• The KIPS Transactions:PartB
• /
• v.8B no.1
• /
• pp.105-113
• /
• 2001

최근 축약 분산 기억 장치(SDM)가 적응적 문제 해결 능력과 하드웨어화의 용이성으로 인해 현실성이 있는 신경망의 한 모델로 제안되었다. 그러나 다층 인식자의 개별 뉴런이 선형 또는 비선형 결정 함수로 해 공간을 이분하고 그들이 다양하게 결합함으로써 일반적인 문제 해결 능력을 갖는데 비해, 축약 분산 기억 장치의 뉴런은 해 공간에서 자신을 중심으로 한 일정 반경 영역을 안과 밖으로 이분하고 이들을 단순하게 합하므로써, 해 공간이 실수 공간과 같이 크기 관계를 갖는 경우 비효율적인 모델로 된다. 본 논문에서는 이러한 축약 분산 기억 장치의 특성과 그 원인을 규명하고, 문제의 해 공간이 단조 증가 또는 감소 결정 함수로 양분되는 경우, 기존의 축약 분산 기억 장치에 크기 비교 과정을 도입함으로써, 주어진 문제를 효율적으로 해결할 수 있는 수정된 축약 분산 기억 장치 모델을 제안한다. 아울러 제안된 모델을 ATM망에서의 호 수락 제어 과정에 적용한 예를 보인다.최근 축약 분산 기억 장치(SDM)가 적응적 문제 해결 능력과 하드웨어화의 용이성으로 인해 현실성이 있는 신경망의 한 모델로 제안되었다. 그러나 다층 인식자의 개별 뉴런이 선형 또는 비선형 결정 함수로 해 공간을 이분하고 그들이 다양하게 결합함으로써 일반적인 문제 해결 능력을 갖는데 비해, 축약 분산 기억 장치의 뉴런은 해 공간에서 자신을 중심으로 한 일정 반경 영역을 안과 밖으로 이분하고 이들을 단순하게 합하므로써, 해 공간이 실수 공간과 같이 크기 관계를 갖는 경우 비효율적인 모델로 된다. 본 논문에서는 이러한 축약 분산 기억 장치의 특성과 그 원인을 규명하고, 문제의 해 공간이 단조 증가 또는 감소 결정 함수로 양분되는 경우, 기존의 축약 분산 기억 장치에 크기 비교 과정을 도입함으로써, 주어진 문제를 효율적으로 해결할 수 있는 수정된 축약 분산 기억 장치 모델을 제안한다. 아울러 제안된 모델을 ATM망에서의 호 수락 제어 과정에 적용한 예를 보인다.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.18 no.1
• /
• pp.66-73
• /
• 2010

This work was focused on the material parameter extraction for the isothermal cyclic deformation analysis for which Chaboche(Combined Nonlinear Isotropic and Kinematic Hardening) and Overlay(Multi Linear Hardening) models are normally used. In this study all the parameters were driven especially based on Overlay theories. A simple method is suggested to find out best material parameters for the cyclic deformation analysis prior to the isothermal LCF(Low Cycle Fatigue) analysis. The parameter extraction was done using 400 series stainless steel data which were published in the reference papers. For simple and quick review of the parameters extracted by suggested method, 1D FORTRAN program was developed, and this program could reduce the time for checking the material data tremendously. For the application to FE code ABAQUS user subroutine for the material models was developed by means of UMAT(User Material Subroutine), and the stabilized hysteresis loops obtained by the numerical analysis were in good harmony with test results.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.27 no.11
• /
• pp.1856-1863
• /
• 2003

Overlay model had several advantages to describe hysteretic behavior of material and showed good capability for many engineering materials. However, this model is only applicable to material obeying Masing postulate. Some materials such as 316L stainless steel do not follow Masing postulate and show cyclic hardening(or softening) and strain range dependence. Low cycle fatigue tests of 316L stainless steel at 600$^{\circ}C$ were performed to investigate the characteristics of cyclic behavior of non-Masing material. From all tests cyclic softening was observed. There were differences in elastic limit of hysteresis loop according to applied strain range. To consider these features, modified overlay model was developed. Yield stresses of subelements were divided into isotropic and anisotropic part to describe the non-Masing behavior. The plastic strain range memorization was introduced to consider the strain range dependence. The prediction using modified overlay model showed a good accordance to actual hysteresis loops.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.28 no.10
• /
• pp.1603-1611
• /
• 2004

The validity of 'modified overlay model' to describe the cyclic behavior of annealed 316L stainless steel at room temperature was investigated. Material parameters(~f$_{i}$, m$_{i}$b, η, E) fur the model were obtained through constant strain amplitude test. The strain amplitude dependency of elastic limit and cyclic hardening, which were the characteristics of this model, were considered. Eight subelements were used to describe the nonlinearity of the hysteresis loops. The calculated hysteresis curve in each condition (0.5％, 0.7％, 0.9％ train amplitude test) was very close to the experimental one. Two tests, incremental step test and 5-step test, ere performed to check the validity of 'modified overlay model'. The elastic limit was saturated to the one of the highest strain amplitudes of the block in the incremental step test, so it seemed to be Masing material at the stabilized block. Cyclic hardening was successfully described in the increasing sequence of the strain amplitude in 5-step test. But, the slight cyclic softening followed by higher strain amplitude would not be able to simulate by'modified overlay model'. However, the discrepancy induced was very small between the calculated hystereses and the experimental ones. In conclusion,'Modified overlay model'was proved to be appropriate in strain range of 0.35％~ 1.0％..0％.

• Journal of KIISE:Computing Practices and Letters
• /
• v.13 no.5
• /
• pp.338-342
• /
• 2007

In this paper we propose a user adaptive post-processing method to improve the accuracy of speaker dependent, isolated word speech recognition, particularly for mobile devices. Our method considers the recognition result of the basic recognizer simply as a high-level speech feature and processes it further for correct recognition result. Our method learns correlation between the output of the basic recognizer and the correct final results and uses it to correct the erroneous output of the basic recognizer. A multi-layer perceptron model is built for each incorrectly recognized word with high frequency. As the result of experiments, we achieved a significant improvement of 41% in recognition accuracy (41% error correction rate).

• Journal of the Korean Geotechnical Society
• /
• v.16 no.6
• /
• pp.105-115
• /
• 2000

본 연구는 현실에 부합하는 연약지반의 압밀거동을 예측하기 위한 연구로서, 일단 3차원 배수 조건하에서 지반의 자중 및 압축성과 투수성의 비선형적 성질이 고려된 비선형 압밀모델을 구성하였다. 또한 연직 배수재의 시공과정에서 발생할수 있는 지반의 교란현상 및 다양한 이질층의 구성, 점증적인 하중재하 조건, 연직배수재의 부분관입 조건에 대한 고려가 가능하도록 비선형 압밀모델을 수정, 보완하였다. 이상의 연구결과를 바탕으로 유한차분방법에 의한 수치해석을 실시하였고 최종적으로 각종 희귀분석과정을 도입한 3차원 비선형 압밀해석 프로그램을 개발하였다. Ska-Edeby의 시험시공 사례를 통한 개발 프로그램의 검증을 실시하였는데, 시험시공 사례의 경우, 현장에서 측정한 깊이별 침하량 및 간극수압 결과를 개발 프로그램에 의한 예측결과와 비교, 분석하였다. 또한 개발 프로그램을 이용하여 다층지반 해석과 관련된 기존 해석방법의 문제점 및 지반의 교란효과와 연직배수재의 부분관입조건, 점증적인 하중재하 조건등이 지반의 압밀거동에 미치는 영향에 대해 살펴보았다.

• The Journal of the Acoustical Society of Korea
• /
• v.22 no.2
• /
• pp.135-144
• /
• 2003

A method for the automatic segmentation of speech signals is described. The method is dedicated to the construction of a large database for a Text-To-Speech (TTS) synthesis system. The main issue of the work involves the refinement of an initial estimation of phone boundaries which are provided by an alignment, based on a Hidden Market Model(HMM). Multi-layer perceptron (MLP) was used as a phone boundary detector. To increase the performance of segmentation, a technique which individually trains an MLP according to phonetic transition is proposed. The optimum partitioning of the entire phonetic transition space is constructed from the standpoint of minimizing the overall deviation from hand labelling positions. With single speaker stimuli, the experimental results showed that more than 95% of all phone boundaries have a boundary deviation from the reference position smaller than 20 ms, and the refinement of the boundaries reduces the root mean square error by about 25%.

• Journal of Korea Water Resources Association
• /
• v.56 no.spc1
• /
• pp.1059-1069
• /
• 2023

Dam-break flow occurs when an elevated dam suddenly collapses, resulting in the catastrophic release of rapid and uncontrolled impounded water. This study compares laminar and turbulent closure models for simulating three-dimensional dam-break flows using OpenFOAM. The Reynolds-Averaged Navier-Stokes (RANS) model, specifically the k-ε model, is employed to capture turbulent dissipation. Two scenarios are evaluated based on a laboratory experiment and a modified multi-layered block obstacle scenario. Both models effectively represent dam-break flows, with the turbulent closure model reducing oscillations. However, excessive dissipation in turbulent models can underestimate water surface profiles. Improving numerical schemes and grid resolution enhances flow recreation, particularly near structures and during turbulence. Model stability is more significantly influenced by numerical schemes and grid refinement than the use of turbulence closure. The k-ε model's reliance on time-averaging processes poses challenges in representing dam-break profiles with pronounced discontinuities and unsteadiness. While simulating turbulence models requires extensive computational efforts, the performance improvement compared to laminar models is marginal. To achieve better representation, more advanced turbulence models like Large Eddy Simulation (LES) and Direct Numerical Simulation (DNS) are recommended, necessitating small spatial and time scales. This research provides insights into the applicability of different modeling approaches for simulating dam-break flows, emphasizing the importance of accurate representation near structures and during turbulence.

• Journal of the Korea Convergence Society
• /
• v.12 no.9
• /
• pp.11-19
• /
• 2021

A software system is required to change during its life cycle due to various requirements such as adding functionalities, fixing bugs, and adjusting to new computing environments. Such program code modification should be considered as carefully as a new system development becase unexpected software errors could be introduced. In addition, when reusing open source programs, we can expect higher quality software if code changes of the open source program are predicted in advance. This paper proposes a Convolutional Neural Network (CNN)-based deep learning model to predict source code changes. In this paper, the prediction of code changes is considered as a kind of a binary classification problem in deep learning and labeled datasets are used for supervised learning. Java projects and code change logs are collected from GitHub for training and testing datasets. Software metrics are computed from the collected Java source code and they are used as input data for the proposed model to detect code changes. The performance of the proposed model has been measured by using evaluation metrics such as precision, recall, F1-score, and accuracy. The experimental results show the proposed CNN model has achieved 95% in terms of F1-Score and outperformed the multilayer percept-based DNN model whose F1-Score is 92%.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.11 no.2
• /
• pp.117-129
• /
• 2009

Several researches have been done to estimate the earth pressure on a vertical circular shaft considering three dimensional arching effect and verified them by conducting model tests. However, any equation suggested so far is not applicable in case of multi-layered soils and/or C-${\phi}$ soils. In this study, new equation for estimating the earth pressure acting on the vertical shaft in c-${\phi}$ soils is proposed. A parametric study is performed to investigate the significance of the cohesion when estimating the coefficient of earth pressure in C-${\phi}$ soils and estimating earth pressures in vertical shafts. A method which can estimate the earth pressure on vertical shafts in layered soils is also proposed by assuming a failure surface in layered soils and using the modified equation. This paper is Part I of companion papers focusing on the theoretical aspect of model developments; the experimental verification will be made in Part II.