechanisms involved in membrane filtration of AnPOME collected after microalgae treatment. The results showed that fouling of UF and NF membrane was mainly caused by cake layer formation and it was also supported by the analysis for resistance-in-series model. Whereas, fouling of RO membrane was dominated by concentration polarization.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.53 no.1
• /
• pp.40-49
• /
• 2004

In this paper, we propose a new architecture of Genetic Algorithms(GAs)-based Self-Organizing Polynomial Neural Networks(SOPNN), discuss a comprehensive design methodology and carry out a series of numeric experiments. The conventional SOPNN is based on the extended Group Method of Data Handling(GMDH) method and utilized the polynomial order (viz. linear, quadratic, and modified quadratic) as well as the number of node inputs fixed (selected in advance by designer) at Polynomial Neurons (or nodes) located in each layer through a growth process of the network. Moreover it does not guarantee that the SOPNN generated through learning has the optimal network architecture. But the proposed GA-based SOPNN enable the architecture to be a structurally more optimized network, and to be much more flexible and preferable neural network than the conventional SOPNN. In order to generate the structurally optimized SOPNN, GA-based design procedure at each stage (layer) of SOPNN leads to the selection of preferred nodes (or PNs) with optimal parameters- such as the number of input variables, input variables, and the order of the polynomial-available within SOPNN. An aggregate performance index with a weighting factor is proposed in order to achieve a sound balance between approximation and generalization (predictive) abilities of the model. A detailed design procedure is discussed in detail. To evaluate the performance of the GA-based SOPNN, the model is experimented with using two time series data (gas furnace and NOx emission process data of gas turbine power plant). A comparative analysis shows that the proposed GA-based SOPNN is model with higher accuracy as well as more superb predictive capability than other intelligent models presented previously.

• 제어로봇시스템학회:학술대회논문집
• /
• 1991.10b
• /
• pp.1659-1663
• /
• 1991

A new control design methodology is presented here which is based on a nonlinear time-series reference model. It is indicated by highly nonlinear simulations that such designs successfully stabilize troublesome aircraft maneuvers undergoing large changes in angle of attack as well as large electric power transients due to line faults. In both applications, the nonlinear controller was significantly better than the corresponding linear adaptive controller. For the electric power network, a flexible a.c. transmission system (FACTS) with series capacitor power feedback control is studied. A bilinear auto-regressive moving average (BARMA) reference model is identified from system data and the feedback control manipulated according to a desired reference state. The control is optimized according to a predictive one-step quadratic performance index (J). A similar algorithm is derived for control of rapid changes in aircraft angle of attack over a normally unstable flight regime. In the latter case, however, a generalization of a bilinear time-series model reference includes quadratic and cubic terms in angle of attack. These applications are typical of the numerous plants for which nonlinear adaptive control has the potential to provide significant performance improvements. For aircraft control, significant maneuverability gains can provide safer transportation under large windshear disturbances as well as tactical advantages. For FACTS, there is the potential for significant increase in admissible electric power transmission over available transmission lines along with energy conservation. Electric power systems are inherently nonlinear for significant transient variations from synchronism such as may result for large fault disturbances. In such cases, traditional linear controllers may not stabilize the swing (in rotor angle) without inefficient energy wasting strategies to shed loads, etc. Fortunately, the advent of power electronics (e.g., high-speed thyristors) admits the possibility of adaptive control by means of FACTS. Line admittance manipulation seems to be an effective means to achieve stabilization and high efficiency for such FACTS. This results in parametric (or multiplicative) control of a highly nonlinear plant.