• Journal of the Korean Society of Laryngology, Phoniatrics and Logopedics
• /
• v.8 no.2
• /
• pp.210-216
• /
• 1997

Many tools have been used to evaluate the voice abnormalities of velopharyngeal insufficiency(VPI). The aim of study was to obtain the objective evaluation method of VPI by comparing the acoustic and nasalance data of experimentally induced VPI group and those of normal control group. Ten healthy young men were included in this study Mild and severe VPI were experimentally induced by retracting velopharyngeal movement. Using the nasometer, we obtained the nasalance score of the sustained oral vowels and those of three types of nasometer passages and the slope scores of nasogram of nasal words. And we analysed the change of formant frequencies for the sustained oral vowels and the changes of various parameters of hyper-tnasality by the computerized speech analysis system. The nasalance score of sustained /a/ was increased significantly in VPI conditions. There was no changes in the slope score of nasogram. On the acoustic speech analysis, the second formant frequencies of vowel /e/ and /i/ were decreased significantly in VPI conditions. This results suggested that the measurement of nasalance score and formant frequency might be useful in the evaluation of VPI.

• The Transactions of the Korean Institute of Electrical Engineers A
• /
• v.53 no.6
• /
• pp.324-333
• /
• 2004

This paper discusses the development of an educational web-based power flow program for undergraduate students. The interaction between lectures and users can be much enhanced via the web-based programs which result in the student's learning effectiveness on the power flow problem. However the difficulties for developing web-based application programs are that there can be the numerous unspecified users to access the application programs. To overcome the aforementioned multi-users problem and to develope the educational web-based power flow program, we have revised the system architecture, the modeling of application programs, and database which efficiently and effectively manages the complex data sets related to the power flow analysis program. The developed application program is composed of the physical three tiers where the middle tier is logically divided into two kinds of application programs. The divided application programs are interconnected by using the Web-service based on XML (Extended Markup Technology) and HTTP (Hyper Text Transfer Protocol) which make it possible the distributed computing technology Also, this paper describes the method of database modeling to handle effectively when the numerous users change the parameters of the power system to compare the results of the base case.

• Computers and Concrete
• /
• v.24 no.6
• /
• pp.555-560
• /
• 2019

During the application of shotcrete, a part of the concrete bounces back after hitting to the surface, the reinforcement or previously sprayed concrete. This rebound material is definitely not added to the mixture and considered as waste. In this study, a deep neural network model was developed to predict the rebound material during shotcrete application. The factors affecting rebound and the datasets of these parameters were obtained from previous experiments. The Long Short-Term Memory (LSTM) architecture of the proposed deep neural network model was used in accordance with this data set. In the development of the proposed four-tier prediction model, the dataset was divided into 90% training and 10% test. The deep neural network was modeled with 11 dependents 1 independent data by determining the most appropriate hyper parameter values for prediction. Accuracy and error performance in success performance of LSTM model were evaluated over MSE and RMSE. A success of 93.2% was achieved at the end of training of the model and a success of 85.6% in the test. There was a difference of 7.6% between training and test. In the following stage, it is aimed to increase the success rate of the model by increasing the number of data in the data set with synthetic and experimental data. In addition, it is thought that prediction of the amount of rebound during dry-mix shotcrete application will provide economic gain as well as contributing to environmental protection.

• IEIE Transactions on Smart Processing and Computing
• /
• v.4 no.4
• /
• pp.202-208
• /
• 2015

In this study, we propose a new inference algorithm for a multiclass Gaussian process classification model using a variational EM framework and the Laplace approximation (LA) technique. This is performed in two steps, called expectation and maximization. First, in the expectation step (E-step), using Bayes' theorem and the LA technique, we derive the approximate posterior distribution of the latent function, indicating the possibility that each observation belongs to a certain class in the Gaussian process classification model. In the maximization step, we compute the maximum likelihood estimators for hyper-parameters of a covariance matrix necessary to define the prior distribution of the latent function by using the posterior distribution derived in the E-step. These steps iteratively repeat until a convergence condition is satisfied. Moreover, we conducted the experiments by using synthetic data and Iris data in order to verify the performance of the proposed algorithm. Experimental results reveal that the proposed algorithm shows good performance on these datasets.

• International Journal of Reliability and Applications
• /
• v.17 no.2
• /
• pp.137-147
• /
• 2016

The engine mount of a car subjected to a pre-load related to the weight of the engine, and acts to insulate the vibration coming from the engine by moving on large or small displacement depending on the driving condition of the car. The vibration insulation of the engine mount is an effect obtained by dissipating the mechanical energy into heat by the viscosity characteristic of the rubber and the microscopic behavior of the additive carbon black. Therefore, dynamic stiffness from the intrinsic properties of rubber filled with carbon black at the design stage is an important design consideration. In this paper, we introduced a hyper-elastic, visco-elastic and elasto-plastic model to predict the dynamic characteristics of rubber, and developed a fitting program to determine the material model parameters using MATLAB. The dynamic characteristics analysis of the rubber insulator of the ACTIVE MOUNT was carried out by using MSC.MARC nonlinear structural analysis software, which provides the dynamic characteristics material model. The analysis results were compared with the dynamic characteristics test results of the rubber insulator, which is one of the active mount components, and the analysis results were confirmed to be valid.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.14 no.2
• /
• pp.389-396
• /
• 2019

In this paper, various architectures of deep neural networks were applied for sound event detection and their performances were compared using a common audio database. The FNN, CNN, RNN and CRNN were implemented using hyper-parameters optimized for the database as well as the architecture of each neural network. Among the implemented deep neural networks, CRNN performed best at all testing conditions and CNN followed CRNN in performance. Although RNN has a merit in tracking the time-correlations in audio signals, it showed poor performance compared with CNN and CRNN.

• Journal of Korean Association for Spatial Structures
• /
• v.21 no.2
• /
• pp.41-48
• /
• 2021

A smart tuned mass damper (TMD) is widely studied for seismic response reduction of various structures. Control algorithm is the most important factor for control performance of a smart TMD. This study used a Deep Deterministic Policy Gradient (DDPG) among reinforcement learning techniques to develop a control algorithm for a smart TMD. A magnetorheological (MR) damper was used to make the smart TMD. A single mass model with the smart TMD was employed to make a reinforcement learning environment. Time history analysis simulations of the example structure subject to artificial seismic load were performed in the reinforcement learning process. Critic of policy network and actor of value network for DDPG agent were constructed. The action of DDPG agent was selected as the command voltage sent to the MR damper. Reward for the DDPG action was calculated by using displacement and velocity responses of the main mass. Groundhook control algorithm was used as a comparative control algorithm. After 10,000 episode training of the DDPG agent model with proper hyper-parameters, the semi-active control algorithm for control of seismic responses of the example structure with the smart TMD was developed. The simulation results presented that the developed DDPG model can provide effective control algorithms for smart TMD for reduction of seismic responses.

• Journal of the Korean Society of Systems Engineering
• /
• v.16 no.2
• /
• pp.67-77
• /
• 2020

Traditionally nuclear thermal hydraulic and nuclear safety has relied on numerical simulations to predict the system response of a nuclear power plant either under normal operation or accident condition. However, this approach may sometimes be rather time consuming particularly for design and optimization problems. To expedite the decision-making process data-driven models can be used to deduce the statistical relationships between inputs and outputs rather than solving physics-based models. Compared to the traditional approach, data driven models can provide a fast and cost-effective framework to predict the behavior of highly complex and non-linear systems where otherwise great computational efforts would be required. The objective of this work is to develop an AI algorithm to predict the peak fuel cladding temperature as a metric for the successful implementation of FLEX strategies under extended station black out. To achieve this, the model requires to be conditioned using pre-existing database created using the thermal-hydraulic analysis code, MARS-KS. In the development stage, the model hyper-parameters are tuned and optimized using the talos tool.

• International Journal of Computer Science & Network Security
• /
• v.22 no.5
• /
• pp.143-148
• /
• 2022

Brain tumor classification is an important process that allows doctors to plan treatment for patients based on the stages of the tumor. To improve classification performance, various CNN-based architectures are used for brain tumor classification. Existing methods for brain tumor segmentation suffer from overfitting and poor efficiency when dealing with large datasets. The enhanced CNN architecture proposed in this study is based on U-Net for brain tumor segmentation, RefineNet for pattern analysis, and SegNet architecture for brain tumor classification. The brain tumor benchmark dataset was used to evaluate the enhanced CNN model's efficiency. Based on the local and context information of the MRI image, the U-Net provides good segmentation. SegNet selects the most important features for classification while also reducing the trainable parameters. In the classification of brain tumors, the enhanced CNN method outperforms the existing methods. The enhanced CNN model has an accuracy of 96.85 percent, while the existing CNN with transfer learning has an accuracy of 94.82 percent.

• Journal of Korean Association for Spatial Structures
• /
• v.22 no.2
• /
• pp.39-46
• /
• 2022

Recently, machine learning is widely used to solve optimization problems in various engineering fields. In this study, machine learning is applied to development of a control algorithm for a smart control device for reduction of seismic responses. For this purpose, Deep Q-network (DQN) out of reinforcement learning algorithms was employed to develop control algorithm. A single degree of freedom (SDOF) structure with a smart tuned mass damper (TMD) was used as an example structure. A smart TMD system was composed of MR (magnetorheological) damper instead of passive damper. Reward design of reinforcement learning mainly affects the control performance of the smart TMD. Various hyper-parameters were investigated to optimize the control performance of DQN-based control algorithm. Usually, decrease of the time step for numerical simulation is desirable to increase the accuracy of simulation results. However, the numerical simulation results presented that decrease of the time step for reward calculation might decrease the control performance of DQN-based control algorithm. Therefore, a proper time step for reward calculation should be selected in a DQN training process.