• Atmosphere
• /
• v.16 no.4
• /
• pp.259-267
• /
• 2006

In the present study, the neural network (NN) model with cluster analysis method was developed to predict storm surge in the whole Korean coastal regions with special focuses on the regional extension. The model used in this study is NN model for each cluster (CL-NN) with the cluster analysis. In order to find the optimal clustering of the stations, agglomerative method among hierarchical clustering methods was used. Various stations were clustered each other according to the centroid-linkage criterion and the cluster analysis should stop when the distances between merged groups exceed any criterion. Finally the CL-NN can be constructed for predicting storm surge in the cluster regions. To validate model results, predicted sea level value from CL-NN model was compared with that of conventional harmonic analysis (HA) and of the NN model in each region. The forecast values from NN and CL-NN models show more accuracy with observed data than that of HA. Especially the statistics analysis such as RMSE and correlation coefficient shows little differences between CL-NN and NN model results. These results show that cluster analysis and CL-NN model can be applied in the regional storm surge prediction and developed forecast system.

• Communications for Statistical Applications and Methods
• /
• v.25 no.6
• /
• pp.659-671
• /
• 2018

In this study, we consider the extension of the heterogeneous autoregressive (HAR) model for realized volatility by incorporating a neural network (NN) structure. Since HAR is a linear model, we expect that adding a neural network term would explain the delicate nonlinearity of the realized volatility. Three neural network-based HAR models, namely HAR-NN, $HAR({\infty})-NN$, and HAR-AR(22)-NN are considered with performance measured by evaluating out-of-sample forecasting errors. The results of the study show that HAR-NN provides a slightly wider interval than traditional HAR as well as shows more peaks and valleys on the turning points. It implies that the HAR-NN model can capture sharper changes due to higher volatility than the traditional HAR model. The HAR-NN model for prediction interval is therefore recommended to account for higher volatility in the stock market. An empirical analysis on the multinational realized volatility of stock indexes shows that the HAR-NN that adds daily, weekly, and monthly volatility averages to the neural network model exhibits the best performance.

• Journal of Korean Society for Quality Management
• /
• v.49 no.2
• /
• pp.201-211
• /
• 2021

Purpose: This paper proposes a density adaptive grid algorithm for the k-NN regression model to reduce the computation time for large datasets without significant prediction accuracy loss. Methods: The proposed method utilizes the concept of the grid with centroid to reduce the number of reference data points so that the required computation time is much reduced. Since the grid generation process in this paper is based on quantiles of original variables, the proposed method can fully reflect the density information of the original reference data set. Results: Using five real-life datasets, the proposed k-NN regression model is compared with the original k-NN regression model. The results show that the proposed density adaptive grid-based k-NN regression model is superior to the original k-NN regression in terms of data reduction ratio and time efficiency ratio, and provides a similar prediction error if the appropriate number of grids is selected. Conclusion: The proposed density adaptive grid algorithm for the k-NN regression model is a simple and effective model which can help avoid a large loss of prediction accuracy with faster execution speed and fewer memory requirements during the testing phase.

• Journal of Intelligence and Information Systems
• /
• v.13 no.2
• /
• pp.1-14
• /
• 2007

Case-based reasoning (CBR) is one of the most widely applied data mining techniques and has proven its effectiveness in various domains. Since CBR is basically based on k-Nearest Neighbors (NN) method, the value of k affects the performance of CBR model directly. Once the value of k is set, it is fixed for the lifetime of the CBR model. However, if the value is set greater or smaller than the optimal value, the performance of CBR model will be deteriorated. In this research, we propose a new method of composing the NN set using similarity scores as themselves, which we shall call s-NN method, rather than using the fixed value of k. In the s-NN method, the different number of nearest neighbors can be selected for each new case. Performance evaluation using the data from UCI Machine Learning Repository shows that the CBR model adopting the s-NN method outperforms the CBR model adopting the traditional k-NN method.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2020.11a
• /
• pp.237-240
• /
• 2020

The fine-tuned neural network (NN) model for a whole temporal portion in a video does not always yield the best quality (e.g., PSNR) performance over all regions of each frame in the temporal period. For certain regions (usually homogeneous regions) in a frame for super-resolution (SR), even a simple bicubic interpolation method may yield better PSNR performance than the fine-tuned NN model. When there are multiple NN models available at the receivers where each NN model is trained for a group of images having a specific category of image characteristics, the performance of Quality enhancement can be improved by selectively applying an appropriate NN model for each image region according to its image characteristic category to which the NN model was dedicatedly trained. In this case, it is necessary to signal which NN model is applied for each region. This is very advantageous for image restoration and quality enhancement (IRQE) applications at user terminals with limited computing capabilities.

• Computers and Concrete
• /
• v.12 no.2
• /
• pp.229-241
• /
• 2013

The objective of this study is to reveal the sufficiency of neural networks (NN) as a securer, quicker, more robust and reliable method to be used in seismic assessment of existing reinforced concrete buildings. The NN based approach is applied as an alternative method to determine the seismic performance of each existing RC buildings, in terms of damage level. In the application of the NN, a multilayer perceptron (MLP) with a back-propagation (BP) algorithm is employed using a scaled conjugate gradient. NN based model wasd eveloped, trained and tested through a based MATLAB program. The database of this model was developed by using a statistical procedure called P25 method. The NN based model was also proved by verification set constituting of real existing RC buildings exposed to 2003 Bingol earthquake. It is demonstrated that the NN based approach is highly successful and can be used as an alternative method to determine the seismic performance of each existing RC buildings.

• Proceedings of the Korean Geotechical Society Conference
• /
• 2009.03a
• /
• pp.456-463
• /
• 2009

The preconsolidation pressure has been commonly determined by oedometer test. However, it can also be determined by in-situ test, such as piezocone test with theoretical and(or) empirical correlations. Recently, Neural Network(NN) theory was applied and some models were proposed to estimate the preconsolidation pressure or OCR. However, since the optimization process of synaptic weights of NN model is dependent on the initial synaptic weights, NN models which are trained with different initial weights can't avoid the variability on prediction result for new database even though they have same structure and use same transfer function. In this study, Committee Neural Network(CNN) model is proposed to improve the initial weight dependency of multi-layered neural network model on the prediction of preconsolidation pressure of soft clay from piezocone test result. It was found that even though the NN model has the optimized structure for given training data set, it still has the initial weight dependency, while the proposed CNN model can improve the initial weight dependency of the NN model and provide a consistent and precise inference result than existing NN models.

• Journal of radiological science and technology
• /
• v.45 no.2
• /
• pp.111-116
• /
• 2022

In this study, the applicability of machine learning for the development of a simulator for general X-ray examination education is evaluated. To this end, k-nearest neighbor(kNN), support vector machine(SVM) and neural network(NN) classification models are analyzed to present the most suitable model by analyzing the results. Image data was obtained by taking 100 photos each corresponding to Posterior anterior(PA), Posterior anterior oblique(Obl), Lateral(Lat), Fan lateral(Fan lat). 70% of the acquired 400 image data were used as training sets for learning machine learning models and 30% were used as test sets for evaluation. and prediction model was constructed for right-handed PA, Obl, Lat, Fan lat image classification. Based on the data set, after constructing the classification model using the kNN, SVM, and NN models, each model was compared through an error matrix. As a result of the evaluation, the accuracy of kNN was 0.967 area under curve(AUC) was 0.993, and the accuracy of SVM was 0.992 AUC was 1.000. The accuracy of NN was 0.992 and AUC was 0.999, which was slightly lower in kNN, but all three models recorded high accuracy and AUC. In this study, right-handed PA, Obl, Lat, Fan lat images were classified and predicted using the machine learning classification models, kNN, SVM, and NN models. The prediction showed that SVM and NN were the same at 0.992, and AUC was similar at 1.000 and 0.999, indicating that both models showed high predictive power and were applicable to educational simulators.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.13 no.3
• /
• pp.66-77
• /
• 2014

UTIS(Urban Traffic Information System) directly collects link travel time in urban area by using probe vehicles. Therefore it can estimate more accurate link travel speed compared to other traffic detection systems. However, UTIS includes some missing data caused by the lack of probe vehicles and RSEs on road network, system failures, and other factors. In this study, we suggest a new model, based on k-NN algorithm, for imputing missing data to provide more accurate travel time information. New imputation model is an adaptive k-NN which can flexibly adjust the number of nearest neighbors(NN) depending on the distribution of candidate objects. The evaluation result indicates that the new model successfully imputed missing speed data and significantly reduced the imputation error as compared with other models(ARIMA and etc). We have a plan to use the new imputation model improving traffic information service by applying UTIS Central Traffic Information Center.

• Journal of the Korea Safety Management & Science
• /
• v.8 no.3
• /
• pp.1-9
• /
• 2006

Recently data mining techniques have been used for analysis and classification of data related to industrial accidents. The main objective of this study is to compare algorithms for data analysis of industrial accidents and this paper provides an optimal predicting model of 5 kinds of algorithms including CHAID, CART, C4.5, LR (Logistic Regression) and NN (Neural Network) with ROC chart, lift chart and response threshold. Also, this paper provides an approximation model for an optimal predicting model based on NN. The approximation model provided in this study can be utilized for easy interpretation of data analysis using NN. This study uses selected ten independent variables to group injured people according to a dependent variable in a way that reduces variation. In order to find an optimal predicting model among 5 algorithms, a retrospective analysis was performed in 67,278 subjects. The sample for this work chosen from data related to industrial accidents during three years ($2002\;{\sim}\;2004$) in korea. According to the result analysis, NN has excellent performance for data analysis and classification of industrial accidents.