• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.46 no.2
• /
• pp.78-88
• /
• 2009

In many face recognition problems, the number of available images is limited compared to the dimension of the input space which is usually equal to the number of pixels. This problem is called as the 'small sample size' problem and regularization methods are typically used to solve this problem in feature extraction methods such as LDA. By using regularization methods, the modified within class matrix becomes nonsingu1ar and LDA can be performed in its original form. However, in the process of adding a scaled version of the identity matrix to the original within scatter matrix, the scale factor should be set heuristically and the performance of the recognition system depends on highly the value of the scalar factor. By using the proposed resampling method, we can generate a set of images similar to but slightly different from the original image. With the increased number of images, the small sample size problem is alleviated and the classification performance increases. Unlike regularization method, the resampling method does not suffer from the heuristic setting of the parameter producing better performance.

• Journal of Radiation Protection and Research
• /
• v.27 no.3
• /
• pp.165-170
• /
• 2002

Combined with deposition model onto the ground of radionuclides, the influence of radioactive contamination to agricultural products was analyzed due to wet deposition as well as dry deposition from radioactive air concentration during a nuclear emergency. The previous dynamic food chain model, in which initial input parameter is only radionuclide concentrations on the ground, was improved for the evaluating of radioactive contamination to agricultural products from either radionuclide concentrations in air or radionuclide concentrations on the ground. As the results, in case of deposition onto the ground, wet deposition was more dominant process than thy deposition. While the contamination levels of agricultural products were dependent on the a variety of factors such as radionuclides and rainfall rate. It means that the contamination levels of agricultural products are determined from which is more dominant process between deposition on the ground and interception onto agricultural plants.

• Proceedings of the Korean Geotechical Society Conference
• /
• 2008.10a
• /
• pp.1404-1414
• /
• 2008

In the mechanistic-empirical trackbed design of railways, the resilient modulus is the key input parameter. This study focused on the resilient modulus prediction model, which is the functions of mean effective principal stress and axial strain, for three types of railroad trackbed materials such as crushed stone, weathered soil, and crushed-rock soil mixture. The model is composed with the maximum Young's modulus and nonlinear values for higher strain in parallel with dynamic shear modulus. The maximum values is modeled by model parameters, $A_E$ and the power of mean effective principal stress, $n_E$. The nonlinear portion is represented by modified hyperbolic model, with the model parameters of reference strain, ${\varepsilon}_r$ and curvature coefficient, a. To assess the performance of the prediction models proposed herein, the elastic response of a test trackbed near PyeongTaek, Korea was evaluated using a 3-D nonlinear elastic computer program (GEOTRACK) and compared with measured elastic vertical displacement during the passages of freight and passenger trains. The material types of sub-ballasts are crushed stone and weathered granite soil, respectively. The calculated vertical displacements within the sub-ballasts are within the order of 0.6mm, and agree well with measured values with the reasonable margin. The prediction models are thus concluded to work properly in the preliminary investigation.

• Journal of Navigation and Port Research
• /
• v.33 no.9
• /
• pp.645-651
• /
• 2009

In this study, a series of laboratory experiments were carried out to investigate the weak reflection of regular and random water waves over a train of protruded permeable shore structures. A cylindrical slit type breakwater and the alternatives are employed and compared for reflecting and transmitting capabilities of incident waves including wave forces. A series of random waves were generated by using the Bretschneider-Mitsuyasu frequency and directional spectrum. Measured spectrum of irregular waves without breakwaters is verified by comparing with those of the input waves generated. Weak reflection is occurred at the breakwater center of the peak frequency. If the row of breakwaters is fixed at three layers and the relative height of breakwater is fixed at 0.6, around 45% of incident wave energy is reflected to offshore. It is also found that the transmission of directional random waves increases as the maximum frequency parameter increases. A very good agreement is observed. Reflection coefficients of permeable submerged breakwaters are less than those of impermeable breakwaters. The upside-down L shape is recommended for a small fishery harbor mooring in terms of reflecting capability and of practical application. The final design was applied to the wharf of a small beach of Seolly, near Namhae at the southeast coast of Korea.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2015.10a
• /
• pp.1121-1124
• /
• 2015

In this paper, we propose and demonstrate an optimal design of wideband pulsed gamma-ray detectors. Pulsed gamma-ray detectors are designed to operate in a dose rate of $1{\times}10^6{\sim}1{\times}10^8rad(Si)/s$. The input parameter was derived based on the energy ratio of pulse gamma-ray spectrum and the time of the energy. The sensor output current was calculated based on the dose rate control circuit. Using the N-type Epi Wafer, the optimum condition detection sensor was designed based on TCAD. The simulation results show that the optimal Epi layer thickness is 45um when applied voltage 3.3V. The doping concentrations are as follows : N-type is an Arsenic as $1{\times}10^{19}/cm^3$, P-type is a Boron as $1{\times}10^{19}/cm^3$ and Epi layer is Phosphorus as $3.4{\times}10^{12}/cm^3$. Pulse gamma-ray detector diameter is the 1.3mm.

• The KIPS Transactions:PartB
• /
• v.8B no.6
• /
• pp.699-704
• /
• 2001

ABSTRACT In this paper, a new hybrid modular recurrent TDNN (time-delay neural network)-HMM (hidden Markov model) architecture for speech recognition has been studied. In TDNN, the recognition rate could be increased if the signal window is extended. To obtain this effect in the neural network, a high-level memory generated through a feedback within the first hidden layer of the neural network unit has been used. To increase the ability to deal with the temporal structure of phonemic features, the input layer of the network has been divided into multiple states in time sequence and has feature detector for each states. To expand the network from small recognition task to the full speech recognition system, modular construction method has been also used. Furthermore, the neural network and HMM are integrated by feeding output vectors from the neural network to HMM, and a new parameter smoothing method which can be applied to this hybrid system has been suggested.

• Structural Engineering and Mechanics
• /
• v.32 no.2
• /
• pp.193-212
• /
• 2009

The resilience of a city confronted with a terrorist bomb attack is the background of the paper. The resilience strongly depends on vital infrastructure and the physical protection of people. The protection buildings provide in case of an external explosion is one of the important elements in safety assessment. Besides the aspect of protection, buildings facilitate and enable many functions, e.g., offices, data storage, -handling and -transfer, energy supply, banks, shopping malls etc. When a building is damaged, the loss of functions is directly related to the location, amount of damage and the damage level. At TNO Defence, Security and Safety methods are developed to quantify the resilience of city infrastructure systems (Weerheijm et al. 2007b). In this framework, the dynamic response, damage levels and residual bearing capacity of multi-storey RC buildings is studied. The current paper addresses the aspects of dynamic response and progressive collapse, as well as the proposed method to relate the structural damage to a volume-damage parameter, which can be linked to the loss of functionality. After a general introduction to the research programme and progressive collapse, the study of the dynamic response and damage due to blast loading for a single RC element is described. Shock tube experiments on plates are used as a reference to study the possibilities of engineering methods and an explicit finite element code to quantify the response and residual bearing capacity. Next the dynamic response and progressive collapse of a multi storey RC building is studied numerically, using a number of models. Conclusions are drawn on the ability to predict initial blast damage and progressive collapse. Finally the link between the structural damage of a building and its loss of functionality is described, which is essential input for the envisaged method to quantify the resilience of city infrastructure.

• Smart Structures and Systems
• /
• v.12 no.5
• /
• pp.501-521
• /
• 2013

This paper is concerned with static and dynamic shape control of a laminated Bernoulli-Euler beam hosting a uniformly distributed array of resistively interconnected piezoelectric patches. We present an analytical one-dimensional model for a laminated piezoelectric beam with material discontinuities within the framework of Bernoulli-Euler and extent the model by a network of resistors which are connected to several piezoelectric patch actuators. The voltage of only one piezoelectric patch is prescribed: we answer the question how to design the interconnected resistive electric network in order to annihilate lateral vibrations of a cantilever. As a practical example, a cantilever with eight patch actuators under the influence of a tip-force is studied. It is found that the deflection at eight arbitrary points along the beam axis may be controlled independently, if the local action of the piezoelectric patches is equal in magnitude, but opposite in sign, to the external load. This is achieved by the proper design of the resistive network and a suitable choice of the input voltage signal. The validity of our method is exact in the static case for a Bernoulli-Euler beam, but it also gives satisfactory results at higher frequencies and for transient excitations. As long as a certain non-dimensional parameter, involving the number of the piezoelectric patches, the sum of the resistances in the electric network and the excitation frequency, is small, the proposed shape control method is approximately fulfilled for dynamic load excitations. We evaluate the feasibility of the proposed shape control method with a more refined model, by comparing the results of our one-dimensional calculations based on the extended Bernoulli-Euler equations to three-dimensional electromechanically coupled finite element results in ANSYS 12.0. The results with the simple Bernoulli-Euler model agree well with the three-dimensional finite element results.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.24 no.5
• /
• pp.632-639
• /
• 2000

Conjugate heat transfer from a heat generating module ($31{\times}31{\times}7mm^3$) bonded through the module support on the floor of a parallel-plate channel(20mm high, 400mm wide, and 800mm long) to mixed convective air flow(0.2${\sim}$0.9m/s) is studied experimentally. The input power to the module is changed in a range 1.0${\sim}$4.5W, the floor thickness 0.2${\sim}$5mm, and the thermal resistance of module support, Rc:=0.06, 1.03 and 82.0K/W. Thermal conductance(Uc) of the board and convective thermal conductance($U_A$) from the module were derived, and the effect of V; Rc and t on Uc was investigated. It is found that the conjugate conductance (Uc) and the conductive heat transfer ratio ($Q_B$/Q) depend on the thermal resistance of the module support, the air velocity and the board thickness. The change of the module support resistance and the board thickness helps to elucidate the relative significance of heat transfer paths through the module support, the board, and from the board surface to the air. Additional information is investigated about the dependence of the heat transfer rate on the mixed convection parameter.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.34 no.11
• /
• pp.1681-1689
• /
• 2010

Several studies on the use of Support Vector Machines (SVMs) for diagnosing rotating machinery have been successfully carried out, but the fault classification depends on the input features as well as a multi-classification scheme, binary optimizer, kernel function, and the parameter to be used in the kernel function. Most of the published papers on multiclass SVM applications report the use of the same features to classify the faults. In this study, simple statistical features are determined on the basis of time domain vibration signals for various fault conditions, and the optimal features for each fault condition are selected. Then, the optimal features are used in the SVM training and in the classification of each fault condition. Simulation results using experimental data show that the results of the proposed stepwise classification approach with a relatively short training time are comparable to those for a single multi-class SVM.