• Journal of the Korea Society of Computer and Information
• /
• v.26 no.4
• /
• pp.47-53
• /
• 2021

In this paper, we propose a quadtree-based optimization technique that enables fast Super-resolution(SR) computation by efficiently classifying and dividing physics-based simulation data required to calculate SR. The proposed method reduces the time required for quadtree computation by downscaling the smoke simulation data used as input data. By binarizing the density of the smoke in this process, a quadtree is constructed while mitigating the problem of numerical loss of density in the downscaling process. The data used for training is the COCO 2017 Dataset, and the artificial neural network uses a VGG19-based network. In order to prevent data loss when passing through the convolutional layer, similar to the residual method, the output value of the previous layer is added and learned. In the case of smoke, the proposed method achieved a speed improvement of about 15 to 18 times compared to the previous approach.

• Structural Engineering and Mechanics
• /
• v.80 no.6
• /
• pp.645-655
• /
• 2021

Performance-based reliability analysis is a practical approach to investigate the seismic performance and stochastic nonlinear response of structures considering a random process. This is significant due to the uncertainties involved in every aspect of the analysis. Therefore, the present study aims to evaluate the performance-based reliability within a stochastic finite element (FE) framework for reinforced concrete (RC) shear walls that are considered as one of the most essential elements of structures. To accomplish this purpose, deterministic FE analyses are conducted for both squat and slender shear walls to validate numerical models through experimental results. The presented numerical analysis is performed by using the ABAQUS FE program. Afterwards, a random-effects investigation is carried out to consider the influence of different random variables on the lateral load-top displacement behavior of RC members. Using these results and through utilizing the Monte-Carlo simulation method, stochastic nonlinear analyses are also performed to generate random FE models based on input parameters and their probabilistic distributions. In order to evaluate the reliability of RC walls, failure probabilities and corresponding reliability indices are calculated at life safety and collapse prevention levels of performance as suggested by FEMA 356. Moreover, based on reliability indices, capacity reduction factors are determined subjected to shear for all specimens that are designed according to the ACI 318 Building Code. Obtained results show that the lateral load and the compressive strength of concrete have the highest effects on load-displacement responses compared to those of other random variables. It is also found that the probability of shear failure for the squat wall is slightly lower than that for slender walls. This implies that 𝛽 values are higher in a non-ductile mode of failure. Besides, the reliability of both squat and slender shear walls does not change significantly in the case of varying capacity reduction factors.

• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.181-193
• /
• 2022

Data-driven structural health monitoring (SHM) of civil infrastructure can be used to continuously assess the state of a structure, allowing preemptive safety measures to be carried out. Long-term monitoring of large-scale civil infrastructure often involves data-collection using a network of numerous sensors of various types. Malfunctioning sensors in the network are common, which can disrupt the condition assessment and even lead to false-negative indications of damage. The overwhelming size of the data collected renders manual approaches to ensure data quality intractable. The task of detecting and classifying an anomaly in the raw data is non-trivial. We propose an approach to automate this task, improving upon the previously developed technique of image-based pre-processing on one-dimensional (1D) data by enriching the features of the neural network input data with multiple channels. In particular, feature engineering is employed to convert the measured time histories into a 3-channel image comprised of (i) the time history, (ii) the spectrogram, and (iii) the probability density function representation of the signal. To demonstrate this approach, a CNN model is designed and trained on a dataset consisting of acceleration records of sensors installed on a long-span bridge, with the goal of fault detection and classification. The effect of imbalance in anomaly patterns observed is studied to better account for unseen test cases. The proposed framework achieves high overall accuracy and recall even when tested on an unseen dataset that is much larger than the samples used for training, offering a viable solution for implementation on full-scale structures where limited labeled-training data is available.

• Geomechanics and Engineering
• /
• v.28 no.1
• /
• pp.11-23
• /
• 2022

The response of pile foundations under lateral loads are usually analyzed using beam-on-nonlinear-Winkler-foundation (BNWF) model framework employing various forms of empirically derived p-y curves and p-multipliers. In practice, the p-y curve presented by the American Petroleum Institute (API) is most often utilized for piles in granular soils, although its shortcomings are recognized. The objective of this study is to evaluate the performance of the BNWF model and to quantify the error in the estimated pile response compared to a rigorous numerical model. BNWF analyses are performed using three sets of p-y curves to evaluate reliability of the procedure. The BNWF model outputs are compared with results of 3D nonlinear finite element (FE) analysis, which are validated via field load test measurements. The BNWF model using API p-y curve produces higher load-displacement curve and peak bending moment compared with the results of the FE model, because empirical p-y curve overestimates the stiffness and underestimates ultimate resistance up to a depth equivalent to four times the pile diameter. The BNWF model overestimates the peak bending moment by approximately 20-30% using both the API and Reese curves. The p-multipliers are revealed to be sensitive on the p-y curve used as input. These results highlight a need to develop updated p-y curves and p-multipliers for improved prediction of the pile response under lateral loading.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.161-161
• /
• 2023

Bias correction of values is a necessary step in downscaling coarse and systematically biased global climate models for use in local climate change impact studies. In addition to univariate bias correction methods, many multivariate methods which correct multiple variables jointly - each with their own mathematical designs - have been developed recently. While some literature have focused on the inter-comparison of these multivariate bias correction methods, none have focused extensively on the effect of diverse configurations (i.e., different combinations of input variables to be corrected) of climate variables, particularly high-dimensional ones, on the ability of the different methods to remove biases in uni- and multivariate statistics. This study evaluates the impact of three configurations (inter-variable, inter-spatial, and full dimensional dependence configurations) on four state-of-the-art multivariate bias correction methods in a national-scale domain over South Korea using a gridded approach. An inter-comparison framework evaluating the performance of the different combinations of configurations and bias correction methods in adjusting various climate variable statistics was created. Precipitation, maximum, and minimum temperatures were corrected across 306 high-resolution (0.2°) grid cells and were evaluated. Results show improvements in most methods in correcting various statistics when implementing high-dimensional configurations. However, some instabilities were observed, likely tied to the mathematical designs of the methods, informing that some multivariate bias correction methods are incompatible with high-dimensional configurations highlighting the potential for further improvements in the field, as well as the importance of proper selection of the correction method specific to the needs of the user.

• International Journal of Computer Science & Network Security
• /
• v.23 no.3
• /
• pp.177-186
• /
• 2023

Hyperspectral imaging technology is one of the most efficient and fast-growing technologies in recent years. Hyperspectral image (HSI) comprises contiguous spectral bands for every pixel that is used to detect the object with significant accuracy and details. HSI contains high dimensionality of spectral information which is not easy to classify every pixel. To confront the problem, we propose a novel RGB channel Assimilation for classification methods. The color features are extracted by using chromaticity computation. Additionally, this work discusses the classification of hyperspectral image based on Domain Transform Interpolated Convolution Filter (DTICF) and 3D-CNN with Bi-directional-Long Short Term Memory (Bi-LSTM). There are three steps for the proposed techniques: First, HSI data is converted to RGB images with spatial features. Before using the DTICF, the RGB images of HSI and patch of the input image from raw HSI are integrated. Afterward, the pair features of spectral and spatial are excerpted using DTICF from integrated HSI. Those obtained spatial and spectral features are finally given into the designed 3D-CNN with Bi-LSTM framework. In the second step, the excerpted color features are classified by 2D-CNN. The probabilistic classification map of 3D-CNN-Bi-LSTM, and 2D-CNN are fused. In the last step, additionally, Markov Random Field (MRF) is utilized for improving the fused probabilistic classification map efficiently. Based on the experimental results, two different hyperspectral images prove that novel RGB channel assimilation of DTICF-3D-CNN-Bi-LSTM approach is more important and provides good classification results compared to other classification approaches.

• Journal of Korea Trade
• /
• v.26 no.4
• /
• pp.23-38
• /
• 2022

Purpose - This paper empirically explores the RCA of electrical equipment trade between China and Korea from the perspective of gross trade and value-added trade. The goal of this paper is to scan the electrical equipment's RCA, the decomposition of gross exports, and the impacts of an exerted shock. Design/methodology - We applied the domestic value-added method in measuring the RCA, which could be more accurate than traditional RCA since it excludes foreign value-added. Based on the research purpose, this paper follows the framework of Koopman, Wang, and Wei (2014)-as extended by Wang, Wei, and Zhu (2018). It extracts the data from the 2019 Multi-regional Input-Output (MRIO) databases compiled by the Asian Development Bank in January 2021. Findings - After rigorous examination, the main findings are as follows: First, the electrical equipment sector maintains a consistent comparative advantage in either assessing method. Second, China exports more gross goods of electrical equipment to the world than South Korea does, but there is a trade deficit with Korea. Third, South Korea and P.R. China are the most significant bilateral partners of foreign value-added sourcing. Finally, it is surprising that there is a shock on electrical equipment; the partner's service, as well as manufacturing sectors, would be affected. Originality/value - This paper explores the revealed comparative advantage between Korea and China from traditional gross export and value-added perspectives. Second, we apply the information from the 2019 MRIO database compiled by the Asian Development Bank in January 2021, reflecting the current situation. Third, this paper analyzes the electrical equipment and the impacts on other parties' sectors. Finally, we carry out the subjects that deserve to be investigated in the future.

• Wind and Structures
• /
• v.36 no.6
• /
• pp.405-421
• /
• 2023

Strong wind is the main factors of wind-damage of high-rise buildings, which often creates largely economical losses and casualties. Wind pressure plays a critical role in wind effects on buildings. To obtain the high-resolution wind pressure field, it often requires massive pressure taps. In this study, two traditional methods, including bilinear and bicubic interpolation, and two deep learning techniques including Residual Networks (ResNet) and Generative Adversarial Networks (GANs), are employed to reconstruct wind pressure filed from limited pressure taps on the surface of an ideal building from TPU database. It was found that the GANs model exhibits the best performance in reconstructing the wind pressure field. Meanwhile, it was confirmed that k-means clustering based retained pressure taps as model input can significantly improve the reconstruction ability of GANs model. Finally, the generalization ability of k-means clustering based GANs model in reconstructing wind pressure field is verified by an actual engineering structure. Importantly, the k-means clustering based GANs model can achieve satisfactory reconstruction in wind pressure field under the inputs processing by k-means clustering, even the 20% of pressure taps. Therefore, it is expected to save a huge number of pressure taps under the field reconstruction and achieve timely and accurately reconstruction of wind pressure field under k-means clustering based GANs model.

• International conference on construction engineering and project management
• /
• 2013.01a
• /
• pp.403-411
• /
• 2013

Horizontal construction projects such as oil and gas pipeline projects typically involve repetitive-work activities with the same crew and equipment from one end of the project to the other. Repetitive scheduling also known as linear scheduling is known to have superior schedule management capabilities specifically for such horizontal construction projects. This study discusses on expanding the capabilities of repetitive scheduling to account for the variance in production rates and visual representation by developing an automated alignment based linear scheduling program for applying temporal and spatial changes in production rates. The study outlines a framework to apply changes in productions rates when and where they will occur along the horizontal alignment of the project and illustrates the complexity of construction through the time-location chart through a new linear scheduling model, Linear Scheduling Model with Varying Production Rates (LSM_VPR). The program uses empirically derived production rate equations with appropriate variables as an input at the appropriate time and location based on actual 750 mile natural gas liquids pipeline project starting in Wyoming and terminating in the center of Kansas. The study showed that the changes in production rates due to time and location resulted in a close approximation of the actual progress of work as compared to the planned progress and can be modeled for use in predicting future linear construction projects. LSM_VPR allows the scheduler to develop schedule durations based on minimal project information. The model also allows the scheduler to analyze the impact of various routes or start dates for construction and the corresponding impact on the schedule. In addition, the graphical format lets the construction team to visualize the obstacles in the project when and where they occur due to a new feature called the Activity Performance Index (API). This index is used to shade the linear scheduling chart by time and location with the variation in color indicating the variance in predicted production rate from the desired production rate.

• International Journal of Computer Science & Network Security
• /
• v.24 no.2
• /
• pp.43-52
• /
• 2024

Medical imaginings assume a important part in the analysis of tumors and cerebrospinal fluid (CSF) leak. Magnetic resonance imaging (MRI) is an image segmentation technology, which shows an angular sectional perspective of the body which provides convenience to medical specialists to examine the patients. The images generated by MRI are detailed, which enable medical specialists to identify affected areas to help them diagnose disease. MRI imaging is usually a basic part of diagnostic and treatment. In this research, we propose new techniques using the 4D-MRI image segmentation process to detect the brain tumor in the skull. We identify the issues related to the quality of cerebrum disease images or CSF leakage (discover fluid inside the brain). The aim of this research is to construct a framework that can identify cancer-damaged areas to be isolated from non-tumor. We use 4D image light field segmentation, which is followed by MATLAB modeling techniques, and measure the size of brain-damaged cells deep inside CSF. Data is usually collected from the support vector machine (SVM) tool using MATLAB's included K-Nearest Neighbor (KNN) algorithm. We propose a 4D light field tool (LFT) modulation method that can be used for the light editing field application. Depending on the input of the user, an objective evaluation of each ray is evaluated using the KNN to maintain the 4D frequency (redundancy). These light fields' approaches can help increase the efficiency of device segmentation and light field composite pipeline editing, as they minimize boundary artefacts.