• Proceedings of the KIEE Conference
• /
• 2000.11d
• /
• pp.800-802
• /
• 2000

In this paper, we propose the Self-Organizing Networks(SON) based on competitive Fuzzy Polynomial Neuron(FPN) for the optimal design of nonlinear process system. The SON architectures consist of layers with activation nodes based on fuzzy inference rules. Here each activation node is presented as FPN which includes either the simplified or regression Polynomial fuzzy inference rules. The proposed SON is a network resulting from the fusion of the Polynomial Neural Networks(PNN) and a fuzzy inference system. The conclusion part of the rules, especially the regression polynomial uses several types of high-order polynomials such as liner, quadratic and modified quadratic. As the premise part of the rules, both triangular and Gaussian-like membership functions are studied. Chaotic time series data used to evaluate the performance of our proposed model.

• Journal of Ship and Ocean Technology
• /
• v.11 no.4
• /
• pp.21-28
• /
• 2007

Recently the importance of the utilization of engineering data is gradually increasing. Engineering data contains the experiences and know-how of experts. Data mining technique is useful to extract knowledge or information from the accumulated existing data. This paper deals with generating optimal polynomials using genetic programming (GP) as the module of Data Mining system. Low order Taylor series are used to approximate the polynomial easily as a nonlinear function to fit the accumulated data. The overfitting problem is unavoidable because in real applications, the size of learning samples is minimal. This problem can be handled with the extended data set and function node stabilization method. The Data Mining system for the ship design based on polynomial genetic programming is presented.

• ETRI Journal
• /
• v.39 no.6
• /
• pp.841-850
• /
• 2017

We investigate neural network image reconstruction for magnetic particle imaging. The network performance strongly depends on the convolution effects of the spectrum input data. The larger convolution effect appearing at a relatively smaller nanoparticle size obstructs the network training. The trained single-layer network reveals the weighting matrix consisting of a basis vector in the form of Chebyshev polynomials of the second kind. The weighting matrix corresponds to an inverse system matrix, where an incoherency of basis vectors due to low convolution effects, as well as a nonlinear activation function, plays a key role in retrieving the matrix elements. Test images are well reconstructed through trained networks having an inverse kernel matrix. We also confirm that a multi-layer network with one hidden layer improves the performance. Based on the results, a neural network architecture overcoming the low incoherence of the inverse kernel through the classification property is expected to become a better tool for image reconstruction.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 1998.03a
• /
• pp.148-153
• /
• 1998

In order to control thermal deformation of machine origin of machine tools due to internal and external heat sources, the real-time compensation system has been developed. First, GMDH models were constructed to estimate thermal deformation of machine origin for a vertical machining center through the measurement of deformation data and temperature data of specific points on the machine tool. Thermocouples and gap sensors are used respectively for measurement. These models are nonlinear equations with high-order polynomials and implemented in a multilayered perceptron type network structure. Secondly, work origin shift method were developed by implementing digital I/O interface board between CNC controller and IBM-PC. The work origin shift method is to shift the work origin by the compensation amounts which is calculated by pre-established GMDH model. From the experimental result, thermal deformation of machine origin was reduced to below $\pm$5${\mu}{\textrm}{m}$.

• Proceedings of the KIEE Conference
• /
• 1997.07b
• /
• pp.584-586
• /
• 1997

The orthogonal polynomials have been widely employed to solve control problems, but the LQG(linear quadratic gaussian) problem remains unsolved. In this paper, we obtained the solutions of Riccati equation and covariance matrix Riccati equation by two point boundary problem and matrix fraction method using BPF(Block Pulse Function), respectively. This solutions are solved the problem of the LQG controller design.

• Structural Engineering and Mechanics
• /
• v.68 no.5
• /
• pp.603-619
• /
• 2018

In this research, an effective computational technique is carried out for nonlinear and post-buckling analyses of cracked imperfect composite plates. The laminated plates are assumed to be moderately thick so that the analysis can be carried out based on the first-order shear deformation theory. Geometric non-linearity is introduced in the way of von-Karman assumptions for the strain-displacement equations. The Ritz technique is applied using Legendre polynomials for the primary variable approximations. The crack is modeled by partitioning the entire domain of the plates into several sub-plates and therefore the plate decomposition technique is implemented in this research. The penalty technique is used for imposing the interface continuity between the sub-plates. Different out-of-plane essential boundary conditions such as clamp, simply support or free conditions will be assumed in this research by defining the relevant displacement functions. For in-plane boundary conditions, lateral expansions of the unloaded edges are completely free while the loaded edges are assumed to move straight but restricted to move laterally. With the formulation presented here, the plates can be subjected to biaxial compressive loads, therefore a sensitivity analysis is performed with respect to the applied load direction, along the parallel or perpendicular to the crack axis. The integrals of potential energy are numerically computed using Gauss-Lobatto quadrature formulas to get adequate accuracy. Then, the obtained non-linear system of equations is solved by the Newton-Raphson method. Finally, the results are presented to show the influence of crack length, various locations of crack, load direction, boundary conditions and different values of initial imperfection on nonlinear and post-buckling behavior of laminates.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.16 no.3
• /
• pp.533-540
• /
• 2021

To evaluate the performance of a system, one-dimensional 3-neighborhood cellular automata(CA) based pseudo-random generators are widely used in many fields. Although two-dimensional CA and one-dimensional 5-neighborhood CA have been applied for more effective key sequence generation, designing symmetric one-dimensional 5-neighborhood CA corresponding to a given primitive polynomial is a very challenging problem. To solve this problem, studies on one-dimensional 5-neighborhood CA synthesis, such as synthesis method using recurrence relation of characteristic polynomials and synthesis method using Krylov matrix, were conducted. However, there was still a problem with solving nonlinear equations. To solve this problem, a symmetric one-dimensional 5-neighborhood CA synthesis method using a transition matrix of 90/150 CA and a block matrix has recently been proposed. In this paper, we detail the theoretical process of the proposed algorithm and use it to obtain symmetric one-dimensional 5-neighborhood CA corresponding to high-order primitive polynomials.

• Proceedings of the KIEE Conference
• /
• 2001.11c
• /
• pp.413-415
• /
• 2001

In this paper, Polynomial Neural Networks(PNN) is proposed to overcome some problems, such as the conflict between overfitting and good generation, and low reliability and to control nonlinearity and unknown parameter of complex system. PNN structure is consisted of layers and nodes like conventional neural networks but is not fixed and can be generated according to the system environments. The performances depend on two factors, number of inputs and order of polynomials in each node directly. In most cases these factors are decided by the trial and error of designer so optimization is needed in deciding procedure of the factors. Evolutionary algorithm is applied to decide the factors in PNN. The study is illustrated with the aid of representative time series data for gas furnace process used widely for performance comparison, and shows the designed PNN architecture with evolutionary algorithm.

• Proceedings of the KIEE Conference
• /
• 1999.07g
• /
• pp.2856-2858
• /
• 1999

In this paper, the FPNN(Fuzzy Polynomial Neural Networks) algorithm with multi-layer fuzzy inference structure is proposed for the model identification of a complex nonlinear system. The FPNN structure is generated from the mutual combination of PNN (Polynomial Neural Network) structure and fuzzy inference method. The PNN extended from the GMDH(Group Method of Data Handling) uses several types of polynomials such as linear, quadratic and modifled quadratic besides the biquadratic polynomial used in the GMDH. In the fuzzy inference method, simplified and regression polynomial inference method which is based on the consequence of fuzzy rule expressed with a polynomial such as linear, quadratic and modified quadratic equation are used Each node of the FPNN is defined as a fuzzy rule and its structure is a kind of fuzzy-neural networks. Gas furnace data used to evaluate the performance of our proposed model.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.58 no.1
• /
• pp.18-22
• /
• 2009

Short-term load forecasting (STLF) is an important task in power system planning and operation. Its accuracy affects the reliability and economic operation of power systems. STLF is to be classified into load forecasting for weekdays, weekends, and holidays. Due to the limited historical data available, it is more difficult to accurately forecast load for holidays than to forecast load for weekdays and weekends. It has been recognized that the forecasting errors for holidays are large compared with those for weekdays in Korea. This paper presents a polynomial regression with data mining technique to forecast load for holidays. In statistics, a polynomial is widely used in situations where the response is curvilinear, because even complex nonlinear relationships can be adequately modeled by polynomials over a reasonably small range of the dependent variables. In the paper, the coefficient of determination is proposed as a selection criterion for screening weekday data used in holiday load forecasting. A numerical example is presented to validate the effectiveness of the proposed holiday load forecasting method.