• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.77-91
• /
• 2022

Various monitoring systems have been implemented in civil infrastructure to ensure structural safety and integrity. In long-term monitoring, these systems generate a large amount of data, where anomalies are not unusual and can pose unique challenges for structural health monitoring applications, such as system identification and damage detection. Therefore, developing efficient techniques is quite essential to recognize the anomalies in monitoring data. In this study, several machine learning techniques are explored and implemented to detect and classify various types of data anomalies. A field dataset, which consists of one month long acceleration data obtained from a long-span cable-stayed bridge in China, is employed to examine the machine learning techniques for automated data anomaly detection. These techniques include the statistic-based pattern recognition network, spectrogram-based convolutional neural network, image-based time history convolutional neural network, image-based time-frequency hybrid convolution neural network (GoogLeNet), and proposed ensemble neural network model. The ensemble model deliberately combines different machine learning models to enhance anomaly classification performance. The results show that all these techniques can successfully detect and classify six types of data anomalies (i.e., missing, minor, outlier, square, trend, drift). Moreover, both image-based time history convolutional neural network and GoogLeNet are further investigated for the capability of autonomous online anomaly classification and found to effectively classify anomalies with decent performance. As seen in comparison with accuracy, the proposed ensemble neural network model outperforms the other three machine learning techniques. This study also evaluates the proposed ensemble neural network model to a blind test dataset. As found in the results, this ensemble model is effective for data anomaly detection and applicable for the signal characteristics changing over time.

• Computers and Concrete
• /
• v.34 no.3
• /
• pp.279-296
• /
• 2024

In this study, ensemble machine learning (ML) models are employed to estimate the hardened properties of Self-Compacting Geopolymer Concrete (SCGC). The input variables affecting model development include the content of the SCGC such as the binder material, the age of the specimen, and the ratio of alkaline solution. On the other hand, the output parameters examined includes compressive strength, flexural strength, and split tensile strength. The ensemble machine learning models are trained and validated using a database comprising 396 records compiled from 132 unique mix trials performed in the laboratory. Diverse machine learning techniques, notably K-nearest neighbours (KNN), Random Forest, and Extreme Gradient Boosting (XGBoost), have been employed to construct the models coupled with Bayesian optimisation (BO) for the purpose of hyperparameter tuning. Furthermore, the application of nested cross-validation has been employed in order to mitigate the risk of overfitting. The findings of this study reveal that the BO-XGBoost hybrid model confirms better predictive accuracy in comparison to other models. The R² values for compressive strength, flexural strength, and split tensile strength are 0.9974, 0.9978, and 0.9937, respectively. Additionally, the BO-XGBoost hybrid model exhibits the lowest RMSE values of 0.8712, 0.0773, and 0.0799 for compressive strength, flexural strength, and split tensile strength, respectively. Furthermore, a SHAP dependency analysis was conducted to ascertain the significance of each parameter. It is observed from this study that GGBS, Flyash, and the age of specimens exhibit a substantial level of influence when predicting the strengths of geopolymers.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.2
• /
• pp.1-12
• /
• 2024

Predicting path loss is one of the important factors for wireless network design, such as selecting the installation location of base stations in cellular networks. In the past, path loss values were measured through numerous field tests to determine the optimal installation location of the base station, which has the disadvantage of taking a lot of time to measure. To solve this problem, in this study, we propose a path loss prediction method based on machine learning (ML). In particular, an ensemble learning approach is applied to improve the path loss prediction performance. Bootstrap dataset was utilized to obtain models with different hyperparameter configurations, and the final model was built by ensembling these models. We evaluated and compared the performance of the proposed ensemble-based path loss prediction method with various ML-based methods using publicly available path loss datasets. The experimental results show that the proposed method outperforms the existing methods and can predict the path loss values accurately.

• Journal of the Society of Naval Architects of Korea
• /
• v.56 no.6
• /
• pp.488-496
• /
• 2019

The estimation of block erection work time at a dock is one of the important factors when establishing or managing the total shipbuilding schedule. In order to predict the work time, it is a natural approach that the existing block erection data would be used to solve the problem. Generally the work time per unit is the product of coefficient value, quantity, and product value. Previously, the work time per unit is determined statistically by unit load data. However, we estimate the work time per unit through work time coefficient value from series ships using machine learning. In machine learning, the outcome depends mainly on how the training data is organized. Therefore, in this study, we use 'Feature Engineering' to determine which one should be used as features, and to check their influence on the result. In order to get the coefficient value of each block, we try to solve this problem through the Ensemble learning methods which is actively used nowadays. Among the many techniques of Ensemble learning, the final model is constructed by Stacking Ensemble techniques, consisting of the existing Ensemble models (Decision Tree, Random Forest, Gradient Boost, Square Loss Gradient Boost, XG Boost), and the accuracy is maximized by selecting three candidates among all models. Finally, the results of this study are verified by the predicted total work time for one ship among the same series.

• The Korean Journal of Applied Statistics
• /
• v.32 no.2
• /
• pp.319-330
• /
• 2019

Forecasting the electricity consumption through analyzing the past electricity consumption a advantageous for energy planing and policy. Machine learning is widely used as a method to predict electricity consumption. Among them, ensemble learning is a method to avoid the overfitting of models and reduce variance to improve prediction accuracy. However, ensemble learning applied to daily data shows the disadvantages of predicting a center value without showing a peak due to the characteristics of ensemble learning. In this study, we overcome the shortcomings of ensemble learning by considering the temperature trend. We compare nine models and propose a model using random forest with the linear trend of temperature.

• The Journal of Information Systems
• /
• v.30 no.4
• /
• pp.247-275
• /
• 2021

Purpose This study attempted to predict corporate innovation and business performance using ensemble learning. Design/methodology/approach The ensemble techniques uses weak learning to create robust learning, which combines several weak models to derive improved performance. In this study, XGboost, LightGBM, and Catboost were used among ensemble techniques. It was compared and evaluated with traditional machine learning methods. Findings The summary of the research results is as follows. First, the type of innovation is expanding from technical innovation to non-technical areas. Second, it was confirmed that LightGBM performed best for radical innovation prediction, and XGboost performed best for incremental innovation prediction. Third, Catboost performed best for firm performance prediction. Although there was no significant difference in predictive power between ensemble techniques, we found that comparative analysis was necessary to confirm better prediction performance.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.36 no.1
• /
• pp.9-18
• /
• 2023

Predicting the compressive strength of high-performance concrete (HPC) is challenging because of the use of additional cementitious materials; thus, the development of improved predictive models is essential. The purpose of this study was to develop an HPC compressive-strength prediction model using an ensemble machine-learning method of combined bagging and stacking techniques. The result is a new ensemble technique that integrates the existing ensemble methods of bagging and stacking to solve the problems of a single machine-learning model and improve the prediction performance of the model. The nonlinear regression, support vector machine, artificial neural network, and Gaussian process regression approaches were used as single machine-learning methods and bagging and stacking techniques as ensemble machine-learning methods. As a result, the model of the proposed method showed improved accuracy results compared with single machine-learning models, an individual bagging technique model, and a stacking technique model. This was confirmed through a comparison of four representative performance indicators, verifying the effectiveness of the method.

• Journal of Aerospace System Engineering
• /
• v.18 no.5
• /
• pp.1-14
• /
• 2024

This paper aimed to develop mesh stiffness prediction models using spur gear design parameters as input variables through a machine learning ensemble method. A dataset was generated by calculating individual stiffness using a calculation method presented in previous studies and deriving the minimum and maximum values of total mesh stiffness. Using multivariate linear regression, support vector regression, and decision tree regression, models were created to predict the minimum and maximum values of mesh stiffness. The stacking ensemble method was used to create meta models. Prediction models of three algorithms were used as base models. These Ensemble meta models were verified with specifications of gears used in actual aircraft engine starters, showing very high prediction performances. Thus, feasibility of applying Ensemble meta models to an actual gear system and their effectiveness were confirmed.

• Journal of Wind Energy
• /
• v.15 no.3
• /
• pp.21-29
• /
• 2024

Wind power is highly variable due to the intermittent nature of wind. This can lead to power grid instability and decreased efficiency. Therefore, it is necessary to improve wind power prediction performance to minimize the negative impact on the power system. Recently, wind power prediction using machine learning has gained popularity, and ensemble models in machine learning have shown high prediction accuracy. RF, GB, XGB and LGBM are decision tree-based ensemble models and have high predictive performance in wind power, but these models have problems from over-fitting and strong dependence on certain variables. However, the stacking model can improve prediction performance by combining individual models and compensate for the shortcomings of each model. In this study, The MAE of RF, XGB and LGBM is 310.42 kWh, 217.07 kWh and 265.20 kWh, respectively, while the stacking model based on RF, XGB and LGBM is 202.33 kWh. Stacking models can improve prediction performance. Finally, it is expected to contribute to electricity supply and demand planning.

• Geomechanics and Engineering
• /
• v.39 no.3
• /
• pp.241-256
• /
• 2024

The shear strength (SS) of soil is a critical parameter utilized in the design of civil engineering projects. The SS parameters, including cohesion (c) and friction angle (𝜑), can be determined through methods conducted either in the field or within a laboratory environment. However, the traditional method for determining SS parameters are not only costly but also time-consuming. Recently, the application of machine learning (ML) in geotechnical problems has received increasing attention. In order to select an appropriate ML model and assess the effect of physical properties on the SS of soil. This research endeavors to predict critical SS parameters of soil through the application of five machine learning (ML) models, integrating easily-available physical soil index, including specific gravity (G), saturation degree (Sr), liquid limit (LL), silt content (SC), and clay content (CC). The used ML techniques include Extreme Gradient Boosting (XGBoost), Random Forest (RF), Multilayer Perceptron (MLP), Support Vector Machine (SVM), and Convolutional Neural Network (CNN). A range of metrics, encompassing the root mean square error (RMSE), mean absolute error (MAE), and determination coefficient (R²) were used to measure the predictive efficacy of the employed models as well as compare the performance of the used ML models. The values of R² range from 0.769 to 0.987 indicate that all ML models exhibit excellent predictive capabilities for estimating SS parameters, in which the XGBoost, and CNN techniques show outperforming results compared to the other models. The study uses decision tree feature importance (DTFI) and coefficient feature importance (CFI) techniques to investigate how various physical properties impact the predictive capabilities of the model and indicates that both G and LL have a substantial impact on the predictive accuracy of cohesion and friction angle.