• Journal of Ocean Engineering and Technology
• /
• v.10 no.1
• /
• pp.65-74
• /
• 1996

Up to now, the existing crack growth modelling has used a mathematical approximation but an assumed function have a great influence on this method. Especially, crack growth behavior that shows very strong nonlinearity needed complicated function which has difficulty in setting parameter of it. The main characteristics of neural network modelling to engineering field are simple calculations and absence of assumed function. In this paper, after discussing learning and generalization of neural networks, we performed crack growth modelling on the basis of above learning algorithms. J'-da/dt relation predicted by neural networks shows that test condition with unlearned data is simulated well within estimated mean error(5%).

• 한국전산유체공학회:학술대회논문집
• /
• 2010.05a
• /
• pp.109-114
• /
• 2010

Interface tracking of two phase is significant to analyze multi-phase phenomena. The VOF(Volume of Fluid) and level set are well known interface tracking method. However, they have limitations to solve compressible flow and incompressible flow at the same time. CIP(Cubic Interpolate Propagation) method is appropriate for considering compressible and incompressible flow at once by solving the governing equation which is divided up into advection and non-advection term. In this article, we analyze the droplet impingement according to various We number using improved CIP method which treats nonlinear term once more comparison with original CIP method. Furthermore, we compare spread radius after droplet impingement on the wall with the experimental data and original CIP original CIP method, and it reduces the mass conservation error which is generated in the numerical analysis comparison with original CIP method.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2003.09a
• /
• pp.315-317
• /
• 2003

Neural oscillator is applied in oscillatory systems (Analysis of image information, Voice recognition. Etc...). If we apply established EBPA(Error back Propagation Algorithm) to oscillatory system, we are difficult to presume complicated input's patterns. Therefore, it requires more data at training, and approximation of convergent speed is difficult. In this paper, I studied the neural oscillator as synchronized states with appropriate phase relation between neurons and recognized the Korean alphabet using Neural Oscillator Phase model Synchronization.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.9
• /
• pp.4240-4258
• /
• 2016

A practical iterative channel estimation technique is proposed for the multiple-input-multiple-output orthogonal frequency division multiplexing (MIMO-OFDM) system in the high-speed mobile environment, such as high speed railway scenario. In the iterative algorithm, the Kalman filter and data detection are jointed to estimate the time-varying channel, where the detection error is considered as part of the noise in the Kalman recursion in each iteration to reduce the effect of the detection error propagation. Moreover, the employed Kalman filter is from the canonical state space model, which does not include the parameters of the autoregressive (AR) model, so the proposed method does not need to estimate the parameters of AR model, whose accuracy affects the convergence speed. Simulation results show that the proposed method is robust to the fast time-varying channel, and it can obtain more gains compared with the available methods.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.25 no.5
• /
• pp.425-430
• /
• 2015

This paper is a study to improve the classification efficiency of rotating objects by using deep neural networks to which a deep learning algorithm was applied. For the classification experiment of rotating objects, COIL-20 is used as data and total 3 types of classifiers are compared and analyzed. 3 types of classifiers used in the study include PCA classifier to derive a feature value while reducing the dimension of data by using Principal Component Analysis and classify by using euclidean distance, MLP classifier of the way of reducing the error energy by using error back-propagation algorithm and finally, deep learning applied DBN classifier of the way of increasing the probability of observing learning data through pre-training and reducing the error energy through fine-tuning. In order to identify the structure-specific error rate of the deep neural networks, the experiment is carried out while changing the number of hidden layers and number of hidden neurons. The classifier using DBN showed the lowest error rate. Its structure of deep neural networks with 2 hidden layers showed a high recognition rate by moving parameters to a location helpful for recognition.

• Journal of Korea Society of Industrial Information Systems
• /
• v.13 no.5
• /
• pp.168-177
• /
• 2008

The code propagation is one of the most important technic for software update in wireless sensor networks. This paper presents a new scheme for code propagation using network coding. The proposed code propagation method roughly shows 20$\sim$25% performance improvement according to network environments in terms of the number of data exchange compared with the previously proposed pipelining scheme. As a result, we can efficiently perform the software update from the viewpoint of speed, energy, and network congestion when the proposed code propagation system is applied. In addition, the proposed system solves the overhearing problems of network coding such as the loss of original messages and decoding error using the predefined message. Therefore, our system allows a software update system to exchange reliable data in wireless sensor networks.

• Magazine of the Korean Society of Agricultural Engineers
• /
• v.45 no.1
• /
• pp.102-114
• /
• 2003

The objectives of the paper are to evaluate cell based pollutant loadings for different storm events, to monitor the hydrology and water quality of the Baran HP#6 watershed, and to validate AGNPS with the field data. Simplification was made to AGNPS in estimating storm erosivity factors from a triangular rainfall distribution. GIS-AGNPS interface model consists of three subsystems; the input data processor based on a geographic information system. the models. and the post processor Land use patten at the tested watershed was classified from the Landsat TM data using the artificial neural network model that adopts an error back propagation algorithm. AGNPS model parameters were obtained from the GIS databases, and additional parameters calibrated with field data. It was then tested with ungauged conditions. The simulated runoff was reasonably in good agreement as compared with the observed data. And simulated water quality parameters appear to be reasonably comparable to the field data.

• Journal of Korea Water Resources Association
• /
• v.43 no.8
• /
• pp.721-731
• /
• 2010

The rainfall-runoff relationship is very difficult to predict because it is complicate factor affected by many temporal and spatial parameters of the basin. In recent, models which is based on artificial intelligent such as neural network, genetic algorithm fuzzy etc., are frequently used to predict discharge while stochastic or deterministic or empirical models are used in the past. However, the discharge data which are generally used for prediction as training and validation set are often estimated from rating curve which has potential error in its estimation that makes a problem in reliability. Therefore, in this study, water stage is predicted from antecedent rainfall and water stage data for short term using three models of neural network which trained by error back propagation algorithm and optimized by genetic algorithm and training error back propagation after it is optimized by genetic algorithm respectively. As the result, the model optimized by Genetic Algorithm gives the best forecasting ability which is not much decreased as the forecasting time increase. Moreover, the models using stage data only as the input data give better results than the models using precipitation data with stage data.

• Journal of Korean Society for Geospatial Information Science
• /
• v.9 no.2 s.18
• /
• pp.17-27
• /
• 2001

Buffering is one of the popular spatial analytical functions widely used in many proximity analyses. The buffeting inevitably entails a new polygon of specified edge that is simulated by rolling a ball around the buffering object. While buffering, the error on the buffering object propagates to the new buffered object. In this paper the error propagation behavior during the buffering operation is analyzed based on a pilot project for two different data models: polyline and spline curve. Thus, the error on the buffered objects are classified, mathematically defined, and measured. For measurements, the pilot project is designed and performed using a test site that is a lake boundary at Wisconsin, USA.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.45 no.10
• /
• pp.881-891
• /
• 2017

In this paper, we described the new TLE(Two Line Elements) generation method based on the compansation technique by using past TLEs(Two Line Elements) released by JSpOC(Joint Space Operation Center) in USA to reduce the orbit prediction error for long duration of SGP4(Simplified General Perturbations 4) which is a simplifed and analytical orbit propagator. The orbital residuals the orbital difference between two ephemeris for the first TLE only and for the all TLEs updated by JSpOC for the past some period was applied for this algorithm instead of general orbit determination software. Actually, in these orbital residuals, the trend of orbit prediction error from SGP4 is included. Thus, it is possible to make a simple residual function from these orbital residulas by using the fitting process. By using these residual functions with SGP4 prediction data for the currnet TLE data, the compansated orbit prediction can be reconstructed and the orbit prediction error for long duration of SGP4 is also reduced. And it is possible to generate new TLE data from it. In this paper, we demonstraed this algorithm in simple simulation, and the orbital error is decreased dramatically from 4km for the SGP4 propagation to 2km for it during 7 days as a result.