• The KIPS Transactions:PartB
• /
• v.13B no.3 s.106
• /
• pp.345-352
• /
• 2006

The practical English-Korean machine translation system should be able to translate long sentences quickly and accurately. The intra-sentence segmentation method has been proposed and contributed to speeding up the syntactic analysis. This paper proposes the syntactic category prediction method using decision trees for getting accurate parsing results. In parsing with segmentation, the segment is separately parsed and combined to generate the sentence structure. The syntactic category prediction would facilitate to select more accurate analysis structures after the partial parsing. Thus, we could improve the parsing accuracy by the prediction. We construct features for predicting syntactic categories from the parsed corpus of Wall Street Journal and generate decision trees. In the experiments, we show the performance comparisons with the predictions by human-built rules, trigram probability and neural networks. Also, we present how much the category prediction would contribute to improving the translation quality.

• Journal of Electrical Engineering and Technology
• /
• v.13 no.5
• /
• pp.1841-1851
• /
• 2018

For the safe and stable operation of the power system, accurate wind power prediction is of great significance. A wind power prediction method based on empirical mode decomposition and improved extreme learning machine is proposed in this paper. Firstly, wind power time series is decomposed into several components with different frequency by empirical mode decomposition, which can reduce the non-stationary of time series. The components after decomposing remove the long correlation and promote the different local characteristics of original wind power time series. Secondly, an improved extreme learning machine prediction model is introduced to overcome the sample data updating disadvantages of standard extreme learning machine. Different improved extreme learning machine prediction model of each component is established. Finally, the prediction value of each component is superimposed to obtain the final result. Compared with other prediction models, the simulation results demonstrate that the proposed prediction method has better prediction accuracy for wind power.

• Structural Engineering and Mechanics
• /
• v.18 no.3
• /
• pp.363-376
• /
• 2004

The present study provides a relatively simple and accurate analytical model for the prediction of time-dependent stresses and curvatures of cracked R.C. sections under working loads. A more simplified solution is also provided. The proposed models are demonstrated by considering a numerical example and conducting a parametric study on the effects of relevant R.C. design parameters. In contrary to tension reinforcement, the compression reinforcement is found to contribute significantly in reducing tensile stresses in tension steel and in reducing the total section curvatures. The good accuracy of the proposed approximate solution opens a new vision towards a simple yet accurate model for the prediction of time-dependent effects in R.C. structures.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.26 no.8
• /
• pp.1088-1094
• /
• 2002

A channel flow with a high Reynolds number but coarse grids is numerically studied to investigate the prediction possibility of its turbulence which is three-dimensional and time-dependent. In the present paper, a Reynolds-Averaged Navier-Stokes (RANS) model, a Large Eddy Simulation (LES) and a Navier-Stokes equation with no model are tested with a new approach of hybrid RANS/LES, which reduces to RANS model in the boundary layers and at separation, and to Smagorinsky-like LES downstream of separation, and then compared with each other. It is found that the simulations of hybrid RANS/LES method sustain turbulence like those of LES and with no model, and the results are stable and fairly accurate. This indicates strongly that gradual improvements could lead to a simple, stable, and accurate approach to predict turbulence phenomena of wall-bounded flow.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2017.11a
• /
• pp.145-147
• /
• 2017

Tracking filter plays a key role in accurate estimation and prediction of maneuvering vessel's dynamics. The third-order ${\alpha}-{\beta}-{\gamma}$ filter is one of the special cases of the general solution provided by the Kalman filter. Fading memory algorithm performs a better performance in numerous of ${\alpha}-{\beta}-{\gamma}$ filter algorithms. This study aims to optimize the fourth-order fading memory algorithm ${\alpha}-{\beta}-{\gamma}-{\eta}$ filter, which is extended form ${\alpha}-{\beta}-{\gamma}$ filter, to get much more accurate position of high dynamic target on the condition that the own ship is also high dynamic.

• Proceedings of the KIEE Conference
• /
• 1999.07c
• /
• pp.1088-1090
• /
• 1999

The radio noise produced by corona discharge in high voltage transmission tines is one of the most important line design considerations. Therefore it is necessary to pre-evaluate radio noise for transmission line designers using Prediction formulas or field test results. In this Paper, more accurate and useful formulas for Predicting radio noise during fair and foul weathers in AC transmission lines were proposed through comparison with the existing formulas. Also it was verified by comparing with the long-term measured data from operating lines that the Proposed formulas are very accurate. The Proposed prediction formulas are developed by the applications of nonlinear least square optimization method to radio noise database collected from lines throughout the world.

• 한국전산유체공학회:학술대회논문집
• /
• 2008.03b
• /
• pp.13-16
• /
• 2008

After the collapse of the Tacoma bay bridge at Tacoma Washington, the accurate prediction of aerodynamics became crucial to the sound design of bridges. CFD(Computational Fluid Dynamics) becomes important tool for the prediction on wind effects on the bridge due to the recent development of CFD. The usage of CFD is further prompted by the advantages in using CFD, such as low-cost and fast feed-back of design. In this paper, an unsteady compressible Reynolds averaged Navier-Stokes code is used for the computation of the flow over bridges. Coakley's ��q-${\omega}$ �� two-equation turbulence model is used for the turbulent eddy viscosity. For accurate and stable computations, the local preconditioning method is adapted to the code. Aerodynamic characteristics of a couple bridges are presented to show the validity and the accuracy of the method.

• Journal of the Korean Institute of Electrical and Electronic Material Engineers
• /
• v.14 no.3
• /
• pp.241-245
• /
• 2001

In this paper, we present parameter optimization technique for GaAs/AlGaAs multiple quantum well avalanche photodiodes used for image capture mechanism in high-definition system. Even under flawless environment in semiconductor manufacturing process, random variation in process parameters can bring the fluctuation to device performance. The precise modeling for this variation is thus required for accurate prediction of device performance. The precise modeling for this variation is thus required for accurate prediction of device performance. This paper will first use experimental design and neural networks to model the nonlinear relationship between device process parameters and device performance parameters. The derived model was then put into genetic algorithms to acquire optimized device process parameters. From the optimized technique, we can predict device performance before high-volume manufacturign, and also increase production efficiency.

• Proceedings of the SAREK Conference
• /
• 2008.06a
• /
• pp.523-528
• /
• 2008

The accurate distribution of flow rate has been a very important part to control the air change rate since introduction of house ventilation system. An inappropriate selection of fan due to incorrect prediction of pressure loss in duct brings energy loss. In the previous study the pressure loss of general spiral duct was measured and database was constructed for finding correct loss factors in fitting upper stream. The purpose of this study is to compare and investigate the error range of flow rate by applying T-Method to bilateral symmetry and asymmetry layout of duct. The results of this study are as following. It is demanded to decide accurate size under duct design for house ventilation system. Because the small amount of Flow rate was considered at that time. The error range was 3.17% on case1 and 3.52% on case2. The error range difference was 0.35%.

• International conference on construction engineering and project management
• /
• 2005.10a
• /
• pp.935-940
• /
• 2005

This paper presents the results of a statistical analysis using historical data of cost contingency. As a result, a model that predicts and estimates an accurate cost contingency value using the least squares estimation method was developed. Data such as original contract amounts, estimated contingency amounts set by maximum funding limits, and actual contingency amounts, were collected and used for model development. The more effective prediction model was selected from the two developed models based on its prediction capability. The model would help guide project managers making financial decisions when the determination of the cost contingency amounts for multiple projects is necessary.