• Journal of the Korean Institute of Intelligent Systems
• /
• v.22 no.6
• /
• pp.793-798
• /
• 2012

In this paper, we explored the new method for extracting feature from the electroencephalography (EEG) signal based on linear regression technique with the orthonormal polynomial bases. At first, EEG signals from electrodes around motor cortex were selected and were filtered in both spatial and temporal filter using band pass filter for alpha and beta rhymic band which considered related to the synchronization and desynchonization of firing neurons population during motor imagery task. Signal from epoch length 1s were fitted into linear regression with Legendre polynomials bases and extract the linear regression weight as final features. We compared our feature to the state of art feature, power band feature in binary classification using support vector machine (SVM) with 5-fold cross validations for comparing the classification accuracy. The result showed that our proposed method improved the classification accuracy 5.44% in average of all subject over power band features in individual subject study and 84.5% of classification accuracy with forward feature selection improvement.

• Journal of the Korean Mathematical Society
• /
• v.58 no.3
• /
• pp.571-595
• /
• 2021

In this paper we study the algebraic structure of ℤ_pℤ_p[u]/k>-cyclic codes, where u^k = 0 and p is a prime. A ℤ_pℤ_p[u]/k>-linear code of length (r + s) is an R_k-submodule of ℤ^r_p × R^s_k with respect to a suitable scalar multiplication, where R_k = ℤ_p[u]/k>. Such a code can also be viewed as an R_k-submodule of ℤ_p[x]/r - 1> × R_k[x]/s - 1>. A new Gray map has been defined on ℤ_p[u]/k>. We have considered two cases for studying the algebraic structure of ℤ_pℤ_p[u]/k>-cyclic codes, and determined the generator polynomials and minimal spanning sets of these codes in both the cases. In the first case, we have considered (r, p) = 1 and (s, p) ≠ 1, and in the second case we consider (r, p) = 1 and (s, p) = 1. We have established the MacWilliams identity for complete weight enumerators of ℤ_pℤ_p[u]/k>-linear codes. Examples have been given to construct ℤ_pℤ_p[u]/k>-cyclic codes, through which we get codes over ℤ_p using the Gray map. Some optimal p-ary codes have been obtained in this way. An example has also been given to illustrate the use of MacWilliams identity.

• Asian-Australasian Journal of Animal Sciences
• /
• v.24 no.1
• /
• pp.17-27
• /
• 2011

A selection experiment for reduced residual feed intake (RFI) in Yorkshire pigs consisted of a line selected for lower RFI (LRFI) and a random control line (CTRL). Longitudinal measurements of daily feed intake (DFI) and body weight (BW) from generation 5 of this experiment were used. The objectives of this study were to evaluate the use of random regression (RR) and nonlinear mixed models to predict DFI and BW for individual pigs, accounting for the substantial missing information that characterizes these data, and to evaluate the effect of selection for RFI on BW and DFI curves. Forty RR models with different-order polynomials of age as fixed and random effects, and with homogeneous or heterogeneous residual variance by month of age, were fitted for both DFI and BW. Based on predicted residual sum of squares (PRESS) and residual diagnostics, the quadratic polynomial RR model was identified to be best, but with heterogeneous residual variance for DFI and homogeneous residual variance for BW. Compared to the simple quadratic and linear regression models for individual pigs, these RR models decreased PRESS by 1% and 2% for DFI and by 42% and 36% for BW on boars and gilts, respectively. Given the same number of random effects as the polynomial RR models, i.e., two for BW and one for DFI, the non-linear Gompertz model predicted better than the polynomial RR models but not as good as higher order polynomial RR models. After five generations of selection for reduced RFI, the LRFI line had a lower population curve for DFI and BW than the CTRL line, especially towards the end of the growth period.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.61 no.5
• /
• pp.744-752
• /
• 2012

In this study, the Polynomial-based Radial Basis Function Neural Networks is proposed as an one of the recognition part of overall face recognition system that consists of two parts such as the preprocessing part and recognition part. The design methodology and procedure of the proposed pRBFNNs are presented to obtain the solution to high-dimensional pattern recognition problems. In data preprocessing part, Principal Component Analysis(PCA) which is generally used in face recognition, which is useful to express some classes using reduction, since it is effective to maintain the rate of recognition and to reduce the amount of data at the same time. However, because of there of the whole face image, it can not guarantee the detection rate about the change of viewpoint and whole image. Thus, to compensate for the defects, Linear Discriminant Analysis(LDA) is used to enhance the separation of different classes. In this paper, we combine the PCA&LDA algorithm and design the optimized pRBFNNs for recognition module. The proposed pRBFNNs architecture consists of three functional modules such as the condition part, the conclusion part, and the inference part as fuzzy rules formed in 'If-then' format. In the condition part of fuzzy rules, input space is partitioned with Fuzzy C-Means clustering. In the conclusion part of rules, the connection weight of pRBFNNs is represented as two kinds of polynomials such as constant, and linear. The coefficients of connection weight identified with back-propagation using gradient descent method. The output of the pRBFNNs model is obtained by fuzzy inference method in the inference part of fuzzy rules. The essential design parameters (including learning rate, momentum coefficient and fuzzification coefficient) of the networks are optimized by means of Differential Evolution. The proposed pRBFNNs are applied to face image(ex Yale, AT&T) datasets and then demonstrated from the viewpoint of the output performance and recognition rate.

• Journal of Ocean Engineering and Technology
• /
• v.35 no.2
• /
• pp.131-140
• /
• 2021

The paper deals with comparative study of various surrogate models based approximate optimization in the structural design of the passive type deck support frame under design load conditions. The passive type deck support frame was devised to facilitate both transportation and installation of 20,000 ton class topside. Structural analysis was performed using the finite element method to evaluate the strength performance of the passive type deck support frame in its initial design stage. In the structural analysis, the strength performances were evaluated for various design load conditions. The optimum design problem based on surrogate model was formulated such that thickness sizing variables of main structure members were determined by minimizing the weight of the passive type deck support frame subject to the strength performance constraints. The surrogate models used in the approximate optimization were response surface method, Kriging model, and Chebyshev orthogonal polynomials. In the context of numerical performances, the solution results from approximate optimization were compared to actual non-approximate optimization. The response surface method among the surrogate models used in the approximate optimization showed the most appropriate optimum design results for the structure design of the passive type deck support frame.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.37 no.6A
• /
• pp.438-449
• /
• 2012

This paper presents new CRC-p codes for VHF band maritime wireless communication system based on performance analysis of various CRC codes. For this purpose, we firstly describe the method of determination of undetected error probability and minimum Hamming distance according to variation of CRC codeword length. By using the fact that the dual code of cyclic Hamming code and primitive BCH code become maximum length codes, we present an algorithm for computation of undetected error probability and minimum Hamming distance where the concept of simple hardware that is consisted of linear feedback shift register is utilized to compute the weight distribution of CRC codes. We also present construction of transmit data frame of VHF band maritime wireless communication system and specification of major communication parameters. Finally, new optimal CRC-p codes are presented based on the simulation results of undetected error probability and minimum Hamming distance using the various generator polynomials of CRC codes, and their performances are evaluated with simulation results of bit error rate based on the Rician maritime channel model and ${\pi}$/4-DQPSK modulator.

• Asian-Australasian Journal of Animal Sciences
• /
• v.31 no.1
• /
• pp.86-90
• /
• 2018

Objective: This study was conducted to investigate the effects of dietary detoxified Rhus verniciflua sap (RVS) on production performance, egg quality, lipid fractions of egg yolk, liver and serum, and the profile of cecal microflora in laying hens. Methods: Two hundred 52-week-old Hy-Line Brown layers were randomly divided into 4 groups with 5 replicates per group (2 hens per cage, 5 cages per replicate) and were provided with one of 4 experimental diets containing 0%, 0.05%, 0.1%, or 0.2% RVS, for 6 weeks. Due to unequal intervals of RVS doses, the interactive matrix language procedure of the SAS program was used to correct the contrast coefficients of orthogonal polynomials. Results: There were no differences in feed intake and egg weight among the groups. Egg production increased (linearly and quadratically, p<0.05) with increasing levels of RVS. Eggshell thickness increased (linear, p<0.05) as the level of RVS in diets increased. The levels of blood cholesterol and activities of glutamic-oxaloacetic transaminase and glutamic-pyruvic transaminase were not altered by dietary treatments. Increasing level of RVS increased (linear, p<0.05) the populations of cecal lactic acid bacteria. The content of yolk cholesterol decreased (linear, p<0.05) with increasing levels of dietary RVS, although there were no significant differences in each lipid fraction of the liver. Conclusion: This study indicates that dietary RVS could improve laying performance and eggshell quality, and affect cecal lactic acid bacteria in a dose-dependent manner.

• Journal of Institute of Control, Robotics and Systems
• /
• v.16 no.12
• /
• pp.1150-1158
• /
• 2010

In this study, the Polynomial-based Radial Basis Function Neural Networks is proposed as one of the recognition part of overall face recognition system that consists of two parts such as the preprocessing part and recognition part. The design methodology and procedure of the proposed pRBFNNs are presented to obtain the solution to high-dimensional pattern recognition problem. First, in preprocessing part, we use a CCD camera to obtain a picture frame in real-time. By using histogram equalization method, we can partially enhance the distorted image influenced by natural as well as artificial illumination. We use an AdaBoost algorithm proposed by Viola and Jones, which is exploited for the detection of facial image area between face and non-facial image area. As the feature extraction algorithm, PCA method is used. In this study, the PCA method, which is a feature extraction algorithm, is used to carry out the dimension reduction of facial image area formed by high-dimensional information. Secondly, we use pRBFNNs to identify the ID by recognizing unique pattern of each person. The proposed pRBFNNs architecture consists of three functional modules such as the condition part, the conclusion part, and the inference part as fuzzy rules formed in 'If-then' format. In the condition part of fuzzy rules, input space is partitioned with Fuzzy C-Means clustering. In the conclusion part of rules, the connection weight of pRBFNNs is represented as three kinds of polynomials such as constant, linear, and quadratic. Coefficients of connection weight identified with back-propagation using gradient descent method. The output of pRBFNNs model is obtained by fuzzy inference method in the inference part of fuzzy rules. The essential design parameters (including learning rate, momentum coefficient and fuzzification coefficient) of the networks are optimized by means of the Particle Swarm Optimization. The proposed pRBFNNs are applied to real-time face recognition system and then demonstrated from the viewpoint of output performance and recognition rate.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.60 no.3
• /
• pp.639-647
• /
• 2011

In this paper, we introduce a design methodology of data-centroid Radial Basis Function neural networks with extended polynomial function. The two underlying design mechanisms of such networks involve K-means clustering method and Particle Swarm Optimization(PSO). The proposed algorithm is based on K-means clustering method for efficient processing of data and the optimization of model was carried out using PSO. In this paper, as the connection weight of RBF neural networks, we are able to use four types of polynomials such as simplified, linear, quadratic, and modified quadratic. Using K-means clustering, the center values of Gaussian function as activation function are selected. And the PSO-based RBF neural networks results in a structurally optimized structure and comes with a higher level of flexibility than the one encountered in the conventional RBF neural networks. The PSO-based design procedure being applied at each node of RBF neural networks leads to the selection of preferred parameters with specific local characteristics (such as the number of input variables, a specific set of input variables, and the distribution constant value in activation function) available within the RBF neural networks. To evaluate the performance of the proposed data-centroid RBF neural network with extended polynomial function, the model is experimented with using the nonlinear process data(2-Dimensional synthetic data and Mackey-Glass time series process data) and the Machine Learning dataset(NOx emission process data in gas turbine plant, Automobile Miles per Gallon(MPG) data, and Boston housing data). For the characteristic analysis of the given entire dataset with non-linearity as well as the efficient construction and evaluation of the dynamic network model, the partition of the given entire dataset distinguishes between two cases of Division I(training dataset and testing dataset) and Division II(training dataset, validation dataset, and testing dataset). A comparative analysis shows that the proposed RBF neural networks produces model with higher accuracy as well as more superb predictive capability than other intelligent models presented previously.

• Journal of the Korea Concrete Institute
• /
• v.21 no.1
• /
• pp.105-116
• /
• 2009

Reinforced concrete (RC) structures have been most widely used because of their good economic efficiency. However, it is very weak in tensile stresses and difficult to control deflection due to the heavy self-weight of concrete. On the other hand, it is generally known that prestressed concrete structures can be the most effective to overcome the demerits of RC structures by using various tendon lay-out and its amount. In the prestressed concrete members, the inflection points of tendons should be placed effectively for the deflection control and the moment reduction. Therefore, in this study, the equations of tendon profiles are derived in terms of polynomials that satisfy essential conditions of tendon geometries such as inflection points and natural curved shapes of tendons placed in continuous members, from which vertical components of prestressing forces can be also calculated. The derived high order polynomial expression for the distributed shape of the upward and downward forces was transformed to an simplified equivalent uniform vertical force in order to improve the applicability in the calculation of member deflection. The influences of vertical forces by tendons to deflection and moment in a continuous slab were also considered depending on the distance from column face to the location of tendons. The applicability of the proposed method was examined by an example of deflection calculation for the cases of slabs with and without tendons, and the efficiency of deflection control by tendons was also quantitatively estimated.