• Journal of the Korean Geotechnical Society
• /
• v.39 no.4
• /
• pp.5-17
• /
• 2023

The advancement in large-scale underground excavation in urban areas necessitates monitoring and predicting technologies that can pre-emptively mitigate risk factors at construction sites. Traditionally, two methods predict the deformation of retaining walls induced by excavation: empirical and numerical analysis. Recent progress in artificial intelligence technology has led to the development of a predictive model using machine learning techniques. This study developed a model for predicting the deformation of a retaining wall under construction using a boosting-based algorithm and an ensemble model with outstanding predictive power and efficiency. A database was established using the data from the design-construction-maintenance process of the underground retaining wall project in a manifold manner. Based on these data, a learning model was created, and the performance was evaluated. The boosting and ensemble models demonstrated that wall deformation could be accurately predicted. In addition, it was confirmed that prediction results with the characteristics of the actual construction process can be presented using data collected from ground measurements. The predictive model developed in this study is expected to be used to evaluate and monitor the stability of retaining walls under construction.

• IE interfaces
• /
• v.25 no.2
• /
• pp.178-186
• /
• 2012

The DRAM module is an important part of servers, workstations and personal computer. Its malfunction causes a lot of damage on customer system. Therefore, customers demand the highest quality products. The company applies DRAM module Outgoing Quality Assurance Inspection(OQA) to secures the highest quality. It is the key process to decides shipment of products through sample inspection method with customer oriented tests. High fraction of defectives entering to OQA causes inevitable high quality cost. This article proposes the application of ensemble learning to classify the lot status to minimize the ratio of wrong decision in OQA, observing a potential in reducing the wrong decision.

• Korea Trade Review
• /
• v.46 no.2
• /
• pp.281-299
• /
• 2021

This paper analyzes the feasibility of using machine learning methods to forecast the employment. The machine learning methods, such as decision tree, artificial neural network, and ensemble models such as random forest and gradient boosting regression tree were used to forecast the employment in Busan regional economy. The following were the main findings of the comparison of their predictive abilities. First, the forecasting power of machine learning methods can predict the employment well. Second, the forecasting values for the employment by decision tree models appeared somewhat differently according to the depth of decision trees. Third, the predictive power of artificial neural network model, however, does not show the high predictive power. Fourth, the ensemble models such as random forest and gradient boosting regression tree model show the higher predictive power. Thus, since the machine learning method can accurately predict the employment, we need to improve the accuracy of forecasting employment with the use of machine learning methods.

• Smart Media Journal
• /
• v.11 no.3
• /
• pp.9-17
• /
• 2022

Algorithmic trading, which uses algorithms to trade financial products, has a problem in that the results are not stable due to many factors in the market. To alleviate this problem, ensemble techniques that combine trading algorithms have been proposed. However, there are several problems with this ensemble method. First, the trading algorithm may not be selected so as to satisfy the minimum performance requirement (more than random) of the algorithm included in the ensemble, which is a necessary requirement of the ensemble. Second, there is no guarantee that an ensemble model that performed well in the past will perform well in the future. In order to solve these problems, a method for selecting trading algorithms included in the ensemble model is proposed as follows. Based on past data, we measure the contribution of the trading algorithms included in the ensemble models with high performance. However, for contributions based only on this historical data, since there are not enough past data and the uncertainty of the past data is not reflected, the contribution distribution is approximated using the Dirichlet distribution, and the contribution values are sampled from the contribution distribution to reflect the uncertainty. Based on the contribution distribution of the trading algorithm obtained from the past data, the Transformer is trained to predict the future contribution. Trading algorithms with high predicted future contribution are selected and included in the ensemble model. Through experiments, it was proved that the proposed ensemble method showed superior performance compared to the existing ensemble methods.

• Journal of Korea Water Resources Association
• /
• v.39 no.3 s.164
• /
• pp.187-198
• /
• 2006

Korea Water Resources Corporation(KOWACO) has developed the Integrated Real-time Water Management System(IRWMS) that calculates monthly optimal ending target storages by using Sampling Stochastic Dynamic Programming(SSDP) with Ensemble Streamflow Prediction(ESP) running on the $1^{st}$ day of each month. This system, however, has a shortcoming: it cannot reflect the hydrolmeteorologic variations in the middle of the month. To overcome this drawback, in this study updated ESP forecasts three times each month by using the observed precipitation series from the $1^{st}$ day of the month to the forecast day and the historical precipitation ensemble for the remaining days. The improved accuracy and its effect on the reservoir operations were quantified as a result. SSDP/ESP21 that reflects within-a-month hydrolmeteorologic states saves $1\;X\;10^6\;m^3$ in water shortage on average than SSDP/ESP01. In addition, the simulation result demonstrated that the effect of ESP accuracy on the reduction of water shortage became more important when the total runoff was low during the drawdown period.

• Atmosphere
• /
• v.25 no.2
• /
• pp.323-337
• /
• 2015

This study explores the 6-month lead prediction skill of several climate indices that influence on East Asian climate in the GloSea5 hindcast experiment. Such indices include Nino3.4, Indian Ocean Diploe (IOD), Arctic Oscillation (AO), various summer and winter Asian monsoon indices. The model's prediction skill of these indices is evaluated by computing the anomaly correlation coefficient (ACC) and mean squared skill score (MSSS) for ensemble mean values over the period of 1996~2009. In general, climate indices that have low seasonal variability are predicted well. For example, in terms of ACC, Nino3.4 index is predicted well at least 6 months in advance. The IOD index is also well predicted in late summer and autumn. This contrasts with the prediction skill of AO index which shows essentially no skill beyond a few months except in February and August. Both summer and winter Asian monsoon indices are also poorly predicted. An exception is the Western North Pacific Monsoon (WNPM) index that exhibits a prediction skill up to 4- to 6-month lead time. However, when MSSS is considered, most climate indices, except Nino3.4 index, show a negligible prediction skill, indicating that conditional bias is significant in the model. These results are only weakly sensitive to the number of ensemble members.

• Journal of Information Technology Services
• /
• v.11 no.4
• /
• pp.233-250
• /
• 2012

In this paper, credit card delinquency means the possibility of occurring bad debt within the certain near future from the normal accounts that have no debt and the problem is to predict, on the monthly basis, the occurrence of delinquency 3 months in advance. This prediction is typical binary classification problem but suffers from the issue of data imbalance that means the instances of target class is very few. For the effective prediction of bad debt occurrence, Support Vector Machine (SVM) with kernel trick is adopted using credit card usage and payment patterns as its inputs. SVM is widely accepted in the data mining society because of its prediction accuracy and no fear of overfitting. However, it is known that SVM has the limitation in its ability to processing the large-scale data. To resolve the difficulties in applying SVM to bad debt occurrence prediction, two stage clustering is suggested as an effective data reduction method and ensembles of SVM models are also adopted to mitigate the difficulty due to data imbalance intrinsic to the target problem of this paper. In the experiments with the real world data from one of the major domestic credit card companies, the suggested approach reveals the superior prediction accuracy to the traditional data mining approaches that use neural networks, decision trees or logistics regressions. SVM ensemble model learned from T2 training set shows the best prediction results among the alternatives considered and it is noteworthy that the performance of neural networks with T2 is better than that of SVM with T1. These results prove that the suggested approach is very effective for both SVM training and the classification problem of data imbalance.

• Journal of Korea Water Resources Association
• /
• v.38 no.6 s.155
• /
• pp.471-483
• /
• 2005

A monthly Ensemble Streamflow Prediction (ESP) system was developed by applying a daily rainfall-runoff model known as the Streamflow Synthesis and Reservoir Regulation (SSARR) model to the Han, Nakdong, and Seomjin River basins in Korea. This study first assesses the accuracy of the averaged monthly runoffs simulated by SSARR for the 3 basins and proposes some improvements. The study found that the SSARR modeling of the Han and Nakdong River basins tended to significantly underestimate the actual runoff levels and the modeling of the Seomjin River basinshowed a large error variance. However, by implementing optimal linear correction (OLC), the accuracy of the SSARR model was considerably improved in predicting averaged monthly runoffs of the Han and Nakdong River basins. This improvement was not seen in the modeling of the Seomjin River basin. In addition, the ESP system was applied to forecast probabilistic runoff forecasts one month in advance for the 3 river basins from 1998 to 2003. Considerably improvement was also achieved with OLC in probabilistic forecasting accuracy for the Han and Nakdong River basins, but not in that of the Seomjin River basin.

• The Journal of Bigdata
• /
• v.6 no.1
• /
• pp.133-144
• /
• 2021

This paper derives the fire risk of buildings in Seoul through the prediction of property damage and the occurrence of fires. This study differs from prior research in that it utilizes variables that include not only a building's characteristics but also its affiliated administrative area as well as the accessibility of nearby fire-fighting facilities. We use Ensemble Voting techniques to merge different machine learning algorithms to predict property damage and fire occurrence, and to extract feature importance to produce fire risk. Fire risk prediction was made on 300 buildings in Seoul utilizing the established model, and it has been derived that with buildings at Level 1 for fire risks, there were a high number of households occupying the building, and the buildings had many factors that could contribute to increasing the size of the fire, including the lack of nearby fire-fighting facilities as well as the far location of the 119 Safety Center. On the other hand, in the case of Level 5 buildings, the number of buildings and businesses is large, but the 119 Safety Center in charge are located closest to the building, which can properly respond to fire.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.10
• /
• pp.1296-1301
• /
• 2021

With the recent increase in diabetes incidence worldwide, research has been conducted to predict diabetes through various machine learning and deep learning technologies. In this work, we present a model for predicting diabetes using machine learning techniques with German Frankfurt Hospital data. We apply outlier handling using Interquartile Range (IQR) techniques and Pearson correlation and compare model-specific diabetes prediction performance with Decision Tree, Random Forest, Knn (k-nearest neighbor), SVM (support vector machine), Bayesian Network, ensemble techniques XGBoost, Voting, and Stacking. As a result of the study, the XGBoost technique showed the best performance with 97% accuracy on top of the various scenarios. Therefore, this study is meaningful in that the model can be used to accurately predict and prevent diabetes prevalent in modern society.