• Speech Sciences
• /
• v.10 no.1
• /
• pp.117-129
• /
• 2003

Many people suffer from various laryngeal diseases. Since we can notice voice change easily, acoustic analysis can be helpful to diagnose the diseases. Several attempts have been made to clarify the relation between the parameters and the state of sick vocal folds but any decisive parameters are not found yet. The purpose of this study was to select and develop those parameters useful for diagnosing and differentiating laryngeal diseases. We examined eight MDVP parameters, and two additional MFCC and LPC parameters obtained from the production of an open vowel by 252 subjects with or without laryngeal diseases. Using a statistical procedure through the artificial neural networks, we attempted to differentiate laryngeal disease groups. Results showed that the LPC parameters indicated the highest differentiating rate by the networks followed by the MFCC and the MDVP parameters. In addition, Jita, Shim and NHR among the MDVP parameters came out better parameters in diagnosing laryngeal diseases.

• Proceedings of the Korean Geotechical Society Conference
• /
• 2008.03a
• /
• pp.792-802
• /
• 2008

If a tunnel is constructed below the groundwater level, the groundwater flow will occur inducing the seepage force toward the tunnel and will result in the increase of tunnel convergence. The longitudinal deformation during tunnel excavation will also be increased due to seepage pressure. A back-analysis methodology in underwater tunnel was proposed in this study based on the relative longitudinal deformation measured in-situ. Geotechnical parameters can be estimated utilizing the proposed method where the prior estimate as well as the measured convergence can be reasonably combined by adopting the Extend Bayesian Method.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.30 no.1
• /
• pp.55-74
• /
• 2005

Bankruptcy prediction has drawn a lot of research interests in previous literature, and recent studies have shown that machine learning techniques achieved better performance than traditional statistical ones. This paper employs a relatively new machine learning technique, support vector machines (SVMs). to bankruptcy prediction problem in an attempt to suggest a new model with better explanatory power and stability. To serve this purpose, we use grid search technique using 5-fold cross-validation to find out the optimal values of the parameters of kernel function of SVM. In addition, to evaluate the prediction accuracy of SVM. we compare its performance with multiple discriminant analysis (MDA), logistic regression analysis (Logit), and three-layer fully connected back-propagation neural networks (BPNs). The experiment results show that SVM outperforms the other methods.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.2 no.4
• /
• pp.50-58
• /
• 1994

To examine the residual stress field resulting from stamping process for the lower control arm of a car, the explicit finite element analysis is performed for the stamping process by way of the ABAQUS Explicit. The residual stress is obtained in terms of the Von Mises stress and other parameters such as equivalent plastic strain, the change of blank thickness, the final configuration of the blank and the spring back effect are also considered. Moreover, discussed is the convergence of the explicit FEM versus the punch sped and the element discretization

• The Transactions of the Korean Institute of Electrical Engineers B
• /
• v.55 no.1
• /
• pp.21-26
• /
• 2006

This paper deals with the dynamic analysis and experiments of moving-magnet linear actuator with/without spring. On the basis of two dimensional (2-D) analytical solutions and experiments, control parameters such as thrust constant, back-emf constant, inductance and resistance are obtained. And then, dynamic simulation algorithm is established from the voltage and motion equation. Finally, for various values of frequency, dynamic simulation results for characteristics of current and displacement of moving-magnet linear actuator with and without spring are presented and confirmed through the experiments. In particular, This paper applies the PWM voltage waveform obtained from a DSP for bidirectional voltage drive to the actuator.

• Earthquakes and Structures
• /
• v.25 no.1
• /
• pp.15-26
• /
• 2023

It is of great importance to assess the residual displacement demand in the performance-based seismic design. In this paper, a hybrid deep learning model for predicting the residual displacement spectra under near-fault (NF) ground motions is proposed by combining the long short-term memory network (LSTM) and back-propagation (BP) network. The model is featured by its capacity of predicting the residual displacement spectrum under a given NF ground motion while considering the effects of structural parameters. To construct this model, 315 natural and artificial NF ground motions were employed to compute the residual displacement spectra through elastoplastic time history analysis considering different structural parameters. Based on the resulted dataset with a total of 9,450 samples, the proposed model was finally trained and tested. The results show that the proposed model has a satisfactory accuracy as well as a high efficiency in predicting residual displacement spectra under given NF ground motions while considering the impacts of structural parameters.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.14 no.6
• /
• pp.127-136
• /
• 2006

Prediction of diesel particulate filtration is typically made by virtue of modeling of particulate matter(PM) collection. The model is closed with filtration parameters reflecting all small scale phenomena associated with PM trapping, and these parameters are to be traced back by inversely analyzing large-scale empirical data-the pressure drop histories. Included are soot cake permeability, soot cake density, soot density in the porous filter wall, and percolation constant. In the present study, a series of single channel DPF experiment is conducted, pressure histories are inversely analyzed, and the essential filtration parameters are deducted by DPF filtration model formulated with non-linear description of soot cake regression. Sensitivity analyses of model parameters are also made. Results showed that filtration transients are significantly altered by the extent of percolation constant, and the soot density in the porous filter wall is controlling the filtration qualities in deep-bed filtration regime. In addition, effect of soot particle size on filtration quality is distinct in a period of soot cake regime.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.39 no.4
• /
• pp.90-96
• /
• 2016

Incremental sheet forming (ISF) is a highly versatile and flexible process for rapid manufacturing of complex sheet metal parts. Compared to conventional sheet forming processes, ISF is of a clear advantage in manufacturing small batch or customized parts. ISF needs die-less machine alone, while conventional sheet forming requires highly expensive facilities like dies, molds, and presses. This equipment takes long time to get preparation for manufacturing. However, ISF does not need the full facilities nor much cost and time. Because of the facts, ISF is continuously being used for small batch or prototyping manufacturing in current industries. However, spring-back induced in the process of incremental forming becomes a critical drawback on precision manufacturing. Since sheet metal, being a raw material for ISF, has property to resilience, spring-back would come in the case. It is the research objective to investigate how geometrical shaping parameters make effect on shape dimensional errors. In order to analyze the spring-back occurred in the process, this study experimented on Al 1015 material in the ISF. The statistical tool employed experimental design with factors. The table of orthogonal arrays of $L_8(2^7)$ are used to design the experiments and ANOVA method are employed to statistically analyze the collected data. The results of the analysis from this study shows that the type of shape and the slope of bottom are the significant, whereas the shape size, the shape height, and the side angle are not significant factors on dimensional errors. More error incurred on the pyramid than on the circular type in the experiments. The sloped bottom showed higher errors than the flat one.

• Journal of international Conference on Electrical Machines and Systems
• /
• v.2 no.1
• /
• pp.16-22
• /
• 2013

This paper presents the analysis and optimization of air-core permanent magnet linear synchronous motor with overlapping concentrated windings to achieve high thrust density, high thrust per copper losses and low thrust ripple. For the motor design, we adopt equivalent magnetizing current (EMC) method to analyze the magnetic field and give analytical formulae for calculation of motor parameters such as no-load back EMF, dynamic force, thrust density and thrust per copper losses. Further, we proposed a multi-objective optimization by genetic algorithm to search for the optimum parameters. The design optimization is verified by 2-D Finite Element analysis (FEA).

• Proceedings of the KIEE Conference
• /
• 2008.07a
• /
• pp.731-732
• /
• 2008

This paper deals with design and characteristics analysis of 7.5-kW, 60,000-rpm class permanent magnet synchronous motor for turbo compressor. In order to determine the design parameters of rotor, torque per rotor volume method is applied. And, to analyze the magnetic field distribution and estimate the electrical parameters such as back EMF constant, inductance and torque constant, electromagnetic transfer relations theorem is employed. We compare the characteristics analysis results of model designed by proposed method with those by nonlinear FEA. As a result of this, the design have been validated.