• Steel and Composite Structures
• /
• v.41 no.6
• /
• pp.831-850
• /
• 2021

Surface subsidence caused by mining subsidence has an impact on neighboring structures and utilities. In other words, subsurface voids created by mining or tunneling activities induce soil movement, exposing buildings to physical and/or functional destruction. Soil-structure is evaluated employing probability distribution laws to account for their uncertainty and complexity to estimate structural vulnerability. In this study, to investigate the displacement field and surface settlement profile caused by mining subsidence, on the basis of a Winklersoil model, analytical equations for the moment-rotation response ofsoil during mining induced ground movements are developed. To define the full static moment-rotation response, an equation for the uplift-yield state is constructed and integrated with equations for the uplift- and yield-only conditions. The constructed model's findings reveal that the inverse of the factor of safety (x) has a considerable influence on the moment-rotation curve. The maximal moment-rotation response of the footing is defined by X = 0:6. Despite the use of Winkler model, the computed moment-rotation response results derived from the literature were analyzed through the ELM-SVM hybrid of Extreme Learning Machine (ELM) and Support Vector Machine (SVM). Also, Monte Carlo simulations are used to apply continuous random parameters to assess the transmission of ground motions to structures. Following the findings of RMSE and R2, the results show that the choice of probabilistic laws of input parameters has a substantial impact on the outcome of analysis performed.

• Journal of the Korean Society of Systems Engineering
• /
• v.18 no.2
• /
• pp.75-93
• /
• 2022

Machine learning (ML) data-driven meta-model is proposed as a surrogate model to reduce the excessive computational cost of the physics-based model and facilitate the real-time prediction of a nuclear power plant's transient response. To forecast the transient response three machine learning (ML) meta-models based on recurrent neural networks (RNNs); specifically, Long Short Term Memory (LSTM), Gated Recurrent Unit (GRU), and a sequence combination of Convolutional Neural Network (CNN) and LSTM are developed. The chosen accident scenario is a control element assembly withdrawal at power concurrent with the Loss Of Offsite Power (LOOP). The transient response was obtained using the best estimate thermal hydraulics code, MARS-KS, and cross-validated against the Design and control document (DCD). DAKOTA software is loosely coupled with MARS-KS code via a python interface to perform the Best Estimate Plus Uncertainty Quantification (BEPU) analysis and generate a time series database of the system response to train, test and validate the ML meta-models. Key uncertain parameters identified as required by the CASU methodology were propagated using the non-parametric Monte-Carlo (MC) random propagation and Latin Hypercube Sampling technique until a statistically significant database (181 samples) as required by Wilk's fifth order is achieved with 95% probability and 95% confidence level. The three ML RNN models were built and optimized with the help of the Talos tool and demonstrated excellent performance in forecasting the most probable NPP transient response. This research was guided by the Systems Engineering (SE) approach for the systematic and efficient planning and execution of the research.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.37 no.1
• /
• pp.57-65
• /
• 2024

In a fire-resistant structure, uncertainties arise in factors such as ventilation, material elasticity modulus, yield strength, coefficient of thermal expansion, external forces, and fire location. The ventilation uncertainty affects thefactor contributes to uncertainties in fire temperature, subsequently impacting the structural temperature. These temperatures, combined with material properties, give rise to uncertain structural responses. Given the nonlinear behavior of structures under fire conditions, calculating fire fragility traditionally involves time-consuming Monte Carlo simulations. To address this, recent studies have explored leveraging machine learning algorithms to predict fire fragility, aiming to enhance efficiency while maintaining accuracy. This study focuses on predicting the fire fragility of a steel moment frame building, accounting for uncertainties in fire size, location, and structural material properties. The fragility curve, derived from nonlinear structural behavior under fire, follows a log-normal distribution. The results demonstrate that the proposed method accurately and efficiently predicts fire fragility, showcasing its effectiveness in streamlining the analysis process.

• Journal of the Korean Data and Information Science Society
• /
• v.12 no.2
• /
• pp.11-25
• /
• 2001

There are several algorithms for classification in modeling relations, patterns, and rules which exist in data. We learn to classify objects on the basis of instances presented to us, not by being given a set of classification rules. The Bayesian learning uses the probability distribution to express our knowledge about unknown parameters and update our knowledge by the law of probability as the evidence gathered from data. Also, the neural network models are designed for predicting an unknown category or quantity on the basis of known attributes by training. In this paper, we compare the misclassification error rates of Bayesian Neural Network method with those of other classification algorithms, CHAID, CART, and QUBST using several data sets.

• Geomechanics and Engineering
• /
• v.18 no.6
• /
• pp.595-603
• /
• 2019

A modified model combining Kriging and Monte Carlo method (MC) is proposed for probabilistic estimation of tunnel face stability in this paper. In the model, a novel uniform design is adopted to train the Kriging, instead of the existing active learning function. It has advantage of avoiding addition of new training points iteratively, and greatly saves the computational time in model training. The kinematic approach of limit analysis is employed to define the deterministic computational model of face failure, in which the Hoek-Brown failure criterion is introduced to account for the nonlinear behaviors of rock mass. The trained Kriging is used as a surrogate model to perform MC with dramatic reduction of calls to actual limit state function. The parameters in Hoek-Brown failure criterion are considered as random variables in the analysis. The failure probability is estimated by direct MC to test the accuracy and efficiency of the proposed probabilistic model. The influences of uncertainty level, correlation relationship and distribution type of random variables are further discussed using the proposed approach. In summary, the probabilistic model is an accurate and economical alternative to perform probabilistic stability analysis of tunnel face excavated in spatially random Hoek- Brown media.

• Korean Journal of Remote Sensing
• /
• v.37 no.1
• /
• pp.57-67
• /
• 2021

An earthquake occurred on 17 November 2017 in Pohang, South Korea with a strength of 5.4 Mw. This is the second strongest earthquake recorded by local authorities since the equipment was first installed. In order to improve understanding of earthquakes and surface deformation, many studies have been conducted according to these phenomena. In this research, we will estimate the surface deformation using the Okada model equation. The SAR images of three satellites with different wavelengths (ALOS-2, Cosmo SkyMed and Sentinel-1) were used to produce the interferogram pairs. The interferogram is used as a reference for surface deformation changes by using Okada to determine the source of surface deformation that occurs during an earthquake. The Non-linear optimization (Levemberg-Marquadrt algorithm) and Monte Carlo restart was applied to optimize the fault parameter on modeling process. Based on the modeling results of each satellite data, the fault geometry is ~6 km length, ~2 km width and ~5 km depth. The root mean square error values in the surface deformation model results for Sentinel, CSK and ALOS are 0.37 cm, 0.79 cm and 1.47 cm, respectively. Furthermore, the results of this modeling can be used as learning material in understanding about seismic activity to minimize the impacts that arise in the future.

• Nuclear Engineering and Technology
• /
• v.53 no.7
• /
• pp.2334-2340
• /
• 2021

Radioactive particle tracking (RPT) is a minimally invasive nuclear technique that tracks a radioactive particle inside a volume of interest by means of a mathematical location algorithm. During the past decades, many algorithms have been developed including ones based on artificial intelligence techniques. In this study, RPT technique is applied in a simulated test section that employs a simplified mixer filled with concrete, six scintillator detectors and a¹³⁷Cs radioactive particle emitting gamma rays of 662 keV. The test section was developed using MCNPX code, which is a mathematical code based on Monte Carlo simulation, and 3516 different radioactive particle positions (x,y,z) were simulated. Novelty of this paper is the use of a location algorithm based on a deep learning model, more specifically a 6-layers deep rectifier neural network (DRNN), in which hyperparameters were defined using a Bayesian optimization method. DRNN is a type of deep feedforward neural network that substitutes the usual sigmoid based activation functions, traditionally used in vanilla Multilayer Perceptron Networks, for rectified activation functions. Results show the great accuracy of the DRNN in a RPT tracking system. Root mean squared error for x, y and coordinates of the radioactive particle is, respectively, 0.03064, 0.02523 and 0.07653.

• The Korean Journal of Applied Statistics
• /
• v.32 no.2
• /
• pp.213-227
• /
• 2019

In this paper, we propose an end-to-end deep learning model combining Bayesian neural network with Korean speech recognition. In the past, Korean speech recognition was a complicated task due to the excessive parameters of many intermediate steps and needs for Korean expertise knowledge. Fortunately, Korean speech recognition becomes manageable with the aid of recent breakthroughs in "End-to-end" model. The end-to-end model decodes mel-frequency cepstral coefficients directly as text without any intermediate processes. Especially, Connectionist Temporal Classification loss and Attention based model are a kind of the end-to-end. In addition, we combine Bayesian neural network to implement the end-to-end model and obtain Monte Carlo estimates. Finally, we carry out our experiments on the "WorimalSam" online dictionary dataset. We obtain 4.58% Word Error Rate showing improved results compared to Google and Naver API.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.7 no.1
• /
• pp.81-98
• /
• 2013

Since Probabilistic Latent Semantic Analysis (PLSA) and Latent Dirichlet Allocation (LDA) were introduced, many revised or extended topic models have appeared. Due to the intractable likelihood of these models, training any topic model requires to use some approximation algorithm such as variational approximation, Laplace approximation, or Markov chain Monte Carlo (MCMC). Although these approximation algorithms perform well, training a topic model is still computationally expensive given the large amount of data it requires. In this paper, we propose a new method, called non-simultaneous sampling deactivation, for efficient approximation of parameters in a topic model. While each random variable is normally sampled or obtained by a single predefined burn-in period in the traditional approximation algorithms, our new method is based on the observation that the random variable nodes in one topic model have all different periods of convergence. During the iterative approximation process, the proposed method allows each random variable node to be terminated or deactivated when it is converged. Therefore, compared to the traditional approximation ways in which usually every node is deactivated concurrently, the proposed method achieves the inference efficiency in terms of time and memory. We do not propose a new approximation algorithm, but a new process applicable to the existing approximation algorithms. Through experiments, we show the time and memory efficiency of the method, and discuss about the tradeoff between the efficiency of the approximation process and the parameter consistency.

• Journal of Biomedical Engineering Research
• /
• v.37 no.5
• /
• pp.161-167
• /
• 2016

Recent technological advances in sensor fabrication and bio-signal processing enabled non-constraint and non-intrusive measurement of human bio-signals. Especially, non-constraint measurement of ECG makes it available to estimate various human health parameters such as heart rate. Additionally, non-constraint ECG measurement of wheelchair user provides real-time health parameter information for emergency response. For accurate emergency response with low false alarm rate, it is necessary to discriminate quality levels of ECG measured using non-constraint approach. Health parameters acquired from low quality ECG results in inaccurate information. Thus, in this study, a machine learning based approach for three-class classification of ECG quality level is suggested. Three sensors are embedded in the back seat, chest belt, and handle of automatic wheelchair. For the two sensors embedded in back seat and chest belt, capacitively coupled electrodes were used. The accuracy of quality level classification was estimated using Monte Carlo cross validation. The proposed approach demonstrated accuracy of 94.01%, 95.57%, and 96.94% for each channel of three sensors. Furthermore, the implemented algorithm enables classification of user posture by detection of contacted electrodes. The accuracy for posture estimation was 94.57%. The proposed algorithm will contribute to non-constraint and robust estimation of health parameter of wheelchair users.