• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.38 no.2
• /
• pp.20-30
• /
• 2001

In the paper, we propose a predictive control scheme using multiple neural network-based prediction models. To construct the multiple models, we select several specific values of a parameter whose variation affects serious control performance in the plant. Among the multiple prediction models, we choose one that shows the best predictions for future outputs of the plant by a switching technique. Based on a nonlinear programming method, we calculate the current process input in the nonlinear predictive control system with multiple prediction models. The proposed control method is shown to be very effective when a parameter of the plant changes or the time delay, if it exists, varies. It is also shown that the proposed method is successfully applied for the control of suspension in a electro-magnetic levitation system.

• Proceedings of the Korean Information Science Society Conference
• /
• 2007.10d
• /
• pp.160-165
• /
• 2007

무선 센서 망에서 다중싱크 이동성에 관련된 연구는 단순히 독립된 단일싱크 이동성 확장에 기인한다. 하지만, 다중 싱크의 경우 싱크 상호간의 이동 결집도에 따라 두 가지 그룹으로 분류될 수 있다: 싱크간의 산재된 싱크그룹(loosely coupled sink group)과 밀집된 싱크그룹(tightly coupled sink group)이다. 전자는 기존 다중싱크 연구에서 가정하고 있는 일반적인 모델이다. 반면, 후자의 예로는 전쟁터에서 동일한 작전을 수행하는 작은 분대 단위의 군인들의 이동성 등이 있다. 본 논문은 밀집된 싱크그룹 이동성을 갖는 다중 싱크를 위한 데이터전달 프로토콜을 제안한다.

• Tunnel and Underground Space
• /
• v.33 no.6
• /
• pp.594-609
• /
• 2023

TBM (Tunnel Boring Machine) method is gaining popularity in urban and underwater tunneling projects due to its ability to ensure excavation face stability and minimize environmental impact. Among the prominent models for predicting disc cutter life, the NTNU model uses the Cutter Life Index(CLI) as a key parameter, but the complexity of testing procedures and rarity of equipment make measurement challenging. In this study, CLI was predicted using multiple linear regression analysis and tree-based machine learning techniques, utilizing rock properties. Through literature review, a database including rock uniaxial compressive strength, Brazilian tensile strength, equivalent quartz content, and Cerchar abrasivity index was built, and derived variables were added. The multiple linear regression analysis selected input variables based on statistical significance and multicollinearity, while the machine learning prediction model chose variables based on their importance. Dividing the data into 80% for training and 20% for testing, a comparative analysis of the predictive performance was conducted, and XGBoost was identified as the optimal model. The validity of the multiple linear regression and XGBoost models derived in this study was confirmed by comparing their predictive performance with prior research.

• Proceedings of the Korean Information Science Society Conference
• /
• 2003.10a
• /
• pp.625-627
• /
• 2003

역할기반 접근통제(RBAC)모델은 쉬운 관리성과 정책 적용의 유연성, 그리고 정책 중립적인 이점으로 인하여, 현재 많은 컴퓨팅 환경에서 적용되고 있다. 하지만 기존에 연구되었던 RBAC 모델들은 대부분 단일 보안 관리를 가정하므로 최근의 협업 컴퓨팅 환경을 위한 접근통제를 설계하는 데 문제가 있다. 본 논문에서는 협업 컴퓨팅 환경을 다중 도메인 보안(Multi-Domain Security)으로 사상하고, 협업환경을 적절하게 고려하지 않은 RBAC의 적용이 야기할 수 있는 문제점들을 살펴본다.

• The Journal of the Acoustical Society of Korea
• /
• v.12 no.1E
• /
• pp.12-19
• /
• 1993

덕트에서의 능동소음감쇄 문제를 다루었다. 음향귀환이 있는 경우의 덕트를 중첩의 원리를 이용하여 모델링하였다. 본 논문에서 다루어진 능동소음제어를 위한 덕트모델은 consistent하다고 가정했다. 스피커와 오차 마이크로폰 사이의 2차 경로 전달함수를 추정하기 위한 새로운 알고리즘을 제안했으며 제안된 알고리즘은 기존의 알고리즘보다 계산양이 작아 다중 채널 능동소음제어에도 이용될 수 있으리라 생각된다. 제안된 알고리즘의 효율성을 보이기 위하여 컴퓨터 시뮬레이션을 행했다.

• Journal of the Korea Society for Simulation
• /
• v.25 no.3
• /
• pp.15-28
• /
• 2016

It is necessary to analyze underwater acoustics channel(UAC) modeling and simulation for underwater weapon system development and acquisition. In order to analyze UAC, there are underwater acoustics propagation numerical analysis models(Ray theory, Parabolic equation, Normal-mode, Wavenumber integration). However, If these models are used for multiple frequency signal analysis, they are inaccurate to calculate result of analysis effectiveness and restricted for signal processing and analysis. In this paper, to overcome this problem, we propose simple/multiple frequency signal analysis model of the Pseudospectral Time-Domain Method synthetic environment UAC applied to underwater environment noise model as like as realistic underwater environment. In order to confirm the validation of the model, we performed the 9 scenarios simulation(4 scenarios of single frequency signal, 4 scenarios of multiple frequency signal, 1 scenario of single/multiple frequency signal like submarine radiated noise) for validation and confirmed the validation of this model through the simulation model.

• Annual Conference of KIPS
• /
• 2023.11a
• /
• pp.621-623
• /
• 2023

본 연구는 당뇨병성 망막증의 자동 분류를 위해 딥러닝 모델을 활용한다. CLAHE 를 사용한 전처리로 이미지의 대비를 향상시켰으며, ResNet50 모델을 기반으로 한 전이학습을 통해 모델의 성능을 향상했다. 또한, 데이터의 불균형을 고려하여 정확도 뿐만 아니라 민감도와 특이도를 평가함으로써 모델의 분류 성능을 종합적으로 평가하였다. 실험 결과, 제안한 방법은 당뇨병성 망막증 분류 작업에서 높은 정확도를 달성하였으나, 양성 클래스의 식별에서 일부 한계가 있었다. 이에 데이터의 품질 개선과 불균형 데이터 처리에 초점을 맞춘 향후 연구 방향을 제시하였다.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.36 no.2
• /
• pp.125-135
• /
• 2012

The FE model for shot peening often assume that shots impact vertically on the engineering parts to generate compressive residual stresses. However, the shots obliquely impact on the surface in actual peening. In this work, we propose a 3D finite element (FE) model for evaluation of residual stress under angled shot peening. Using the FE model for angled multi-impact, we examine the effects of factors such as impact angle, impact pattern and the number of shots. Plastic deformation of shot is also considered. To validate the model, we then compare the FE solution with experimental result by X-ray diffraction (XRD). The proposed model will be a base of 3D multi-impact FE model with diverse impact angles.

• Journal of the Korean Society of Hazard Mitigation
• /
• v.9 no.2
• /
• pp.1-9
• /
• 2009

Water binder ratio combine high-performance concrete shrinkage of less than 0.4 to determine the transformation to a total shrinkage of water to move outside and internal consumption of moisture due to drying shrinkage and autogenous shrinkage, and then, the relative humidity changes and strain to be approached by surface physics describe the relationship between self-desiccation and autogenous shrinkage was set. To verify the self-desiccation in the humidity shrinkage and humidity measurements performed, and the research model, Tazawa, CEB-FIP model than to let the measure and the most similar results in this study based on self-desiccation model, autogenous shrinkage didn't represent the linear shrinkage by the drying shrinkage of the external moving but exponential relationships, unlike with the nature and rapid in the early age properly describes the attributes in shrinkage could see. After this research to move moisture and to reflect the shrinkage model, temperature, moisture transfer, strain analysis by multi-physics model is very similar to the results of mock-up specimen measurements performed for this research, the value measured by the internal consumption of moisture, therefore self-desiccation and a multi-physics model considering autogenous shrinkage might be relevant.

• Journal of the Korea Society for Simulation
• /
• v.18 no.4
• /
• pp.137-148
• /
• 2009

The purpose of this study is to implement variable selection algorithm which helps construct a reliable linear regression model. If we use all candidate variables to construct a linear regression model, the significance of the model will be decreased and it will cause 'Curse of Dimensionality'. And if the number of data is less than the number of variables (dimension), we cannot construct the regression model. Due to these problems, we consider the variable selection problem as a combinatorial optimization problem, and apply GA (Genetic Algorithm) to the problem. Typical measures of estimating statistical significance are $R^2$, F-value of regression model, t-value of regression coefficients, and standard error of estimates. We design GA to solve multi-objective functions, because statistical significance of model is not to be estimated by a single measure. We perform experiments using simulation data, designed to consider various kinds of situations. As a result, it shows better performance than LARS (Least Angle Regression) which is an algorithm to solve variable selection problems. We modify algorithm to solve portfolio selection problem which construct portfolio by selecting stocks. We conclude that the algorithm is able to solve real problems.