• Steel and Composite Structures
• /
• v.51 no.6
• /
• 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.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.25 no.5
• /
• pp.617-626
• /
• 2019

This study analyzes the optimal location of gas detectors through the gas dispersion in a cargo compressor room of a 174K LNG carrier equipped with high-pressure cargo handling equipment; in addition, we propose a reasonable method for determining the safety regulations specified in the new International Code of the Construction and Equipment of Ships Carrying Liquefied Gases in Bulk (IGC). To conduct an LNG gas dispersion simulation in the cargo compressor room-equipped with an ME-GI engine-of a 174 K LNG carrier, the geometry of the room as well as the equipment and piping, are designed using the same 3D size at a 1-to-1 scale. Scenarios for a gas leak were examined under high pressure of 305 bar and low pressure of 1 bar. The pinhole sizes for high pressure are 4.5, 5.0, and 5.6mm, and for low pressure are 100 and 140 mm. The results demonstrate that the cargo compressor room will not pose a serious risk with respect to the flammable gas concentration as verified by a ventilation assessment for a 5.6 mm pinhole for a high-pressure leak under gas rupture conditions, and a low-pressure leak of 100 and 140 mm with different pinhole sizes. However, it was confirmed that the actual location of the gas detection sensors in a cargo compressor room, according to the new IGC code, should be moved to other points, and an analysis of the virtual monitor points through a computational fluid dynamics (CFD) simulation.

• Clean Technology
• /
• v.26 no.3
• /
• pp.228-236
• /
• 2020

Korea has an economy based on manufacturing industrial fields, which produce high amounts of hazardous wastes, in spite of few landfill candidates, and a significant concern for fine airborne particulates; therefore, traditional waste management is difficult to apply in this country. Moreover, waste collection and accumulation have recently been intensified by the waste import prohibitions or regulations in developing nations, the universalization of delivery services in Korea, and the global COVID-19 crisis. This study thus presents a domestic waste management strategy that aims to address the recent issues on waste. The contents of the strategy as the main results of the study include the (1) improvement of the compatibility of the classification codes between the domestic hazardous waste and the international ones such as those of the Basel Convention; (2) consideration of the mixed hazard indices to represent toxicity from low-content components such as rare earth metals often contained in electrical and electronic equipment waste; (3) management application based on risks throughout the life cycles of waste; (4) establishment of detailed material flow information of waste by integrating the Albaro system, Pollutant Release and Transfer Register (PRTR) system, and online trade databases; (5) real-time monitoring and prediction of the waste movement or discharge using positional sensors and geographic information systems, among others; and (6) selection and implementation of optimal treatment or recycling practices through Life Cycle Assessment (LCA) and clean technologies.

• Journal of Periodontal and Implant Science
• /
• v.47 no.5
• /
• pp.264-272
• /
• 2017

Purpose: This study evaluated trends in tooth extraction due to acute and chronic periodontal disease (PD) using data from the National Health Insurance Service-National Sample Cohort for 2002-2013. Methods: A random sample of 1,025,340 individuals was selected as a representative sample of the population, and a database (DB) of diagnostic and prescription codes was followed up for 12 years. We used multivariate logistic regression analysis to assess the incidence of total extraction (TE), extraction due to periodontal disease (EPD), and immediate extraction due to periodontal disease (IEPD) according to sociodemographic factors (sex, age, household income, health status, and area of residence). Results: The incidence of tooth extraction was found to be increasing, and at a higher rate for TE in PD patients. In 2002, 50.6% of cases of TE were caused by PD, and this increased to 70.8% in 2013, while the number of cases of IEPD increased from 42.8% to 54.9% over the same period. The incidence rates of extraction due to acute and chronic PD increased monotonically. We found that the incidence rates of TE, EPD, and IEPD were all 2-fold higher among patients with high income levels and those who were not beneficiaries of health insurance. Conclusions: The rates of TE, EPD, and IEPD have been steadily increasing despite dental healthcare policies to expand public health insurance coverage, increasing the accessibility of dental clinics. Moreover, the effects of these policies were found to vary with both income and education levels. Consistent patient follow-up is required to observe changes in trends regarding tooth extraction according to changes in dental healthcare policies, and meticulous studies of such changes will ensure optimal policy reviews and revisions.

• Journal of Broadcast Engineering
• /
• v.19 no.4
• /
• pp.491-501
• /
• 2014

Recently, the need for disaster-preventing broadcast has increased gradually to cope with natural disaster like earthquake and tsunami causing enormous losses of both life and property. In disaster-preventing broadcast system, the wake-up signal is used to alert user terminal and switch the current state of channel to the emergency channel, which is for the fast and efficient delivery of emergency information. In this paper, we propose the detection method of wake-up signal for disaster-preventing broadcast systems. The wake-up signals for disaster-preventing broadcast should have a good auto-correlation property in low power and narrow-band conditions that does not affect the existing digital television (DTV) system. The suitability of the m-sequence and complementary code (CC) is analyzed for wake-up signals according to signal to noise ratio. A wake-up signal is proposed by combining the direct sequence spread spectrum (DSSS) technique and pseudo noise (PN) sequences such as Barker and Walsh-Hadamard codes. By using the proposed method, a higher detecting performance can be achieved by the spreading gain compared to the single long m-sequence and the Golay code.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.2 no.3
• /
• pp.87-99
• /
• 1982

This study proposes a reliability based design criteria for the R.C. superstructures of highway bridges. Uncertainties associated with the resistance of T or rectangular sections are investigated, and a set of appropriate uncertainties associated with the bridge dead and traffic live loads are proposed by reflecting our level of practice. Major 2nd moment reliability analysis and design theories including both Cornell's MFOSM(Mean First Order 2nd Moment) Methods and Lind-Hasofer's AFOSM(Advanced First Order 2nd Moment) Methods are summarized and compared, and it has been found that Ellingwood's algorithm and an approximate log-normal type reliability formula are well suited for the proposed reliability study. A target reliability index (${\beta}_0=3.5$) is selected as an optimal value considering our practice based on the calibration with the current R.C. bridge design safety provisions. A set of load and resistance factors is derived by the proposed uncertainties and the methods corresponding to the target reliability. Furthermore, a set of nominal safety factors and allowable stresses are proposed for the current W.S.D. design provisions. It may be asserted that the proposed L.R.F.D. reliability based design criteria for the R.C. highway bridges may have to be incorporated into the current R.C. bridge design codes as a design provision corresponding to the U.S.D. provisions of the current R.C. design code.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.30 no.6
• /
• pp.1131-1139
• /
• 2020

The static analysis of the source code is to find the remaining security weaknesses for a wide range of source codes. The static analysis tool is used to check the result, and the static analysis expert performs spying and false detection analysis on the result. In this process, the amount of analysis is large and the rate of false positives is high, so a lot of time and effort is required, and a method of efficient analysis is required. In addition, it is rare for experts to analyze only the source code of the line where the defect occurred when performing positive/false detection analysis. Depending on the type of defect, the surrounding source code is analyzed together and the final analysis result is delivered. In order to solve the difficulty of experts discriminating positive and false positives using these static analysis tools, this paper proposes a method of determining whether or not the security weakness found by the static analysis tools is a spy detection through artificial intelligence rather than an expert. In addition, the optimal size was confirmed through an experiment to see how the size of the training data (source code around the defects) used for such machine learning affects the performance. This result is expected to help the static analysis expert's job of classifying positive and false positives after static analysis.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.35 no.2
• /
• pp.131-140
• /
• 2022

Installing Continuous Welded Rail (CWR) is one of the economical ways to resolve the challenges of noise, vibration, and the open-deck steel railway bridge impact, and the SSF method using the interlocking sleeper fastener has recently been developed. In this study, the method employed for determining the optimum vertical stiffness of the sleeper pad installed under the bridge sleeper, which is utilized to adjust the rail height and absorb shock when the train passes when the interlocking sleeper fastener is applied, is presented. To determine the optimal vertical stiffness of the sleeper pad, related existing design codes are reviewed, and, running safety, ride comfort, track safety, and bridge vibration according to the change in the vertical stiffness of the sleeper pad are estimated via flexible multi-body dynamic analysis,. The flexible multi-body dynamic analysis is performed using commercial programs ABAQUS and VI-Rail. The numerical analysis is conducted using the bridge model for a 30m-long plate girder bridge, and the response is calculated when passing ITX Saemaeul and KTX vehicles and freight wagon when the vertical stiffness of the sleeper pad is altered from 7.5 kN/mm to 240 kN/mm. The optimum stiffness of the sleeper pad is calculated as 200 kN/mm under the conditions of the track components applied to the numerical analysis.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.35 no.4
• /
• pp.227-233
• /
• 2022

The 3D-printing technique is used for manufacturing objects by adding multiple layers, and it is relatively easy to manufacture objects with complex shapes. The 3D concrete printing technique, which incorporates 3D printing into the construction industry, does not use a formwork when placing concrete, and it requires less workload and labor, so economical construction is possible. However, 3D-printed concrete is expected to have a lower strength than that of molded concrete. In this study, the properties of 3D-printed concrete were analyzed. To fabricate the 3D-printed concrete samples, the extrusion path and shape of the samples were designed with Ultimaker Cura. Based on this, G-codes were generated to control the 3D printer. The optimal concrete mixing proportion was selected considering such factors as extrudability and buildability. Molded samples with the same dimensions were also fabricated for comparative analysis. The properties of each sample were measured through a three-point bending test and uniaxial compression test, and a comparative analysis was performed.

• Journal of Intelligence and Information Systems
• /
• v.17 no.4
• /
• pp.241-254
• /
• 2011

Financial time-series forecasting is one of the most important issues because it is essential for the risk management of financial institutions. Therefore, researchers have tried to forecast financial time-series using various data mining techniques such as regression, artificial neural networks, decision trees, k-nearest neighbor etc. Recently, support vector machines (SVMs) are popularly applied to this research area because they have advantages that they don't require huge training data and have low possibility of overfitting. However, a user must determine several design factors by heuristics in order to use SVM. For example, the selection of appropriate kernel function and its parameters and proper feature subset selection are major design factors of SVM. Other than these factors, the proper selection of instance subset may also improve the forecasting performance of SVM by eliminating irrelevant and distorting training instances. Nonetheless, there have been few studies that have applied instance selection to SVM, especially in the domain of stock market prediction. Instance selection tries to choose proper instance subsets from original training data. It may be considered as a method of knowledge refinement and it maintains the instance-base. This study proposes the novel instance selection algorithm for SVMs. The proposed technique in this study uses genetic algorithm (GA) to optimize instance selection process with parameter optimization simultaneously. We call the model as ISVM (SVM with Instance selection) in this study. Experiments on stock market data are implemented using ISVM. In this study, the GA searches for optimal or near-optimal values of kernel parameters and relevant instances for SVMs. This study needs two sets of parameters in chromosomes in GA setting : The codes for kernel parameters and for instance selection. For the controlling parameters of the GA search, the population size is set at 50 organisms and the value of the crossover rate is set at 0.7 while the mutation rate is 0.1. As the stopping condition, 50 generations are permitted. The application data used in this study consists of technical indicators and the direction of change in the daily Korea stock price index (KOSPI). The total number of samples is 2218 trading days. We separate the whole data into three subsets as training, test, hold-out data set. The number of data in each subset is 1056, 581, 581 respectively. This study compares ISVM to several comparative models including logistic regression (logit), backpropagation neural networks (ANN), nearest neighbor (1-NN), conventional SVM (SVM) and SVM with the optimized parameters (PSVM). In especial, PSVM uses optimized kernel parameters by the genetic algorithm. The experimental results show that ISVM outperforms 1-NN by 15.32%, ANN by 6.89%, Logit and SVM by 5.34%, and PSVM by 4.82% for the holdout data. For ISVM, only 556 data from 1056 original training data are used to produce the result. In addition, the two-sample test for proportions is used to examine whether ISVM significantly outperforms other comparative models. The results indicate that ISVM outperforms ANN and 1-NN at the 1% statistical significance level. In addition, ISVM performs better than Logit, SVM and PSVM at the 5% statistical significance level.