• Geomechanics and Engineering
• /
• 제37권4호
• /
• pp.395-418
• /
• 2024

The epicentral region of earthquakes is typically where liquefaction-related damage takes place. To determine the maximum distance, such as maximum epicentral distance (R_e), maximum fault distance (R_f), or maximum hypocentral distance (R_h), at which an earthquake can inflict damage, given its magnitude, this study, using a recently updated global liquefaction database, multiple ML models are built to predict the limiting distances (R_e, R_f, or R_h) required for an earthquake of a given magnitude to cause damage. Four machine learning models LSTM (Long Short-Term Memory), BiLSTM (Bidirectional Long Short-Term Memory), CNN (Convolutional Neural Network), and XGB (Extreme Gradient Boosting) are developed using the Python programming language. All four proposed ML models performed better than empirical models for limiting distance assessment. Among these models, the XGB model outperformed all the models. In order to determine how well the suggested models can predict limiting distances, a number of statistical parameters have been studied. To compare the accuracy of the proposed models, rank analysis, error matrix, and Taylor diagram have been developed. The ML models proposed in this paper are more robust than other current models and may be used to assess the minimal energy of a liquefaction disaster caused by an earthquake or to estimate the maximum distance of a liquefied site provided an earthquake in rapid disaster mapping.

• 대한원격탐사학회지
• /
• 제40권2호
• /
• pp.123-139
• /
• 2024

Forest vertical structure is vital for comprehending ecosystems and biodiversity, in addition to fundamental forest information. Currently, the forest vertical structure is predominantly assessed via an in-situ method, which is not only difficult to apply to inaccessible locations or large areas but also costly and requires substantial human resources. Therefore, mapping systems based on remote sensing data have been actively explored. Recently, research on analyzing and classifying images using machine learning techniques has been actively conducted and applied to map the vertical structure of forests accurately. In this study, Sentinel-2 and digital surface model images were obtained on two different dates separated by approximately one month, and the spectral index and tree height maps were generated separately. Furthermore, according to the acquisition time, the input data were separated into cases 1 and 2, which were then combined to generate case 3. Using these data, forest vetical structure mapping models based on random forest, support vector machine, and extreme gradient boost(XGBoost)were generated. Consequently, nine models were generated, with the XGBoost model in Case 3 performing the best, with an average precision of 0.99 and an F1 score of 0.91. We confirmed that generating a forest vertical structure mapping model utilizing bi-seasonal data and an appropriate model can result in an accuracy of 90% or higher.

• Steel and Composite Structures
• /
• 제49권1호
• /
• pp.65-79
• /
• 2023

This paper presents a development of empirical evaluations, which can be used to evaluate the damage of fiber-reinforced concrete composites (FRC) wall subjected to close-in blast loads. For this development, a combined application of numerical simulation and machine learning approaches are employed. First, finite element modeling of FRC wall under blast loading is developed and verified using experimental data. Numerical analyses are then carried out to investigate the dynamic behavior of the FRC wall under blast loading. In addition, a data set of 384 samples on the damage of FRC wall due to blast loads is then produced in order to develop machine learning models. Second, three robust machine learning models of Random Forest (RF), Support Vector Machine (SVM), and Extreme Gradient Boosting (XGBoost) are employed to propose empirical evaluations for predicting the damage of FRC wall. The proposed empirical evaluations are very useful for practical evaluation and design of FRC wall subjected to blast loads.

• Steel and Composite Structures
• /
• 제44권1호
• /
• pp.49-63
• /
• 2022

This study aims to develop ensemble machine learning (ML) models for estimating the peak floor acceleration and maximum top drift of steel moment frames. For this purpose, random forest, adaptive boosting, gradient boosting regression tree (GBRT), and extreme gradient boosting (XGBoost) models were considered. A total of 621 steel moment frames were analyzed under 240 ground motions using OpenSees software to generate the dataset for ML models. From the results, the GBRT and XGBoost models exhibited the highest performance for predicting peak floor acceleration and maximum top drift, respectively. The significance of each input variable on the prediction was examined using the best-performing models and Shapley additive explanations approach (SHAP). It turned out that the peak ground acceleration had the most significant impact on the peak floor acceleration prediction. Meanwhile, the spectral accelerations at 1 and 2 s had the most considerable influence on the maximum top drift prediction. Finally, a graphical user interface module was created that places a pioneering step for the application of ML to estimate the seismic demands of building structures in practical design.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2023년도 학술발표회
• /
• pp.164-164
• /
• 2023

This study investigates the importance of flood-influencing factors on the accuracy of flood risk mapping using the integration of remote sensing-based and machine learning techniques. Here, the Extreme Gradient Boosting (XGBoost) and Random Forest (RF) algorithms integrated with GIS-based techniques were considered to develop and generate flood risk maps. For the study area of NAPA County in the United States, rainfall data from the 12 stations, Sentinel-1 SAR, and Sentinel-2 optical images were applied to extract 13 flood-influencing factors including altitude, aspect, slope, topographic wetness index, normalized difference vegetation index, stream power index, sediment transport index, land use/land cover, terrain roughness index, distance from the river, soil, rainfall, and geology. These 13 raster maps were used as input data for the XGBoost and RF algorithms for modeling flood-prone areas using ArcGIS, Python, and R. As results, it indicates that XGBoost showed better performance than RF in modeling flood-prone areas with an ROC of 97.45%, Kappa of 93.65%, and accuracy score of 96.83% compared to RF's 82.21%, 70.54%, and 88%, respectively. In conclusion, XGBoost is more efficient than RF for flood risk mapping and can be potentially utilized for flood mitigation strategies. It should be noted that all flood influencing factors had a positive effect, but altitude, slope, and rainfall were the most influential features in modeling flood risk maps using XGBoost.

• 한국융합학회논문지
• /
• 제10권11호
• /
• pp.15-21
• /
• 2019

4차 산업혁명이 주목받고 있다. 특히 스마트 팩토리는 제조 분야에서 그 필요성이 강조되고 있다. 현재 제조 분야에서 CNC(Computerized Numeric Controller: 컴퓨터 수치 제어)에 관한 연구가 활발히 진행 중이다. 국내에서는 CNC 설비에 음향 센서, 진동 센서 등 여러 가지 센서를 부착하여 소음, 진동 등 설비 관련 데이터를 수집하는 방안에 관한 연구가 존재한다. 본 연구는 CNC 머신에서 발생하는 데이터를 중심으로 머신러닝 기법을 활용하여 설비 가동 조건이 공구 마모도에 미치는 영향을 분석한다. CNC 설비에서 발생하는 X축, Y축, Z축의 힘, 이동 속도 등 다양한 데이터를 수집한다. 데이터 탐색 기법을 통해 데이터의 특성 및 분포를 분석하였다. 데이터를 RF(Random Forest), XGB(Extreme Gradient Boost), SVM(Support Vector Machine)을 이용하여 CNC 설비 가동 조건이 공구 마모도에 미치는 영향을 분석하였다. 본 연구의 결과는 CNC 설비 가동에서 최적의 조건을 찾고, 이를 바탕으로 품질 향상 및 기계 손상을 예방하는데 활용될 수 있을 것으로 기대된다.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2023년도 학술발표회
• /
• pp.248-248
• /
• 2023

In recent years, the number of landslides in Korea has been increasing due to extreme weather events such as localized heavy rainfall and typhoons. Landslides often occur with debris flows, land subsidence, and earthquakes. They cause significant damage to life and property. 64% of Korea's land area is made up of mountains, the government wanted to predict landslides to reduce damage. In response, the Korea Forest Service has established a 'Landslide Information System' to predict the likelihood of landslides. This system selects a total of 13 landslide factors based on past landslide events. Using the LR technique (Logistic Regression) to predict the possibility of a landslide occurrence and the accuracy is known to be 0.75. However, most of the data used for learning in the current system is on landslides that occurred from 2005 to 2011, and it does not reflect recent typhoons or heavy rain. Therefore, in this study, we will apply a total of six machine learning techniques (KNN, LR, SVM, XGB, RF, GNB) to predict the occurrence of landslides based on the data of Inje, Gangwon-do, which was recently produced by the National Institute of Forest. To predict the occurrence of landslides, it is necessary to process converting landslide events and factors data into a suitable form for machine learning techniques through ArcGIS and Python. In addition, there is a large difference in the number of data between areas where landslides occurred or not. Therefore, the prediction was performed after correcting the unbalanced data using Tomek Links and Near Miss techniques. Moreover, to control unbalanced data, a model that reflects soil properties will use to remove absolute safe areas.

• 디지털콘텐츠학회 논문지
• /
• 제18권6호
• /
• pp.1165-1173
• /
• 2017

가장 대표적인 기계학습 알고리즘인 딥러닝 방법은 여러 응용 분야에서 활용성이 입증돼 디지털신호처리에 널리 사용되고 있다. 그러나 많은 학습데이터를 사용해 학습하는 과정에서 많은 메모리와 학습시간이 필요하기 때문에 CPU 성능과 메모리 용량이 제한된 IoT 디바이스에 딥러닝 기술을 적용하기는 어렵다. 특히 메모리 용량이 2K~8K 로 극히 적은 아두이노 기반의 디바이스를 사용한다면 알고리즘 구현에 많은 한계가 발생한다. 본 논문에서는 정확성과 효율성이 입증돼 여러 분야에서 활용되고 있는 ELM 알고리즘을 아두이노에서 최적화하는 방법을 제안하고, 실험을 통해 메모리 용량이 2KB인 아두이노 UNO와 메모리 용량이 8KB인 아두이노 MEGA에서 각각 15차원, 42차원의 다중 클래스 학습이 가능함을 보였다. 실험을 입증하기 위해 가우시안 혼합 모델링을 사용해 생성한 데이터셋과 범용적으로 사용하는 UCI 데이터셋을 사용해 제안한 알고리즘의 효율성을 입증하였다.

• Nuclear Engineering and Technology
• /
• 제55권9호
• /
• pp.3423-3440
• /
• 2023

In this work, a multivariate time-series machine learning meta-model is developed to predict the transient response of a typical nuclear power plant (NPP) undergoing a steam generator tube rupture (SGTR). The model employs Recurrent Neural Networks (RNNs), including the Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), and a hybrid CNN-LSTM model. To address the uncertainty inherent in such predictions, a Bayesian Neural Network (BNN) was implemented. The models were trained using a database generated by the Best Estimate Plus Uncertainty (BEPU) methodology; coupling the thermal hydraulics code, RELAP5/SCDAP/MOD3.4 to the statistical tool, DAKOTA, to predict the variation in system response under various operational and phenomenological uncertainties. The RNN models successfully captures the underlying characteristics of the data with reasonable accuracy, and the BNN-LSTM approach offers an additional layer of insight into the level of uncertainty associated with the predictions. The results demonstrate that LSTM outperforms GRU, while the hybrid CNN-LSTM model is computationally the most efficient. This study aims to gain a better understanding of the capabilities and limitations of machine learning models in the context of nuclear safety. By expanding the application of ML models to more severe accident scenarios, where operators are under extreme stress and prone to errors, ML models can provide valuable support and act as expert systems to assist in decision-making while minimizing the chances of human error.

• Steel and Composite Structures
• /
• 제51권6호
• /
• pp.679-695
• /
• 2024

This paper presents a novel technique that combines machine learning (ML) with moth-flame optimization (MFO) methods to predict the axial compressive strength (ACS) of concrete filled double skin steel tubes (CFDST) columns. The proposed model is trained and tested with a dataset containing 125 tests of the CFDST column subjected to compressive loading. Five ML models, including extreme gradient boosting (XGBoost), gradient tree boosting (GBT), categorical gradient boosting (CAT), support vector machines (SVM), and decision tree (DT) algorithms, are utilized in this work. The MFO algorithm is applied to find optimal hyperparameters of these ML models and to determine the most effective model in predicting the ACS of CFDST columns. Predictive results given by some performance metrics reveal that the MFO-CAT model provides superior accuracy compared to other considered models. The accuracy of the MFO-CAT model is validated by comparing its predictive results with existing design codes and formulae. Moreover, the significance and contribution of each feature in the dataset are examined by employing the SHapley Additive exPlanations (SHAP) method. A comprehensive uncertainty quantification on probabilistic characteristics of the ACS of CFDST columns is conducted for the first time to examine the models' responses to variations of input variables in the stochastic environments. Finally, a web-based application is developed to predict ACS of the CFDST column, enabling rapid practical utilization without requesting any programing or machine learning expertise.