Seok Kim

Prof. Dr. Seok Kim

Korea National University of Transportation, Ŭiwang, Gyeonggi, Republic of Korea
orcid

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
18 March 2021 in KSCE Journal of Civil Engineering
Verified
Journal Article
Open access
PDF file
EKEu Wang Kim
Eu Wang Kim
Seok KimSeok Kim
Seok Kim
Urban railway networks have an important role in increasing the mobility of urban populations while decreasing congestion and pollution. Railway network extension that is caused by urban growth requires additional specialists and equipment for the operation, which causes an increase in maintenance cost. A comprehensive review of the literature regarding the application of facility location problem (FLP) in the railway domain found that there are few studies, and most of the current research involves the maintenance of railway vehicles only. In this paper, the purpose of this study is to determine the optimal location of infrastructure maintenance depot (IMD) for storing special vehicles and to support the inspection and maintenance tasks in a timely and efficient manner. For a challenging problem that should reflect the characteristic that traffic load and the deterioration of railway tracks are proportional, we proposed a method of applying maintenance weights to the p-hub median problem. To examine the proposed model, the test network was constructed by collecting information on the Seoul metropolitan subway. The results of case studies show that the number and location of IMDs are significantly affected by maintenance demand and expanded network.

6 September 2022 in KSCE Journal of Civil Engineering
Verified
Journal Article
Open access
PDF file
YCYeongjun Choi
Yeongjun Choi
SPSuyeul Park
Suyeul Park
Seok KimSeok Kim
Seok Kim
Recently, the construction industry has acquired geographic information on-site and used it in various fields for effective project management. However, a point cloud containing geographic information can be corrupted with noise because of several factors, such as sensor performance limitations, which degrade data quality and make them difficult to use in the future. Numerous algorithms for filtering point clouds have been developed; however, they still have several shortcomings. In this study, a denoising model suitable for an earthwork site with good performance was developed using a deep-learning-based approach. The approach involved selecting the encoder—decoder network as the training network, and training and evaluation were performed using actual earthwork site data. The results show that the developed denoising model precisely maintains the geographical shape without loss of information and deep learning can overcome the limitations of conventional denoising methods.

11 November 2022 in Sensors
Verified
Journal Article
Open access
PDF file
YCYeongjun Choi
Yeongjun Choi
SPSuyeul Park
Suyeul Park
Seok KimSeok Kim
Seok Kim
3D point cloud data (PCD) can accurately and efficiently capture the 3D geometric information of a target and exhibits significant potential for construction applications. Although one of the most common approaches for generating PCD is the use of unmanned aerial vehicles (UAV), UAV photogrammetry-based point clouds are erroneous. This study proposes a novel framework for automatically improving the coordinate accuracy of PCD. Image-based deep learning and PCD analysis methods are integrated into a framework that includes the following four phases: GCP (Ground Control Point) detection, GCP global coordinate extraction, transformation matrix estimation, and fine alignment. Two different experiments, as follows, were performed in the case study to validate the proposed framework: (1) experiments on the fine alignment performance of the developed framework, and (2) performance and run time comparison between the fine alignment framework and common registration algorithms such as ICP (Iterative Closest Points). The framework achieved millimeter-level accuracy for each axis. The run time was less than 30 s, which indicated the feasibility of the proposed framework.

2 August 2024 in Buildings
Verified
Journal Article
Open access
PDF file
SPSuyeul Park
Suyeul Park
Seok KimSeok Kim
Seok Kim
Most of the currently developed 3D point cloud data-based object recognition algorithms have been designed for small indoor objects, posing challenges when applied to large-scale 3D point cloud data in outdoor construction sites. To address this issue, this research selected four high-performance deep learning-based semantic segmentation algorithms for large-scale 3D point cloud data: Rand-LA-Net, KPConv Rigid, KPConv Deformable, and SCF-Net. These algorithms were trained and validated using 3D digital maps of earthwork sites to build semantic segmentation models, and their performance was tested and evaluated. The results of this research represent the first application of 3D semantic segmentation algorithms to large-scale 3D digital maps of earthwork sites. It was experimentally confirmed that object recognition technology can be implemented in the construction industry using 3D digital maps composed of large-scale 3D point cloud data.

28 March 2023 in KSCE Journal of Civil Engineering
Verified
Journal Article
Open access
PDF file
SKSanghyeok Kang
Sanghyeok Kang
YKYoungcheol Kang
Youngcheol Kang
Seok KimSeok Kim
Seok Kim
This bibliographic study presents a historical perspective on Korea’s construction engineering and management (CEM) research and reports a 27-year analysis of papers written by Korean CEM researchers between 1993 and 2019. Frequency analysis of the collected papers was performed according to three main perspectives: the knowledge area, research topics, and methods. Knowledge area analysis shows that research fields have become more diversified and subdivided. Construction technology, cost management, and planning and schedule management have consistently maintained the top three positions for the past three decades. In addition, quality management, resource management, and risk management were also ranked high in the 2000s. In the 2010s, safety management, environmental management, quality management, and construction industry and business were ranked high. These changes reveal how Korean society’s and industry’s demands have changed over the years. Furthermore, the findings from keyword frequency analysis revealed that the focus of CEM research was mostly on cost and scheduling in the 1990s and on scheduling, risk, cost, and construction automation in the 2000s. The advent of Building Information Modeling (BIM) in the 2010s was an epochal change. This study found that the research methods frequently used by CEM researchers were simulation, optimization, regression analysis, computer vision and image processing, 3D modeling, case-based reasoning, genetic algorithm, case study, economic analysis, and artificial neural network.

11 November 2024 in Buildings
Verified
Journal Article
Open access
PDF file
BMBilawal Mahmood
Bilawal Mahmood
Seok KimSeok Kim
Seok Kim
Railway transportation plays a vital role in modern society, enabling the safe and efficient movement of people and goods over long distances. To ensure the longevity and safety of a railway infrastructure, the regular maintenance of tracks is crucial. Traditional track inspections, conducted manually to monitor geometric parameters and to identify defects, are time-consuming, labor-intensive, and prone to human error. Current Scan-to-BIM frameworks for railway maintenance also lack standardized methods for extracting geometric parameters that can be easily integrated into Building Information Modeling (BIM). Additionally, the Industry Foundation Classes (IFC) standard, used for BIM data exchange, does not support storing parameter values at specific chainage points along the track, limiting defect localization. A framework is proposed to address these challenges by standardizing the extraction of geometric parameters from point cloud data and ensuring seamless integration with BIM. The framework calculates parameters at station chainage points and generates additional chainage points along the track, associating the data with the corresponding chainage. A case study demonstrates the framework’s ability to enhance defect localization, using the EN 13848-5 European Standard to identify defects at specific chainages. Ultimately, this approach contributes to the more effective lifecycle management of railway tracks.