• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.41 no.6
• /
• pp.751-760
• /
• 2021

Most bridges in Korea are over 20 years old, and many problems linked to their deterioration are being reported. The current practice for bridge inspection mainly depends on expert evaluation, which can be subjective. Recent studies have introduced data-driven methods using building information modeling, which can be more efficient and objective, but these methods require manual procedures that consume time and money. To overcome this, this study developed an image-based automaticbridge component classification network to reduce the time and cost required for converting the visual information of bridges to a digital model. The proposed method comprises two convolutional neural networks. The first network estimates the type of the bridge based on the superstructure, and the second network classifies the bridge components. In avalidation test, the proposed system automatically classified the components of 461 bridge images with 96.6 % of accuracy. The proposed approach is expected to contribute toward current bridge maintenance practice.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.50 no.1
• /
• pp.59-66
• /
• 2022

In order to solve the problem of urban traffic congestion, Urban Air Mobility (UAM) concept using Electric Vertical Take-off and Landing (eVTOL) aircraft has been gaining popularity, and many domestic and international studies are underway. However, since these aircraft inevitably fly over densely populated areas, it is essential to ensure safety, which starts with accurately analyzing the crash risk. In this paper, the locations and impact speeds of crash are computed using six degree-of-freedom simulations of an eVTOL aircraft in a fixed-wing mode. System malfunction was modeled by a sudden loss of thrust with control surfaces being stuck during cruise. Because most of these eVTOL aircraft are still under development, a methodology of constructing a six degree-of-freedom dynamics model from generic specification is also developed. The results show that the crash locations are highly concentrated right under the aircraft within a square that has an edge length similar to the cruise altitude. Speed distribution is more complicated because almost identical crash locations can be achieved by two very different paths resulting in a large variation in the speeds.

• Journal of Intelligence and Information Systems
• /
• v.28 no.2
• /
• pp.263-278
• /
• 2022

With the recent advent of IoT technology, automatic pet feeders are being distributed so that owners can feed their companion animals while they are out. However, due to behaviors of pets, the method of measuring weight, which is important in automatic feeding, can be easily damaged and broken when using the scale. The 3D camera method has disadvantages due to its cost, and the 2D camera method has relatively poor accuracy when compared to 3D camera method. Hence, the purpose of this study is to propose a deep learning approach that can accurately estimate weight while simply using a 2D camera. For this, various convolutional neural networks were used, and among them, the ResNet101-based model showed the best performance: an average absolute error of 3.06 grams and an average absolute ratio error of 3.40%, which could be used commercially in terms of technical and financial viability. The result of this study can be useful for the practitioners to predict the weight of a standardized object such as feed only through an easy 2D image.

• Journal of Cadastre & Land InformatiX
• /
• v.52 no.1
• /
• pp.5-16
• /
• 2022

Based on the general formula for the area error of a polygon and rectangular parcel, the constant term 0.026² × M (scale denominator) of the area error calculation formula prescribed by the Enforcement Decree was analyzed. As a result, it is found that the formula appropriately reflects the characteristics of the graphical surveying as a typical rectangular parcel model, but quantitatively allows a relatively large area error. In addition, it is found that, even if the area is the same, 50% more area error than a square parcel could be calculated depending on the shape of the parcel, and that the allowable area error should be different when dividing a parcel. Based on the analysis, furthermore, this study shows a solution that can solve the problems at once from the point of cadastral surveying. These are, the problem of reflecting the accuracy of the surveying, the problem of reflecting the size and shape of the parcel, and the problem whether a single area error formula can be used without having to distinguish between graphical and numerical surveyings. The new formula that solves these problems will bring about improvements in many related factors and promote the development of digital cadastral system.

• Journal of Korea Water Resources Association
• /
• v.55 no.6
• /
• pp.461-469
• /
• 2022

It is very important to ensure the reliability of dam inflow data, which is critical in planning and managing the supply and demand of water resources in a basin. However, the simple water balance model sometimes results in negative inflows and does not consider the actual inflow characteristics. In this study, to address these issues, the existing water balance formula was modified by considering evaporation which is available for calculation among other outflows. The modified water balance formula was applied to the Soyang Dam. The results showed that the rate of negative inflows decreased in the re-evaluated dam inflow data and it was possible to secure consistency for the total inflow volume. In addition, investigating the water availability in the Soyang Dam watershed based on the water balance concept considering evaporation, it was found that direct water use in the human aspect was about 60%, and the indirect water use in the natural aspect was about 40%. In drought years, it was also confirmed that the proportion of indirect use of water resources increased.

• Journal of Biomedical Engineering Research
• /
• v.43 no.3
• /
• pp.136-146
• /
• 2022

In this study, it is intended to provide basic data that can help develop a cardiovascular simulator for performance evaluation of pulse wave detectors by identifying the development status of domestic and overseas cardiovascular simulators. A total of 119 papers were selected by excluding duplicate literature, gray literature, and literature not related to a cardiovascular simulator. Based on the selected literature, the research trend of cardiovascular simulators was analyzed. As a result of analyzing the purpose of the study, most of the simulators were developed to evaluate the hemodynamic properties of artificial hearts and valves. In addition, it was used for simulation evaluation or hemodynamic studies such as pulse wave studies. As a result of analyzing configurations of the simulators, a heart most often consisted of only one left ventricle. For blood vessels, the Windkessel model was most often constructed using chambers and valves. In most studies, blood was reproduced by mixing glycerin and water to reproduce both density and viscosity. In addition, as a result of analysis from the perspective of medical device performance evaluation, simulators for evaluating artificial heart and artificial valves have been studied a lot, whereas simulators for blood pressure, pulse wave, and blood flow devices have been relatively insignificant. Based on the review results, we suggested considerations when developing a simulator for performance evaluations of a pulse wave detector.

• Korean Journal of Construction Engineering and Management
• /
• v.23 no.4
• /
• pp.15-25
• /
• 2022

As the incidence and mortality of serious disasters in the construction industry are the highest, various efforts are being made in Korea to reduce them. Among them, risk assessment is used as data for disaster reduction measures and evaluation of risk factors at the construction stage. However, the existing risk assessment involves the subjectivity of the performer and is vulnerable to the domestic construction site. This study established a DB classification system for risk assessment with the aim of early identification and pre-removal of risks by quantitatively deriving risk factors using BIM in the risk assessment field and presents a methodology for risk assessment using BIM. Through this, prior removal of risks increases the safety of construction workers and reduces additional costs in the field of safety management. In addition, since it can be applied to new construction methods, it improves the understanding of project participants and becomes a tool for communication. This study proposes a framework for deriving quantitative risks based on BIM, and will be used as a base technology in the field of risk assessment using BIM in the future.

• Journal of the Korean GEO-environmental Society
• /
• v.23 no.8
• /
• pp.29-36
• /
• 2022

The importance of subsurface information is becoming crucial in urban area due to increase of underground construction. The position of underground facilities should be identified precisely before excavation work. Geophyiscal exporation method such as ground penetration radar (GPR) can be useful to investigate the subsurface facilities. GPR transmits electromagnetic waves to the ground and analyzes the reflected signals to determine the location and depth of subsurface facilities. Unfortunately, the readability of GPR signal is not favorable. To overcome this deficiency and automate the GPR signal processing, deep learning technique has been introduced recently. The accuracy of deep learning model can be improved with abundant training data. The ground is inherently heteorogeneous and the spacially variable ground properties can affact on the GPR signal. However, the effect of ground heterogeneity on the GPR signal has yet to be fully investigated. In this study, ground heterogeneity is simulated based on the fractal theory and GPR simulation is carried out by using gprMax. It is found that as the fractal dimension increases exceed 2.0, the error of fitting parameter reduces significantly. And the range of water content should be less than 0.14 to secure the validity of analysis.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_1
• /
• pp.1329-1341
• /
• 2022

Destroying the marine environment and marine ecosystem and causing marine accidents, marine debris is generated every year, and among them, submerged marine debris is difficult to identify and collect because it is on the seabed. Therefore, deep-learning-based semantic segmentation was experimented on waste fish nets and waste ropes using underwater images to identify efficient collection and distribution. For segmentation, a high-resolution network (HRNet), a state-of-the-art deep learning technique, was used, and the performance of each optimizer was compared. In the segmentation result fish net, F1 score=(86.46%, 86.20%, 85.29%), IoU=(76.15%, 75.74%, 74.36%), For the rope F1 score=(80.49%, 80.48%, 77.86%), IoU=(67.35%, 67.33%, 63.75%) in the order of adaptive moment estimation (Adam), Momentum, and stochastic gradient descent (SGD). Adam's results were the highest in both fish net and rope. Through the research results, the evaluation of segmentation performance for each optimizer and the possibility of segmentation of marine debris in the latest deep learning technique were confirmed. Accordingly, it is judged that by applying the latest deep learning technique to the identification of submerged marine debris through underwater images, it will be helpful in estimating the distribution of marine sedimentation debris through more accurate and efficient identification than identification through the naked eye.

• Applied Chemistry for Engineering
• /
• v.33 no.6
• /
• pp.636-645
• /
• 2022

In this study, we investigated the adsorption characteristics of methyl orange (MO), an anionic dye, on ginkgo shell-based activated carbon (AC). For this purpose, ACs (GS-1, GS-2, and GS-4) with different textural properties were prepared using ginkgo shells and potassium hydroxide (KOH), a representative chemical activating agent. The correlation between the textural characteristics of AC prepared and the mixing ratio of KOH was investigated using nitrogen adsorption/desorption isotherms. The MO adsorption equilibrium experiment on the prepared ACs was conducted under different pH (pH 3~11) and temperature (298~318 K) conditions, and the results were investigated by Langmuir, Freundlich, Sips and temperature-dependent Sips equations. The feasibility of the MO adsorption treatment process of the prepared AC was also investigated using the dimensionless Langmuir separation factor. The heterogeneous adsorption properties of MO for the prepared AC examined using the adsorption energy distribution function (AED) were closely related to the system temperature and textural characteristics of AC. The kinetic results of the batch adsorption performed at different temperatures can be satisfactorily explained by the homogeneous surface diffusion model (HSDM), which takes into account the external mass transfer, intraparticle diffusion, and active site adsorption. The relationship between the activation energy value obtained by the Arrhenius plot and the adsorption energy distribution function value was also investigated. In addition, the adsorption process mechanism of MO on the prepared AC was evaluated using Biot number.