• Structural Engineering and Mechanics
• /
• v.88 no.6
• /
• pp.535-549
• /
• 2023

Deep extreme learning machine (DELM) and multi-verse optimization algorithms (MVO) are hybridized for designing an optimal and adaptive control framework for uncertain buildings. In this approach, first, a robust model predictive control (RMPC) scheme is developed to handle the problem uncertainty. The optimality and adaptivity of the proposed controller are provided by the optimal determination of the tunning weights of the linear programming (LP) cost function for clustered external loads using the MVO. The final control policy is achieved by collecting the clustered data and training them by DELM. The efficiency of the introduced control scheme is demonstrated by the numerical simulation of a ten-story benchmark building subjected to earthquake excitations. The results represent the capability of the proposed framework compared to robust MPC (RMPC), conventional MPC (CMPC), and conventional DELM algorithms in structural motion control.

• Steel and Composite Structures
• /
• v.46 no.2
• /
• pp.153-173
• /
• 2023

Rectangular concrete-filled steel tubular (RCFST) column, a type of concrete-filled steel tubular (CFST), is widely used in compression members of structures because of its advantages. This paper proposes a robust machine learning-based framework for predicting the ultimate compressive strength of RCFST columns under both concentric and eccentric loading. The gradient boosting neural network (GBNN), an efficient and up-to-date ML algorithm, is utilized for developing a predictive model in the proposed framework. A total of 890 experimental data of RCFST columns, which is categorized into two datasets of concentric and eccentric compression, is carefully collected to serve as training and testing purposes. The accuracy of the proposed model is demonstrated by comparing its performance with seven state-of-the-art machine learning methods including decision tree (DT), random forest (RF), support vector machines (SVM), deep learning (DL), adaptive boosting (AdaBoost), extreme gradient boosting (XGBoost), and categorical gradient boosting (CatBoost). Four available design codes, including the European (EC4), American concrete institute (ACI), American institute of steel construction (AISC), and Australian/New Zealand (AS/NZS) are refereed in another comparison. The results demonstrate that the proposed GBNN method is a robust and powerful approach to obtain the ultimate strength of RCFST columns.

• Journal of ILASS-Korea
• /
• v.27 no.2
• /
• pp.57-65
• /
• 2022

The purpose of this study is to use machine learning to build a model capable of predicting the flash boiling spray characteristics. In this study, the flash boiling spray was visualized using Shadowgraph visualization technology, and then the spray image was processed with MATLAB to obtain quantitative data of spray characteristics. The experimental conditions were used as input, and the spray characteristics were used as output to train the machine learning model. For the machine learning model, the XGB (extreme gradient boosting) algorithm was used. Finally, the performance of machine learning model was evaluated using R² and RMSE (root mean square error). In order to have enough data to train the machine learning model, this study used 12 injectors with different design parameters, and set various fuel temperatures and ambient pressures, resulting in about 12,000 data. By comparing the performance of the model with different amounts of training data, it was found that the number of training data must reach at least 7,000 before the model can show optimal performance. The model showed different prediction performances for different spray characteristics. Compared with the upstream spray angle and the downstream spray angle, the model had the best prediction performance for the spray tip penetration. In addition, the prediction performance of the model showed a relatively poor trend in the initial stage of injection and the final stage of injection. The model performance is expired to be further enhanced by optimizing the hyper-parameters input into the model.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.44 no.4
• /
• pp.12-22
• /
• 2021

This article suggests the machine learning model, i.e., classifier, for predicting the production quality of free-machining 303-series stainless steel(STS303) small rolling wire rods according to the operating condition of the manufacturing process. For the development of the classifier, manufacturing data for 37 operating variables were collected from the manufacturing execution system(MES) of Company S, and the 12 types of derived variables were generated based on literature review and interviews with field experts. This research was performed with data preprocessing, exploratory data analysis, feature selection, machine learning modeling, and the evaluation of alternative models. In the preprocessing stage, missing values and outliers are removed, and oversampling using SMOTE(Synthetic oversampling technique) to resolve data imbalance. Features are selected by variable importance of LASSO(Least absolute shrinkage and selection operator) regression, extreme gradient boosting(XGBoost), and random forest models. Finally, logistic regression, support vector machine(SVM), random forest, and XGBoost are developed as a classifier to predict the adequate or defective products with new operating conditions. The optimal hyper-parameters for each model are investigated by the grid search and random search methods based on k-fold cross-validation. As a result of the experiment, XGBoost showed relatively high predictive performance compared to other models with an accuracy of 0.9929, specificity of 0.9372, F₁-score of 0.9963, and logarithmic loss of 0.0209. The classifier developed in this study is expected to improve productivity by enabling effective management of the manufacturing process for the STS303 small rolling wire rods.

• Computers and Concrete
• /
• v.30 no.3
• /
• pp.225-236
• /
• 2022

In this article, Multi-Gene Genetic Programming (MGGP) is proposed for the estimation of the compressive strength of concrete. MGGP is known to be a powerful algorithm able to find a relationship between certain input space features and a desired output vector. With respect to most conventional machine learning algorithms, which are often used as "black boxes" that do not provide a mathematical formulation of the output-input relationship, MGGP is able to identify a closed-form formula for the input-output relationship. In the study presented in this article, MGPP was used to predict the compressive strength of plain concrete, concrete with fly ash, and concrete with furnace slag. A formula was extracted for each mixture and the performance and the accuracy of the predictions were compared to the results of Artificial Neural Network (ANN) and Extreme Learning Machine (ELM) algorithms, which are conventional and well-established machine learning techniques. The results of the study showed that MGGP can achieve a desirable performance, as the coefficients of determination for plain concrete, concrete with ash, and concrete with slag from the testing phase were equal to 0.928, 0.906, 0.890, respectively. In addition, it was found that MGGP outperforms ELM in all cases and its' accuracy is slightly less than ANN's accuracy. However, MGGP models are practical and easy-to-use since they extract closed-form formulas that may be implemented and used for the prediction of compressive strength.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2018.05a
• /
• pp.157-157
• /
• 2018

A reliable and accurate downscaling model which can provide climate change information, obtained from global climate models (GCMs), at finer resolution has been always of great interest to researchers. In order to achieve this model, linear methods widely have been studied in the past decades. However, nonlinear methods also can be potentially beneficial to solve downscaling problem. Therefore, this study explored the applicability of some nonlinear machine learning techniques such as neural network (NN), extreme learning machine (ELM), and ELM autoencoder (ELM-AE) as well as a linear method, least absolute shrinkage and selection operator (LASSO), to build a reliable temperature downscaling model. ELM is an efficient learning algorithm for generalized single layer feed-forward neural networks (SLFNs). Its excellent training speed and good generalization capability make ELM an efficient solution for SLFNs compared to traditional time-consuming learning methods like back propagation (BP). However, due to its shallow architecture, ELM may not capture all of nonlinear relationships between input features. To address this issue, ELM-AE was tested in the current study for temperature downscaling.

• Journal of Korean Society of Disaster and Security
• /
• v.14 no.3
• /
• pp.17-27
• /
• 2021

In this study, classification models were built using machine learning techniques that can classify the soil creep risk into three classes from A to C (A: risk, B: moderate, C: good). A total of six machine learning techniques were used: K-Nearest Neighbor, Support Vector Machine, Logistic Regression, Decision Tree, Random Forest, and Extreme Gradient Boosting and then their classification accuracy was analyzed using the nationwide soil creep field survey data in 2019 and 2020. As a result of classification accuracy analysis, all six methods showed excellent accuracy of 0.9 or more. The methods where numerical data were applied for data training showed better performance than the methods based on character data of field survey evaluation table. Moreover, the methods learned with the data group (R1~R4) reflecting the expert opinion had higher accuracy than the field survey evaluation score data group (C1~C4). The machine learning can be used as a tool for prediction of soil creep if high-quality data are continuously secured and updated in the future.

• Journal of Digital Contents Society
• /
• v.17 no.6
• /
• pp.509-521
• /
• 2016

A novel Samples Balanced Genetic Algorithm combined with Extreme Learning Machine (SBGA-ELM) for Parkinson's Disease diagnosis and detecting bio-markers is presented in this paper. Proposed approach uses genes' expression data of 22,283 genes from open source ParkDB data base for accurate PD diagnosis and detecting bio-markers. Proposed SBGA-ELM includes two major steps: feature (genes) selection and classification. Feature selection procedure is based on proposed Samples Balanced Genetic Algorithm designed specifically for genes expression data from ParkDB. Proposed SBGA searches a robust subset of genes among 22,283 genes available in ParkDB for further analysis. In the "classification" step chosen set of genes is used to train an Extreme Learning Machine (ELM) classifier for an accurate PD diagnosis. Discovered robust subset of genes creates ELM classifier with stable generalization performance for PD diagnosis. In this research the robust subset of genes is also used to discover 24 bio-markers probably responsible for Parkinson's Disease. Discovered robust subset of genes was verified by using existing PD diagnosis approaches such as SVM and PBL-McRBFN. Both tested methods caused maximum generalization performance.

• Journal of Digital Contents Society
• /
• v.17 no.6
• /
• pp.565-579
• /
• 2016

In this paper a novel cancer subtype's classifier based on Hybrid Samples Balanced Genetic Algorithm with Extreme Learning Machine (hSBGA-ELM) is presented. Proposed cancer subtype's classifier uses genes' expression data of 16063 genes from open Global Cancer Map (GCM) data base for accurate cancer subtype's classification. Proposed method efficiently classifies 14 subtypes of cancer (breast, prostate, lung, colorectal, lymphoma, bladder, melanoma, uterus, leukemia, renal, pancreas, ovary, mesothelioma and CNS). Proposed hSBGA-ELM unifies genes' selection procedure and cancer subtype's classification into one framework. Proposed Hybrid Samples Balanced Genetic Algorithm searches a reduced robust set of genes responsible for cancer subtype's classification from 16063 genes available in GCM data base. Selected reduced set of genes is used to build cancer subtype's classifier using Extreme Learning Machine (ELM). As a result, reduced set of robust genes guarantees stable generalization performance of the proposed cancer subtype's classifier. Proposed hSBGA-ELM discovers 95 genes probably responsible for cancer. Comparison with existing cancer subtype's classifiers clear indicates efficiency of the proposed method.

• International Journal of Contents
• /
• v.7 no.1
• /
• pp.14-22
• /
• 2011

Temporal Sign Language Recognition (TSLR) from hand motion is an active area of gesture recognition research in facilitating efficient communication with deaf people. TSLR systems consist of two stages: a motion sensing step which extracts useful features from signers' motion and a classification process which classifies these features as a performed sign. This work focuses on two of the research problems, namely unknown time varying signal of sign languages in feature extraction stage and computing complexity and time consumption in classification stage due to a very large sign sequences database. In this paper, we propose a combination of Dynamic Time Warping (DTW) and application of the Single hidden Layer Feedforward Neural networks (SLFNs) trained by Extreme Learning Machine (ELM) to cope the limitations. DTW has several advantages over other approaches in that it can align the length of the time series data to a same prior size, while ELM is a useful technique for classifying these warped features. Our experiment demonstrates the efficiency of the proposed method with the recognition accuracy up to 98.67%. The proposed approach can be generalized to more detailed measurements so as to recognize hand gestures, body motion and facial expression.