• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.5
• /
• pp.2171-2185
• /
• 2020

In order to judge that whether the vehicles in different images which are captured by surveillance cameras represent the same vehicle or not, we proposed a novel vehicle face recognition algorithm based on improved Nonnegative Matrix Factorization (NMF), different from traditional vehicle recognition algorithms, there are fewer effective features in vehicle face image than in whole vehicle image in general, which brings certain difficulty to recognition. The innovations mainly include the following two aspects: 1) we proposed a novel idea that the vehicle type can be determined by a few key regions of the vehicle face such as logo, grille and so on; 2) Through adding weight, sparseness and classification property constraints to the NMF model, we can acquire the effective feature bases that represent the key regions of vehicle face image. Experimental results show that the proposed algorithm not only achieve a high correct recognition rate, but also has a strong robustness to some non-cooperative factors such as illumination variation.

• Smart Structures and Systems
• /
• v.21 no.4
• /
• pp.469-477
• /
• 2018

This paper presents a numerical solution for the thick cylinders made of functionally graded materials (FGMs) with a constant Poisson's ratio and an arbitrary Young's modulus. We define two fundamental solutions which are derived from an ordinary differential equation under two particular initial boundary conditions. In addition, for the single layer case, we can define the transfer matrix N. The matrix gives a relation between the values of stress and displacement at the interior and exterior points. By using the assumed boundary condition and the transfer matrix, we can obtain the final solution. The transfer matrix method also provides an effective way for the solution of multiply layered cylinder. Finally, a lot of numerical examples are present.

• Journal of Communications and Networks
• /
• v.12 no.6
• /
• pp.624-631
• /
• 2010

Effective traffic matrix estimation is the basis of efficient traffic engineering, and therefore, quality of service provision support in IP networks. In this study, traffic matrix estimation is investigated in IP networks and an Elman neural network-based traffic matrix inference (ENNTMI) method is proposed. In ENNTMI, the conventional Elman neural network is modified to capture the spatio-temporal correlations and the time-varying property, and certain side information is introduced to help estimate traffic matrix in a network accurately. The regular parameter is further introduced into the optimal equation. Thus, the highly ill-posed nature of traffic matrix estimation is overcome effectively and efficiently.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2011.06a
• /
• pp.1417-1418
• /
• 2011

• Journal of applied mathematics & informatics
• /
• v.6 no.2
• /
• pp.649-659
• /
• 1999

This paper presents a parallel implementation of stiff-ness matrix calculation based on the processor farm model on a net-work of workstations running PVM programming environment. As the computational characteristics of stiffnes matrix exhibits good po-tentials for effective prallel computation the performance improve-ment is show to be almost linear with the number of sorkstations involved in the computation.

• The Transactions of the Korean Institute of Electrical Engineers
• /
• v.38 no.11
• /
• pp.870-876
• /
• 1989

A systematic procedure for the elements of system matrix is suggested for the multimachine systems with constant impedance loads. Synchronous machines are represented by either a two-axis model or a classical model. The interrelationship of submatrices of system matrix has been investigated. Once elements of one submatrix are determined, they can be used to calculate the elements of the other submatrix. This algorithm is more effective as the number of generators modeled by a two-axis model increases. It is illustrated for 9-Bus multimachine system.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.10 no.7
• /
• pp.1307-1311
• /
• 2006

In this paper, we propose new speech feature parameter using the Matrix Factorization for appearance part-based features of speech spectrum. The proposed parameter represents effective dimensional reduced data from multi-dimensional feature data through matrix factorization procedure under all of the matrix elements are the non-negative constraint. Reduced feature data presents p art-based features of input data. We verify about usefulness of NMF(Non-Negative Matrix Factorization) algorithm for speech feature extraction applying feature parameter that is got using NMF in Mel-scaled filter bank output. According to recognition experiment results, we confirm that proposed feature parameter is superior to MFCC(Mel-Frequency Cepstral Coefficient) in recognition performance that is used generally.

• Nuclear Engineering and Technology
• /
• v.45 no.7
• /
• pp.839-846
• /
• 2013

This paper describes a finite element model of the microstructure of dispersion type nuclear fuels, which can be used to determine the effective thermal conductivity of the fuels during irradiation. The model simulates a representative region of the fuel as a prism shaped unit cell made of brick elements. The elements within the unit cell are assigned material properties of either the fuel or the matrix depending on position, in such a way as to represent randomly distributed fuel particles with a size distribution similar to that of the as manufactured fuel. By applying an appropriate heat flux across the unit cell it is possible to determine the effective thermal conductivity of the unit cell as a function of the volume fraction of the fuel particles. The presence of a fuel/matrix interaction layer is simulated by the addition of a third set of material properties that are assigned to the finite elements that surround each fuel particle. In this way the effective thermal conductivity of the material may also be determined as a function of the volume fraction of the interaction layer. Work is on going to add fission gas bubbles in the fuel as a fourth phase to the model.

• Journal of Information Processing Systems
• /
• v.17 no.3
• /
• pp.462-472
• /
• 2021

With an increase in the scale of recommender systems, users' rating data tend to be extremely sparse. Some methods have been utilized to alleviate this problem; nevertheless, it has not been satisfactorily solved yet. Therefore, we propose an effective pre-rating method based on users' dichotomous preferences and average ratings fusion. First, based on a user-item ratings matrix, a new user-item preference matrix was constructed to analyze and model user preferences. The items were then divided into two categories based on a parameterized dynamic threshold. The missing ratings for items that the user was not interested in were directly filled with the lowest user rating; otherwise, fusion ratings were utilized to fill the missing ratings. Further, an optimized parameter λ was introduced to adjust their weights. Finally, we verified our method on a standard dataset. The experimental results show that our method can effectively reduce the prediction error and improve the recommendation quality. As for its application, our method is effective, but not complicated.

• Composites Research
• /
• v.29 no.2
• /
• pp.66-72
• /
• 2016

Porosity in polymer matrix composites increases rapidly during thermochemical decomposition at high temperatures. The generation of pores reduces elastic moduli and failure strengths of composite materials, and gas pressures in internal pores influence thermomechanical behaviors. In this paper, micromechanical finite element analysis is carried out by using two-dimensional representative volume elements for unidirectionally fiber-reinforced composites with porous matrix. According to the state of the pores, effective elastic moduli, poroelastic parameters and failure strengths of the overall composites are investigated in detail. In particular, it is confirmed that the failure strengths in the transvers and through-thickness directions are predicted much more weakly than the strength of nonpored matrix, and decrease consistently as the porosity of matrix increases.