• Journal of the Korea Computer Graphics Society
• /
• v.30 no.3
• /
• pp.51-59
• /
• 2024

Collecting a dataset with a corresponding labeled gaze vector requires a high cost in the gaze estimation field. In this paper, we suggest a data augmentation of manipulating the gaze of an original image, which improves the accuracy of the gaze estimation model when the number of given gaze labels is restricted. By conducting multi-class gaze bin classification as an auxiliary task and adjusting the latent variable of the diffusion model, the model semantically edits the gaze from the original image. We manipulate a non-binary attribute, pitch and yaw of gaze vector to a desired range and uses the edited image as an augmented train data. The improved gaze accuracy of the gaze estimation network in the semi-supervised learning validates the effectiveness of our data augmentation, especially when the number of gaze labels is 50k or less.

• Nuclear Engineering and Technology
• /
• v.56 no.9
• /
• pp.3717-3729
• /
• 2024

Accurately predicting evacuation time in a ventilated main control room (MCR) during fire emergencies is crucial for ensuring the safety of personnel at nuclear power plants. This study proposes to use neural networks alongside consolidated fire and smoke transport (CFAST) simulations to serve as a surrogate model for physics-based simulation tools. Our neural networks can promptly predict the evacuation time in MCRs, proving to be a valuable asset in fire emergencies and eliminating the need for time-consuming rollouts of the CFAST simulations. The CFAST model simulates fire and evacuation scenarios in a ventilated MCR with variations in input parameters such as door conditions, ventilation flow rate, leakage area, and fire propagation time. Target output parameters, such as hot gas layer temperature (HGLT), heat flux (HF), and optical density (OD), are used alongside standardized evacuation variables to train a machine learning model for predicting evacuation time. The findings suggest that high ventilation flow rates help to dilute smoke and discharge hot gas, leading to lower target output parameters and quicker evacuation. Standardized evacuation variables exceed the required abandonment criteria for all door conditions, indicating the importance of proper evacuation procedures. The results show that neural networks can generate evacuation times close to those obtained from CFAST simulations.

• International conference on construction engineering and project management
• /
• 2024.07a
• /
• pp.311-318
• /
• 2024

Quality control in construction projects necessitates the detection of defects during construction. Currently, this task is performed manually by site supervisors. This manual process is inefficient, labor-intensive, and prone to human error, potentially leading to decreased productivity. To address this issue, research has been conducted to automate defect detection using computer vision-based object detection technologies. However, these studies often suffer from a lack of data for training deep learning models, resulting in inadequate accuracy. This study proposes a method to improve the accuracy of deep learning models through the use of virtual image data. The target building is created as a 3D model and finished with materials similar to actual components. Subsequently, a virtual defect texture is produced by layering three types of images: defect information, area information, and material information images, to fabricate materials with defects. Images are generated by rendering the 3D model and the defect, and annotations are created for segmentation. This approach creates a hybrid dataset by combining virtual data with actual site image data, which is then used to train the deep learning model. This research was conducted on the tile process of finishing construction projects, focusing on cracks and falls as the target defects. The training results of the deep learning model show that the F1-Score increased by 12.08% for falls and cracks when using the hybrid dataset compared to the real image dataset alone, validating the hybrid data approach. This study contributes not only to unmanned and automated smart construction management but also to enhancing safety on construction sites. To establish an integrated smart quality management system, it is necessary to detect various defects simultaneously with high accuracy. Utilizing this method for automatic defect detection in other types of construction can potentially expand the possibilities for implementing an integrated smart quality management system.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.5
• /
• pp.672-678
• /
• 2020

The parallel-feeding operation of an AC traction power supply system has the advantages of extending the power supply section and increasing the power supply capacity by reducing the voltage drop and peak demand caused by a train operation load. On the other hand, the parallel-feeding operation is restricted because of the circulating power flow induced from the phase difference between substations. Moreover, the power supply capacity is limited because of the unbalanced substation load depending on the trainload distribution, which can be changed by the train operation along the railway track. This paper suggests a Thyristor-controlled Phase Angle Regulator (TCPAR) to reduce the circulating power flow and the unbalanced substation load, which depends on the phase difference and the trainload distribution and provides a feasibility study. A dedicated control model of TCPAR is also provided, which uses substation power supplies as the input to control the circulating power flow and an unbalanced substation load depending on the phase difference and the trainload distribution. Simulation studies using PSCAD/EMTDC shows that the proposed TCPAR control model can reduce the circulating power flow and the unbalanced substation load depending on the phase difference and the trainload distribution. The proposed TCPAR can extend the parallel-feeding operation of an AC traction power system and increase the power supply capacity.

• Journal of the Korean Society for Railway
• /
• v.19 no.5
• /
• pp.629-637
• /
• 2016

In this paper, an investigation was conducted to evaluate the acoustic performance of low height noise barriers installed adjacent to rails; an easy-to-use approximation formula was suggested for the evaluation of insertion loss (IL), instead of using the boundary element method. At first, the acoustic performance of the low height noise barriers was measured in an anechoic chamber using a scaled down model; the overall IL according to the source location was analyzed with the equivalent IL contour line. Using the measurement results obtained from the scaled down model, an approximation formula was suggested for the IL of low height noise barriers having various shapes. Also, the prediction program was validated through a comparison between the actual measurement results in the anechoic chamber and the prediction results. Finally, using the prediction program, an approximation formula for IL was suggested for the low height noise absorption barriers. Considering the frequency characteristics of the noise sources of the train, the absorptive low height noise barriers have a 'ㄱ' type shape, a height of 1.0m, and a length of 0.5m when they are installed on the structure gauge for the train.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.20 no.2
• /
• pp.110-121
• /
• 2016

In the decision-making, such as selection of structure, construction method, or time and scheme of maintenance, the evaluation of life-cycle cost(LCC) is of great importance. The maintenance cost occupy a large portion of the LCC of the railway track as well as the initial construction cost. Futhermore, the proportion of the maintenance cost is much higher in the ballasted track. Thus, the importance of the LCC evaluation is higher than in any other engineering structures. In this study, a LCC model that can consider various design parameters such as the type of track structure, annual traffic volume, axle load, train speed, and proportion of curve sections and engineering structures has been developed. Fundamental data for calculating costs also have been presented. Based on the model and data proposed, the trends in the variation of LCC according to the design parameters were examined and the most important design parameters in the LCC analysis of railway track were investigated. The results show that the proportion of renewal and operational costs is much higher in the ballasted track than in the concrete track, and the annual traffic volume and ballast taming period are most significant factors on the LCC of the ballasted track. On the contrary, it is revealed that the proportion of the initial construction costs in the concrete track is much higher, and the LCC of the concrete track is less sensitive to the traffic volume, train speed, and axle load.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.26 no.2
• /
• pp.9-17
• /
• 2022

To take into account of the increasing speed of next generation high-speed trains, a new design code for the traffic safety of railway bridges is required. To solve dynamic responses of the bridge, this research offers a numerical analyses of PSC (Pre-stressed Concrete) box girder bridge, which is most representative of all the bridges on Gyungbu high-speed train line. This model takes into account of the inertial mass forces by the 38-degree-of-freedom and interaction forces as well as track irregularities. Our numerical analyses analyze the maximum vertical deflection and DAF (Dynamic Amplification Factor) between simple span and two-span continuous bridges to show the dynamic stability of the bridge. The third-order polynomial regression equations we use predict the maximum vertical deflections depending on varying running speeds of the train. We also compare the vertical deflections at several cross-sectional positions to check the influence of running speeds and the maximum irregularity at a longitudinal level. Moreover, our model analyzes the influence lines of vertical deflection accelerations of the bridge to evaluate traffic safety.

• Journal of Internet Computing and Services
• /
• v.23 no.4
• /
• pp.45-55
• /
• 2022

The size of the cryptocurrency market is growing. For example, market capitalization of bitcoin exceeded 500 trillion won. Accordingly, many studies have been conducted to predict the price of cryptocurrency, and most of them have similar methodology of predicting stock prices. However, unlike stock price predictions, machine learning become best model in cryptocurrency price predictions, conceptually cryptocurrency has no passive income from ownership, and statistically, cryptocurrency has at least three times higher liquidity than stocks. Thats why we argue that a methodology different from stock price prediction should be applied to cryptocurrency price prediction studies. We propose Reverse Walk-forward Validation (RWFV), which modifies Walk-forward Validation (WFV). Unlike WFV, RWFV measures accuracy for Validation by pinning the Validation dataset directly in front of the Test dataset in time series, and gradually increasing the size of the Training dataset in front of it in time series. Train data were cut according to the size of the Train dataset with the highest accuracy among all measured Validation accuracy, and then combined with Validation data to measure the accuracy of the Test data. Logistic regression analysis and Support Vector Machine (SVM) were used as the analysis model, and various algorithms and parameters such as L1, L2, rbf, and poly were applied for the reliability of our proposed RWFV. As a result, it was confirmed that all analysis models showed improved accuracy compared to existing studies, and on average, the accuracy increased by 1.23%p. This is a significant improvement in accuracy, given that most of the accuracy of cryptocurrency price prediction remains between 50% and 60% through previous studies.

• Journal of the Korean Regional Science Association
• /
• v.40 no.2
• /
• pp.91-106
• /
• 2024

Around the world, many countries experiencing the issue of shrinking cities are continually expanding high-speed rail networks to enhance regional accessibility and address imbalances. This study analyzed the effects of high-speed train operations on the age-specific population migration in South Korean municipalities from 2012 to 2019, taking into account the risk levels of shrinking cities. For this purpose, an analysis was conducted using age-specific net in-migration population as the dependent variable, employing the spatial panel autoregressive model. The research results indicated that the influence of high-speed rail on regional population inflow varies depending on the risk level of shrinking city. In other words, high-speed railway operations had positive effects on population inflow in the capital areas and some major cities, while explained population outflow in the other regions. High-speed railways particularly exerted a significant impact on the inflow of the young and middle-aged population, representing the working age, but this effect was also limited to regions with a low risk of shrinkage. The findings of this study emphasize the importance of considering planned population and industrial attraction when installing high-speed rail with the goal of achieving regional balanced development and mitigating shrinkage. The results of this study also suggest the need for subsequent research to explore factors that positively influence population structure and inflow based on the level of shrinkage risk in each region, as well as the introduction of new policies tailored to the specific situations of each local government.

• Journal of Intelligence and Information Systems
• /
• v.29 no.1
• /
• pp.27-40
• /
• 2023

With the increase in the spread of smart devices and the impact of COVID-19, the consumption of media contents through smart devices has significantly increased. Along with this trend, the amount of media contents viewed through OTT platforms is increasing, that makes contents recommendations on these platforms more important. Previous contents-based recommendation researches have mostly utilized metadata that describes the characteristics of the contents, with a shortage of researches that utilize the contents' own descriptive metadata. In this paper, various text data including titles and synopses that describe the contents were used to recommend similar contents. KLUE-RoBERTa-large, a Korean language model with excellent performance, was used to train the model on the text data. A dataset of over 20,000 contents metadata including titles, synopses, composite genres, directors, actors, and hash tags information was used as training data. To enter the various text features into the language model, the features were concatenated using special tokens that indicate each feature. The test set was designed to promote the relative and objective nature of the model's similarity classification ability by using the three contents comparison method and applying multiple inspections to label the test set. Genres classification and hash tag classification prediction tasks were used to fine-tune the embeddings for the contents meta text data. As a result, the hash tag classification model showed an accuracy of over 90% based on the similarity test set, which was more than 9% better than the baseline language model. Through hash tag classification training, it was found that the language model's ability to classify similar contents was improved, which demonstrated the value of using a language model for the contents-based filtering.