• The Transactions of the Korean Institute of Electrical Engineers C
• /
• v.52 no.7
• /
• pp.424-424
• /
• 2003

Evolutionary design related to the optimal design of Polynomial Neural Networks (PNNs) structure for model identification of complex and nonlinear system is studied in this paper. The PNN structure is consisted of layers and nodes like conventional neural networks but is not fixed and can be changable according to the system environments. three types of polynomials such as linear, quadratic, and modified quadratic is used in each node that is connected with various kinds of multi-variable inputs. Inputs and order of polynomials in each node are very important element for the performance of model. In most cases these factors are decided by the background information and trial and error of designer. For the high reliability and good performance of the PNN, the factors must be decided according to a logical and systematic way. In the paper evolutionary algorithm is applied to choose the optimal input variables and order. Evolutionary (genetic) algorithm is a random search optimization technique. The evolved PNN with optimally chosen input variables and order is not fixed in advance but becomes fully optimized automatically during the identification process. Gas furnace and pH neutralization processes are used in conventional PNN version are modeled. It shows that the designed PNN architecture with evolutionary structure optimization can produce the model with higher accuracy than previous PNN and other works.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.23 no.6
• /
• pp.615-626
• /
• 2010

The discrete-layer model is proposed to analyze the edge-effect problem of laminates under extension and flexure. Based on three-dimensional elasticity theory, the displacement fields of each layer in a laminate have been treated discretely in terms of three displacement components across the thickness. The displacement fields at bottom and top surfaces within a layer are approximated by two-dimensional shape functions. Then two surfaces are connected by one-dimensional high order shape functions. Thus the p-convergent refinement on approximated one- and two-dimensional shape functions can be implemented independently of each other. The quality of present model is mostly determined by polynomial degrees of shape functions for given displacement fields. For nodal modes with physical meaning, the linear Lagrangian polynomials are considered. Additional modes without physical meaning, which are created by increasing nodeless degrees of shape functions, are derived from integrals of Legendre polynomials which have an orthogonality property. Also, it is assumed that mapping functions are linear in the light of shape of laminated plates. The results obtained by this proposed model are compared with those available in literatures. Especially, three-dimensional out-of-plane stresses in the interior and near the free edges are evaluated and convergence performance of the present model is established with the stress results.

• Communications of the Korean Mathematical Society
• /
• v.22 no.3
• /
• pp.475-485
• /
• 2007

We construct high-degree interpolation rules using not only pointwise values of a function but also of its derivatives up to the p-th order at equally spaced nodes on a closed and bounded interval of interest by introducing a linear functional from which we produce systems of linear equations. The linear systems will lead to a conclusion that the rules are uniquely determined for the nodes. An example is provided to compare the rules with the classical interpolating polynomials.

• Coupled systems mechanics
• /
• v.5 no.1
• /
• pp.59-86
• /
• 2016

This paper deals with the free vibration analysis of a dynamical coupled system: flexible gravity dam- compressible rectangular reservoir. The finite element method is used to compute the natural frequencies and modal shapes of the system. Firstly, the reservoir and subsequently the dam is modeled by classical 8-node elements and the natural frequencies plus modal shapes are calculated. Afterwards, a new 21-node element is introduced and the same procedure is conducted in which an efficient method is employed to carry out the integration operations. Finally, the coupled dam-reservoir system is modeled by solely one 21-node element and the free vibration of dam-reservoir interaction system is investigated. As an important result, it is clearly concluded that the one high-order element treats more precisely than the eight-node elements, since the first one utilizes fifth-degree polynomials to construct the shape functions and the second implements polynomials of degree two.

• Structural Engineering and Mechanics
• /
• v.13 no.5
• /
• pp.491-504
• /
• 2002

Recently we formulated a 2D hybrid stress element from the 3D Hellinger-Reissner principle for the analysis of thick bodies that are symmetric to the thickness direction. Polynomials have typically been used for all the displacement and stress fields. Although the element predicted the dominant stress and all displacement fields accurately, its prediction of the out-of-plane shear stresses was affected by the very high order terms used in the polynomials. This paper describes an improved formulation of the 2D element using Fourier series expansion for the out-of-plane displacement and stress fields. Numerical results illustrate that its predictions have markedly improved.

• Proceedings of the KIEE Conference
• /
• 1998.07g
• /
• pp.2533-2535
• /
• 1998

In this paper, an effect of drive-in process temperature on the residual stress profile of the p+ silicon film has been investigated. The residual stress profile has been calculated as the fourth-order polynomials. All coefficients of the polynomials have been determined from the measurement of the vertical deflections of the p+ silicon cantilevers with various thickness and the tip displacement of the p+ silicon rotating beam. From the determination results of the residual stress profile, the average stress of the film thermally oxidized at 1000 $^{\circ}C$ is 15 MPa and that of the film oxidized at 1100 $^{\circ}C$ is 25 MPa. The profile of the residual stress through the high temperature drive-in process has a steeper gradient than the other case.

• Journal of Korea Multimedia Society
• /
• v.9 no.12
• /
• pp.1607-1616
• /
• 2006

The growing market of multimedia and digital signal processing requires significant data-path portions of SoCs. However, the common models for verification are not suitable for SoCs. A novel model--WGL (Weighted Generalized List) is proposed, which is based on the general-list decomposition of polynomials, with three different weights and manipulation rules introduced to effect node sharing and the canonicity. Timing parameters and operations on them are also considered. Examples show the word-level WGL is the only model to linearly represent the common word-level functions and the bit-level WGL is especially suitable for arithmetic intensive circuits. The model is proved to be a uniform and efficient model for both bit-level and word-level functions. Then Based on the WGL model, a backward-construction logic-verification approach is presented, which reduces time and space complexity for multipliers to polynomial complexity(time complexity is less than $O(n^{3.6})$ and space complexity is less than $O(n^{1.5})$) without hierarchical partitioning. Finally, a construction methodology of word-level polynomials is also presented in order to implement complex high-level verification, which combines order computation and coefficient solving, and adopts an efficient backward approach. The construction complexity is much less than the existing ones, e.g. the construction time for multipliers grows at the power of less than 1.6 in the size of the input word without increasing the maximal space required. The WGL model and the verification methods based on WGL show their theoretical and applicable significance in SoC design.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.63 no.4
• /
• pp.534-540
• /
• 2014

In this paper, we propose a fuzzy combined Polynomial Neural Network(PNN) for pattern classification. The fuzzy combined PNN comes from the generic TSK fuzzy model with several linear polynomial as the consequent part and is the expanded version of the fuzzy model. The proposed pattern classifier has the polynomial neural networks as the consequent part, instead of the general linear polynomial. PNNs are implemented by stacking the simple polynomials dynamically. To implement one layer of PNNs, the various types of simple polynomials are used so that PNNs have flexibility and versatility. Although the structural complexity of the implemented PNNs is high, the PNNs become a high order-multi input polynomial finally. To estimate the coefficients of a polynomial neuron, The weighted linear discriminant analysis. The output of fuzzy rule system with PNNs as the consequent part is the linear combination of the output of several PNNs. To evaluate the classification ability of the proposed pattern classifier, we make some experiments with several machine learning data sets.

• Asian-Australasian Journal of Animal Sciences
• /
• v.31 no.5
• /
• pp.636-642
• /
• 2018

Objective: The objective of this study was to estimate genetic parameters of milk, fat, and protein yields within and across lactations in Tunisian Holsteins using a random regression test-day (TD) model. Methods: A random regression multiple trait multiple lactation TD model was used to estimate genetic parameters in the Tunisian dairy cattle population. Data were TD yields of milk, fat, and protein from the first three lactations. Random regressions were modeled with third-order Legendre polynomials for the additive genetic, and permanent environment effects. Heritabilities, and genetic correlations were estimated by Bayesian techniques using the Gibbs sampler. Results: All variance components tended to be high in the beginning and the end of lactations. Additive genetic variances for milk, fat, and protein yields were the lowest and were the least variable compared to permanent variances. Heritability values tended to increase with parity. Estimates of heritabilities for 305-d yield-traits were low to moderate, 0.14 to 0.2, 0.12 to 0.17, and 0.13 to 0.18 for milk, fat, and protein yields, respectively. Within-parity, genetic correlations among traits were up to 0.74. Genetic correlations among lactations for the yield traits were relatively high and ranged from $0.78{\pm}0.01$ to $0.82{\pm}0.03$, between the first and second parities, from $0.73{\pm}0.03$ to $0.8{\pm}0.04$ between the first and third parities, and from $0.82{\pm}0.02$ to $0.84{\pm}0.04$ between the second and third parities. Conclusion: These results are comparable to previously reported estimates on the same population, indicating that the adoption of a random regression TD model as the official genetic evaluation for production traits in Tunisia, as developed by most Interbull countries, is possible in the Tunisian Holsteins.

• Journal of the Korean Mathematical Society
• /
• v.57 no.6
• /
• pp.1407-1433
• /
• 2020

Parts I-IV showed that the number of ways to place q nonattacking queens or similar chess pieces on an n × n chessboard is a quasipolynomial function of n whose coefficients are essentially polynomials in q. For partial queens, which have a subset of the queen's moves, we proved complete formulas for these counting quasipolynomials for small numbers of pieces and other formulas for high-order coefficients of the general counting quasipolynomials. We found some upper and lower bounds for the periods of those quasipolynomials by calculating explicit denominators of vertices of the inside-out polytope. Here we discover more about the counting quasipolynomials for partial queens, both familiar and strange, and the nightrider and its subpieces, and we compare our results to the empirical formulas found by Kotššovec. We prove some of Kotššovec's formulas and conjectures about the quasipolynomials and their high-order coefficients, and in some instances go beyond them.