• Smart Structures and Systems
• /
• v.24 no.6
• /
• pp.733-744
• /
• 2019

Wind speed forecasting is critical for a variety of engineering tasks, such as wind energy harvesting, scheduling of a wind power system, and dynamic control of structures (e.g., wind turbine, bridge, and building). Wind speed, which has characteristics of random, nonlinear and uncertainty, is difficult to forecast. Nowadays, machine learning approaches (generalized regression neural network (GRNN), back propagation neural network (BPNN), and extreme learning machine (ELM)) are widely used for wind speed forecasting. In this study, two schemes are proposed to improve the forecasting performance of machine learning approaches. One is that optimization algorithms, i.e., cross validation (CV), genetic algorithm (GA), and particle swarm optimization (PSO), are used to automatically find the optimal model parameters. The other is that the combination of different machine learning methods is proposed by finite mixture (FM) method. Specifically, CV-GRNN, GA-BPNN, PSO-ELM belong to optimization algorithm-assisted machine learning approaches, and FM is a hybrid machine learning approach consisting of GRNN, BPNN, and ELM. The effectiveness of these machine learning methods in wind speed forecasting are fully investigated by one-year field monitoring data, and their performance is comprehensively compared.

• Geomechanics and Engineering
• /
• v.12 no.3
• /
• pp.441-464
• /
• 2017

The determination of the mixture parameters of stabilization has become a great concern in geotechnical applications. This paper presents an effort about the application of artificial intelligence (AI) techniques including radial basis neural network (RBNN), multi-layer perceptrons (MLP), generalized regression neural network (GRNN) and adaptive neuro-fuzzy inference system (ANFIS) in order to predict the unconfined compressive strength (UCS) of silty soil stabilized with bottom ash (BA), jute fiber (JF) and steel fiber (SF) under different freeze-thaw cycles (FTC). The dosages of the stabilizers and number of freeze-thaw cycles were employed as input (predictor) variables and the UCS values as output variable. For understanding the dominant parameter of the predictor variables on the UCS of stabilized soil, a sensitivity analysis has also been performed. The performance measures of root mean square error (RMSE), mean absolute error (MAE) and determination coefficient ($R^2$) were used for the evaluations of the prediction accuracy and applicability of the employed models. The results indicate that the predictions due to all AI techniques employed are significantly correlated with the measured UCS ($p{\leq}0.05$). They also perform better predictions than nonlinear regression (NLR) in terms of the performance measures. It is found from the model performances that RBNN approach within AI techniques yields the highest satisfactory results (RMSE = 55.4 kPa, MAE = 45.1 kPa, and $R^2=0.988$). The sensitivity analysis demonstrates that the JF inclusion within the input predictors is the most effective parameter on the UCS responses, followed by FTC.

• Proceedings of the KIEE Conference
• /
• 2000.07d
• /
• pp.2744-2746
• /
• 2000

일반화된 회귀 신경망을 이용하여 반도체 공정 최적화를 위한 플라즈마를 모델링한다. 플라즈마는 Box-W린son 실험계획표에 의해 특성화되었으며, 여기에서 변화시킨 인자로는 소스전력, 압력, 척지지대의 위치, 그리고 염소의 유량이다. 총 24회의 실험이 수행이 되었으며, 플라즈마 변수는 Langmuir Probe를 이용하여 측정하였다. 측정된 주요 플라즈마 변수로는 전자밀도, 전자온도, 그리고 플라즈마 전위이다. 폭변수를 점진적으로 증가시켜 회귀신경망을 최적화하였으며. 최적화된 모델은 통계적인 반응표면모델과 비교하였다. 비교 결과, 회귀신경망은 반응표면모델에 상응하는 예측능력을 보이고 있음을 알 수 있었다.

• Journal of Intelligence and Information Systems
• /
• v.23 no.3
• /
• pp.139-153
• /
• 2017

Corporate bankruptcy can cause great losses not only to stakeholders but also to many related sectors in society. Through the economic crises, bankruptcy have increased and bankruptcy prediction models have become more and more important. Therefore, corporate bankruptcy has been regarded as one of the major topics of research in business management. Also, many studies in the industry are in progress and important. Previous studies attempted to utilize various methodologies to improve the bankruptcy prediction accuracy and to resolve the overfitting problem, such as Multivariate Discriminant Analysis (MDA), Generalized Linear Model (GLM). These methods are based on statistics. Recently, researchers have used machine learning methodologies such as Support Vector Machine (SVM), Artificial Neural Network (ANN). Furthermore, fuzzy theory and genetic algorithms were used. Because of this change, many of bankruptcy models are developed. Also, performance has been improved. In general, the company's financial and accounting information will change over time. Likewise, the market situation also changes, so there are many difficulties in predicting bankruptcy only with information at a certain point in time. However, even though traditional research has problems that don't take into account the time effect, dynamic model has not been studied much. When we ignore the time effect, we get the biased results. So the static model may not be suitable for predicting bankruptcy. Thus, using the dynamic model, there is a possibility that bankruptcy prediction model is improved. In this paper, we propose RNN (Recurrent Neural Network) which is one of the deep learning methodologies. The RNN learns time series data and the performance is known to be good. Prior to experiment, we selected non-financial firms listed on the KOSPI, KOSDAQ and KONEX markets from 2010 to 2016 for the estimation of the bankruptcy prediction model and the comparison of forecasting performance. In order to prevent a mistake of predicting bankruptcy by using the financial information already reflected in the deterioration of the financial condition of the company, the financial information was collected with a lag of two years, and the default period was defined from January to December of the year. Then we defined the bankruptcy. The bankruptcy we defined is the abolition of the listing due to sluggish earnings. We confirmed abolition of the list at KIND that is corporate stock information website. Then we selected variables at previous papers. The first set of variables are Z-score variables. These variables have become traditional variables in predicting bankruptcy. The second set of variables are dynamic variable set. Finally we selected 240 normal companies and 226 bankrupt companies at the first variable set. Likewise, we selected 229 normal companies and 226 bankrupt companies at the second variable set. We created a model that reflects dynamic changes in time-series financial data and by comparing the suggested model with the analysis of existing bankruptcy predictive models, we found that the suggested model could help to improve the accuracy of bankruptcy predictions. We used financial data in KIS Value (Financial database) and selected Multivariate Discriminant Analysis (MDA), Generalized Linear Model called logistic regression (GLM), Support Vector Machine (SVM), Artificial Neural Network (ANN) model as benchmark. The result of the experiment proved that RNN's performance was better than comparative model. The accuracy of RNN was high in both sets of variables and the Area Under the Curve (AUC) value was also high. Also when we saw the hit-ratio table, the ratio of RNNs that predicted a poor company to be bankrupt was higher than that of other comparative models. However the limitation of this paper is that an overfitting problem occurs during RNN learning. But we expect to be able to solve the overfitting problem by selecting more learning data and appropriate variables. From these result, it is expected that this research will contribute to the development of a bankruptcy prediction by proposing a new dynamic model.

• Structural Engineering and Mechanics
• /
• v.71 no.6
• /
• pp.739-749
• /
• 2019

This article deals with the application of reliability analysis for determining the safety of simply supported beam under the uniformly distributed load. The uncertainties of the existing methods were taken into account and hence reliability analysis has been adopted. To accomplish this aim, Generalized Regression Neural Network (GRNN), Extreme Learning Machine (ELM) and Gaussian Process Regression (GPR) models are developed. Reliability analysis is the probabilistic style to determine the possibility of failure free operation of a structure. The application of probabilistic mathematics into the quantitative aspects of a structure and improve the qualitative aspects of a structure. In order to construct the GRNN, ELM and GPR models, the dataset contains Modulus of Elasticity (E), Load intensity (w) and performance function (${\delta}$) in which E and w are inputs and ${\delta}$ is the output. The achievement of the developed models was weighed by various statistical parameters; one among the most primitive parameter is Coefficient of Determination ($R^2$) which has 0.998 for training and 0.989 for testing. The GRNN outperforms the other ELM and GPR models. Other different statistical computations have been carried out, which speaks out the errors and prediction performance in order to justify the capability of the developed models.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.29 no.2B
• /
• pp.111-120
• /
• 2009

A local scour around a bridge pier is known as one of important factors of bridge collapse. Two approaches are usually used in estimating a scour depth in practice. One is to use empirical formulas, and the other is to use computational methods. But the use of empirical formulas is limited to predict a scour depth under similar conditions to which the formulas were derived. Computational methods are currently too expensive to be applied to practical engineering problems. This study presented the application of artificial neural networks (ANN) to the prediction of a scour depth around a bridge pier at an equilibrium state. This study also investigated various ANN algorithms for estimating a scour depth, such as Backpropagation Network, Radial Basis Function Network, and Generalized Regression Network. Preliminary study showed that ANN models resulted in very wide range of errors in predicting a scour depth. To solve this problem this study incorporated cluster analysis into ANN. The incorporation of cluster analysis provided better estimations of scour depth up to 42% compared with other approaches.

• Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
• /
• 2004.07b
• /
• pp.1117-1120
• /
• 2004

경제적인 공정분석과 최적화를 위해서는 컴퓨터를 이용한 플라즈마 예측모델이 요구되고 있다. 본 연구에서는 일반화된 회귀 신경망 (GRNN)을 이용하여 플라즈마 증착공정 모델을 개발한다. GRNN의 예측성능은 패턴층 뉴런의 가우시안 함수를 구성하는 학습인자, 즉 spread에 의존한다. 종래의 모델에서는 모든 가우시안 함수의 spread가 동일한 값에서 최적화되었으며, 이로 인해 모델의 예측성능을 향상시키는 데에는 한계가 있었다. 본 연구에서는 유전자 알고리즘 (GA)를 이용하여 다변수 spread를 최적화하는 기법을 개발하였으며, 그 성능을 PECVD 공정에 의해 증착된 SiN 박막의 증착률에 적용하여 평가하였다. $2^{6-1}$ 부분인자 실험계획법에 의해 수집된 데이터를 이용하여 신경망을 학습하였고, 모델적합성 점검을 위해 별도의 12번의 실험을 수행하였다. 가우시안 함수의 spread는 0.2에서 2.0까지 0.2간격으로 증가시켰으며, 최적화한 GA-GRNN모델의 예측성능은 6.6 ${\AA}/min$이었다. 이는 종래의 방식으로 최적화한 모델의 예측성능 (13.5 ${\AA}/min$)과 비교하여 50.7% 향상된 예측성능이며, 이러한 향상은 제안한 GA-GRNN 모델이 플라즈마 공정 모델의 예측성능을 증진하는데 매우 효과적임을 보여준다.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.11 no.3
• /
• pp.28-38
• /
• 2008

The purpose of this study are to compare existing presence-absence predictive models and to predict suitable habitat for Goral (Nemorhaedus caudatus raddeanus) that is an endangered and protected species in Seoraksan national park using the best model among existing predictive models. The methods of this study are as follows. First, 375 location data and 9 environmental data layers were implemented to build a model. Secondly, 4 existing presence-absence models : Generalized Linear Model (GLM), Generalized Addictive Model (GAM), Classification and Regression Tree (CART), and Artificial Neural Network (ANN) were tested to predict the Goal habitat. Thirdly, ROC (Receiver Operating Characteristic) and Kappa statistics were used to calculate a model performance. Lastly, we verified models and created habitat suitability maps. The ROC AUC (Area Under the Curve) and Kappa values were 0.697/0.266 (GLM), 0.729/0.313 (GAM), 0.776/0.453 (CART), and 0.858/0.559 (ANN). Therefore, ANN was selected as the best model among 4 models. The models showed that elevation, slope, and distance to stream were the significant factors for Goal habitat. The ratio of predicted area of ANN using a threshold was 31.29%, but the area decreased when human effect was considered. We need to investigate the difference of various models to build a suitable wildlife habitat model under a given condition.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2022.05a
• /
• pp.130-130
• /
• 2022

기후변화로 인한 기상이변 현상으로 폭우와 홍수 등 수문학적 극치 사상의 출현 빈도가 잦아지고 있다. 따라서 이러한 기상이변 현상에 적응하기 위하여 보다 정확한 확률강우량 측정의 필요성이 증가하고 있다. 대장 지점의 미래 확률강우량 계산을 위해선 기후변화 시나리오의 비정상성을 고려해야 한다. 본 연구는 비정상적인 미래 기후에서 확률강우량이 어떻게 변화하는지 측정하는 것을 목표로 한다. Representative Concentration Pathway (RCP4.5)에 따른 우리나라의 확률강우량 계산에 인공신경망을 포함한 정상성, 비정상성 확률강우량 산정 모델들이 사용되었다. 지점빈도해석(AFA), 홍수지수법(IFM), 모분포홍수지수법(PIF), 인공신경망을 이용한 Quantile & Parameter regression technique(QRT & PRT)이 정상성 자료에 대해 확률강우량을 계산하는 모델로 사용되었으며, 비정상성 자료에 대해서는 비정상성 지점빈도해석(NS-AFA), 비정상성 홍수지수법(NS-IFM), 비정상성 모분포홍수지수법(NS-PIF), 인공신경망을 사용한 비정상성 Quantile & Parameter regression technique(NS-QRT & NS-PRT)이 사용되었다. Rescaled Akaike information criterion(rAIC)를 사용한 불확실성 분석과 적합도 검정을 통해서 generalized extreme value(GEV) 분포형 모델이 정상성 및 비정상성 확률강우량 산정에 가장 적합한 모델로 선정되었다. 이후, 관측자료가 GEV(0,0,0)을 따르고 시나리오 자료가 GEV(1,0,0)을 따르는 지점들을 선택하여 미래의 확률강우량 변화를 추정하였다. 각 빈도해석 모델들은 몬테카를로 시뮬레이션을 통해 bias, relative bias(Rbias), root mean square error(RMSE), relative root mean square error(RRMSE)를 바탕으로 측정하여 정확도를 계산하였으며 그 결과 QRT와 NS-QRT가 각각 정상성과 비정상성 자료로부터 가장 정확하게 확률강우량을 계산하였다. 본 연구를 통해 향후 기후변화의 영향으로 확률강우량이 증가할 것으로 예상되며, 비정상성을 고려한 빈도분석 또한 필요함을 제안하였다.

• Geophysics and Geophysical Exploration
• /
• v.2 no.4
• /
• pp.167-173
• /
• 1999

Since the resolution of the 2-D hole-to-hole seismic traveltime tomography is affected by the limited ray transmission angle, various methods were used to improve the resolution. Linear traveltime interpolation(LTI) ray tracing method was chosen for forward-modeling method. Inversion results using the LTI method were compared with those using the other ray tracing methods. As an inversion algorithm, SIRT method was used. In the iterative non-linear inversion method, the cost of ray tracing is quite expensive. To reduce the cost, each raypath was stored and the inversion was performed from this information. Using the proposed method, fast convergence was achieved. Inversion results are likely to be affected by the initial velocity guess, especially when the ray transmission angle was limited. To provide a good initial guess for the inversion, generalized regression neural network(GRNN) method was used. When the transmitted raypath angle is not limited or the geological model is very complex, the inversion results are not affected by initial velocity model very much. Since the raypath angles, however, are limited in most geophysical tomographic problems, the enhancement of resolution in tomography can be achieved by providing a proper initial velocity model by another inversion algorithm such as GRNN.