• The Transactions of the Korean Institute of Electrical Engineers
• /
• v.39 no.1
• /
• pp.83-91
• /
• 1990

An adaptive observer which is applicable to discrete linear time invariant systems of ARMA type in the presence of noise is proposed. It first estimates the system parameters of the MA type by applying only the system input to the observer. Then it estimates the output which corresponds to the output of the system without any noise. This is a special case of Suzuki's adaptive observer. This estimated output is applied to Suzuki's adaptive observer to estimate the system parameters of ARMA type and the states. The proposed method can make the estimate errors of the system parameters sufficiently small even in the presence of noise in the system. It can also make the estimate errors of the states of the system sufficiently small when there is no process noise. These properties of the proposed adaptive observer is certified by computer simulation.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.30 no.6C
• /
• pp.490-496
• /
• 2005

In this paper, we propose a self-constructed clustering algorithm based on inference information of the fuzzy model. This method makes it possible to automatically detect and optimize the number of cluster and parameters by using input-output data. The propose method improves the performance of clustering by extended supervised learning technique. This technique uses the output information as well as input characteristics. For effect the similarity measure in clustering, we use the TSK fuzzy model to sent the information of output. In the conceptually, we design a learning method that use to feedback the information of output to the clustering since proposed algorithm perform to separate each classes in input data space. We show effectiveness of proposed method using simulation than previous ones

• Proceedings of the KIEE Conference
• /
• 2000.11d
• /
• pp.761-764
• /
• 2000

This paper presents a Fuzzy Neural Network (FNN) system to decide whether or not the right information of lanes can be extracted from gray-level images of road scene. The decision of noisy level of input images has been required because much noises usually deteriorates the performance of feature detection based on image processing and lead to erroneous results. As input parameters to FNN, eight noisiness indexes are constructed from a cumulative distribution function (CDF) and proved the indexes being classifiers of images as the good and the bad corrupted by sources of noise by correlation analysis between input images and the indexes. Considering real-time processing and discrimination efficiency, the proposed FNN is structured by eight input parameters, three fuzzy variables and single output. We conduct much experiments and show that our system has comparable performance in terms of false-positive rates.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.14 no.4
• /
• pp.859-866
• /
• 1994

It is difficult to make an exact estimate of the peak discharge or the runoff depth of flood and establish the proper measure for the flood protection since the water stage or discharge has been nearly measured at most medium or small river basins. The objective of this study is to estimate parameters of the discrete, linear, input-output model for medium or small river basin. The On-Cheon River basin in Pusan was selected for the study area. The runoff data used in the study has been observed since June 1993, and the effective rainfall was determined using the storage function method. The parameter sets of the discrete, linear, input-output model were estimated using the least squares method and the correlation function method, respectively. The calculated hydrographs by the discrete, linear, input-output model regenerated the observed outflow hydrographs well, and also the simulated flood hydrograph was comparable to the observed one. Therefore, it is believed that the discrete, linear, input-output model is simpler than other runoff analysis methods, and can be applied to a medium or small river basin.

• 제어로봇시스템학회:학술대회논문집
• /
• 1987.10b
• /
• pp.168-173
• /
• 1987

The optimal Input design problem for linear system Which have the common parameters in the system and noise transfer functions. Exploiting the assumed Model structure and deriving the information matrix structure in detail, D-optimal open-loop stochastic input can be realized as an ARMA process under the Input or output variance constraints. In spite of the reduced order, It Is necessary to develop an efficient algorithms for the optimation with respect to the .rho..

• Journal of the Korean Society for Precision Engineering
• /
• v.28 no.7
• /
• pp.814-820
• /
• 2011

It takes long time in numerical simulation because structural design for tire requires the nonlinear material property. Neural networks has been widely studied to engineering design to reduce numerical computation time. The numbers of hidden layer, hidden layer neuron and training data have been considered as the structural design variables of neural networks. In application of neural networks to optimize design, there are a few studies about arrangement method of input layer neurons. To investigate the effect of input layer neuron arrangement on neural networks, the variables of tire contour design and tension in bead area were assigned to inputs and output for neural networks respectively. Design variables arrangement in input layer were determined by main effect analysis. The number of hidden layer, the number of hidden layer neuron and the number of training data and so on have been considered as the structural design variables of neural networks. In application to optimization design problem of neural networks, there are few studies about arrangement method of input layer neurons. To investigate the effect of arrangement of input neurons on neural network learning tire contour design parameters and tension in bead area were assigned to neural input and output respectively. Design variables arrangement in input layer was determined by main effect analysis.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.39C no.8
• /
• pp.626-636
• /
• 2014

Existing mash-up services could not be offered in accordance with the purposes and preferences of all users because they are created by the service developers. Therefore some precedent studies, which enable for individual users to create their own mash-up services automatically, have been conducted. In order to create automatic mash-up services, it is important to find elements to distinguish the possibility of mash-up. The precedent studies determine the possibility of mash-up through comparison of the similarity between input/output parameter names in the REST-based Open API. Only using the similarity to distinguish the possibility of mash-up, however, some unintended mash-up results can be occurred because the property of input/output parameters are not considered. In this paper, we propose the method considering the properties of input/output parameters to decrease the unintended mash-up results and extend ontology proposed in precedent studies by applying this property. And we propose the algorithm to distinguish the possibility of mash-up using the expanded ontology and describe the result of automatic mash-up services.

• The Journal of the Korea Contents Association
• /
• v.11 no.4
• /
• pp.74-82
• /
• 2011

To do fuzzy modelling of a nonlinear process needs to analyze the characteristics of input-output of fuzzy inference systems according to the division of entire input spaces and the fuzzy reasoning methods. For this, fuzzy model is expressed by identifying the structure and parameters of the system by means of input variables, fuzzy partition of input spaces, and consequence polynomial functions. In the premise part of the fuzzy rules Min-Max method using the minimum and maximum values of input data set and C-Means clustering algorithm forming input data into the clusters are used for identification of fuzzy model and membership functions are used as a series of triangular, gaussian-like, trapezoid-type membership functions. In the consequence part of the fuzzy rules fuzzy reasoning is conducted by two types of inferences such as simplified and linear inference. The identification of the consequence parameters, namely polynomial coefficients, of each rule are carried out by the standard least square method. And lastly, using gas furnace process which is widely used in nonlinear process we evaluate the performance and the system characteristics.

• Transactions on Electrical and Electronic Materials
• /
• v.1 no.3
• /
• pp.1-5
• /
• 2000

This paper presents a new sort of multilayer piezoelectric ceramic transformer for switching regulation power supplies. This piezoelectric transformer operate in the second thickness resonant vibration mode. Accordingly its resonant frequency is higher than 1 NHz, Because output power is low if input and output part of transformer are consisted of single layer, this research suggests a new method, which is consisted of both input and output part of transformer have 2-layered piezoelectric ceramics, The size of transformer is 20 mm in width and length, and 1.4 mm in thickness, respectively, To design a high efficient switching circuit of the transformer, internal circuit parameters were measured and then weve calculated a parameter of inductor nd capacitor to design a driving circuit, Weve used a MISFET and its driver circuit modified a calp oscillator circuit as the primary switching circuit.

• Journal of Institute of Control, Robotics and Systems
• /
• v.6 no.8
• /
• pp.689-696
• /
• 2000

In this paper we propose an eminent controller for wheeled mobile robots. This controller consists of an input-output linearization controller trying to stabilize the system and a neural network controller to compensate for uncertainties. The uncertainties are divided into two parts. First unstructured uncertainties include the elements related with system order such as friction disturbance. Second structure uncertainties are the incorrect system parameters A neural network structure of the proposed overall controller learns structural errors of the wheeled mobile robots with uncertainties and includes the neural network output. This controller learns quickly the model and has good tracking performance Simulation results show that the proposed controller is more efficient than analog controllers.