• Journal of The Korean Association of Information Education
• /
• v.26 no.3
• /
• pp.197-207
• /
• 2022

In this paper, we develop a machine learning based block code generation and recommendation model for the purpose of reducing cognitive load of learners during coding education that learns the learner's block that has been made in the block programming environment using natural processing model and fine-tuning and then generates and recommends the selectable blocks for the next step. To develop the model, the training dataset was produced by pre-processing 50 block codes that were on the popular block programming language web site 'Entry'. Also, after dividing the pre-processed blocks into training dataset, verification dataset and test dataset, we developed a model that generates block codes based on LSTM, Seq2Seq, and GPT-2 model. In the results of the performance evaluation of the developed model, GPT-2 showed a higher performance than the LSTM and Seq2Seq model in the BLEU and ROUGE scores which measure sentence similarity. The data results generated through the GPT-2 model, show that the performance was relatively similar in the BLEU and ROUGE scores except for the case where the number of blocks was 1 or 17.

• The Journal of Engineering Geology
• /
• v.32 no.4
• /
• pp.643-659
• /
• 2022

Geologic sequestration technologies such as CCS (carbon capture and storage), EGS (enhanced geothermal systems), and EOR (enhanced oil recovery) have been widely implemented in recent years, prompting evaluation of the mechanical stability of storage sites. As fluid injection can stimulate mechanical instability in storage layers by perturbing the stress state and pore pressure, poroelastic models considering various injection scenarios are required. In this study, we calculate the pore pressure, stress distribution, and vertical displacement along a surface using commercial finite element software (COMSOL); fault slips are subsequently simulated using PyLith, an open-source finite element software. The displacement fields, are obtained from PyLith is transferred back to COMSOL to determine changes in coseismic stresses and surface displacements. Our sequential use of COMSOL-PyLith-COMSOL for poroelastic modeling of fluid-injection and induced-earthquakes reveals large variations of pore pressure, vertical displacement, and Coulomb failure stress change during injection periods. On the other hand, the residual stress diffuses into the remote field after injection stops. This flow pattern suggests the necessity of numerical modeling and long-term monitoring, even after injection has stopped. We found that the time at which the Coulomb failure stress reaches the critical point greatly varies with the hydraulic and poroelastic properties (e.g., permeability and Biot-Willis coefficient) of the fault and injection layer. We suggest that an understanding of the detailed physical properties of the surrounding layer is important in selecting the injection site. Our numerical results showing the surface displacement and deviatoric stress distribution with different amounts of fault slip highlight the need to test more variable fault slip scenarios.

• Journal of Environmental Impact Assessment
• /
• v.31 no.4
• /
• pp.214-225
• /
• 2022

This study emphasized the soil of environmental impact assessment to devise measures to minimize the negative impact of project implementation on the environment. As a series of efforts for impact assessment procedures, a national inventory-based database was established for urban development projects, and three machine learning model performance evaluation as well as soil pollutant concentration distribution mapping were conducted. Here, nine soil pollutants were mapped to the metropolitan area of South Korea using the Random Forest model, which showed the best performance. The results of this study found that concentrations of Zn, F, and Cd were relatively concerned in Seoul, where urbanization is the most active. In addition, in the case of Hg and Cr6+, concentrations were detected below the standard, which was derived from a lack of pollutants such as industrial and industrial complexes that affect contents of heavy metals. A significant correlation between land cover and pollutants was inferred through the spatial distribution mapping of soil pollutants. Through this, it is expected that efficient soil management measures for minimizing soil pollution and planning decisions regarding the location of the project site can be established.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.25 no.4
• /
• pp.15-31
• /
• 2022

The Green Purification Unit System (GPUS) is a green infrastructure facility applicable to the roadside to reduce particulate matter from road traffic. This study introduces two types of GPUS (type1 and type2) and assesses the performance and maintenance costs of each of them. The GPUS's performance analysis used the data collected in November 2021 after the installation of the GPUS type1 and type2 at the study site in Suwon. The changes in the particulate matter concentration near the GPUS were measured. The maintenance cost of GPUS type1 and type2 was assessed by calculating the initial installation cost and the management and repair cost after installation. The results of the performance analysis showed that the GPUS type1, which was manufactured by combining plants and electric dust collectors, had a superior particulate matter reduction performance. In particular, type1 produced a greater effect of particulate matter reduction in the time with a high concentration (50㎍/m³ or higher) of particulate matter due to the operation of electric dust collectors. GPUS type2, which was designed in the form of a plant wall without applying an electric dust collector, showed lower reduction performance than type1 but showed sufficiently improved performance compared to the existing band green area. Meanwhile, the GPUS type1 had three times higher costs for the initial installation than GPUS type2. In terms of costs for managing and repairing, it was evaluated that type1 would be slightly more costly than type2. Finally, this study discussed the applicability of two types of GPUS based on the result of the analysis of their particulate matter performance and maintenance cost at the same time. Since GPUS type2 has a cheaper cost than type1, it could be more economical. However, in the area suffering a high concentration of particulate matter, GPUS type1 would be more effective than type2. Therefore, the choice of GPUS types should rely on the status of particulate matter concentration in the area where GPUS is being installed.

• Journal of Practical Engineering Education
• /
• v.14 no.1
• /
• pp.127-136
• /
• 2022

As manufacturing items have changed in various ways, changes in the mass production of small-scale small-scale production of multiple varieties have become commonplace. As a result, the method of the manufacturing site has also changed, and the "smart factory," which emphasizes the production efficiency aspect using automation lines and big data of factories, is in the spotlight according to the global market economy. The introduction performance of smart factories has a positive effect in terms of production efficiency and is drawing a steep upward curve. In addition to the positive aspects, the aspect that needs to be supplemented in the future is the support and cooperation of specialized smart equipment suppliers, but education on standardized smart factories and the relocation of existing manpower, education, evaluation, and creative production that robots cannot replace Various support measures are also needed for activities. In addition, continuous management and systematic education are required to enter the upper stage. Through the case of companies that have built smart factories, it is intended to emphasize the need for proper use of manpower and support management for settlement and maintenance after introduction and continuous on-the-job training through the comparison of productivity before and after introduction to ensure the effect continues.

• Journal of the Korea Convergence Society
• /
• v.13 no.5
• /
• pp.9-19
• /
• 2022

In this study, a systematic review was conducted to analyze the method of applying sEMG to evaluate the swallowing function of the elderly at each stage of swallowing, and to help objectively measure the swallowing stage of the older adults in clinical practice. From 2011 to 2021, 7 studies that met the selection criteria were selected using Pubmed, Scopus, and Web of Science (WoS). As a result of this study, the older adults and adults were divided into an experimental group and a control group and the swallowing phase was analyzed using sEMG only for the older adults. sEMG was used to evaluate swallowing in the oral and pharyngeal stages, and the sEMG attachment site was attached to the swallowing muscle involved in each stage. The collected sEMG data were filtered using a bandpass-filter and a notch-filter, and were analyzed using RMS, amplitude, and maximum spontaneous contraction. In this study, it was found that sEMG can be used as a tool to objectively and quantitatively evaluate the swallowing function in stages. Therefore, it is expected that this study will activate various studies that incorporate sEMG to evaluate the swallowing function in stages.

• Ecology and Resilient Infrastructure
• /
• v.9 no.3
• /
• pp.131-140
• /
• 2022

The magnitude and frequency of extreme floods are increasing owing to the effects of climate change. Therefore, multipurpose flood management techniques incorporating nature-based solutions have been introduced to mitigate the limitations of flood management and river design methods relying on existing observation data. Nature-based solutions to prepare for such extreme flooding events include ways to retreat the embankment, expand the floodplain, and reduce flood damage. To apply these technologies, adopting appropriate location selection methods based on various evaluation factors, such as flood damage reduction effects, sustainable ecological environments, river connectivity, and physical channel structure enhancements, should be prioritized. Therefore, in this study, the optimal location for implementing the multipurpose floodplain construction project was determined by selecting the location of the floodplain expansion with objectivity in the river waterfront area upstream of Daecheong Dam to downstream of Yongdam Dam. Through the final location determination, the Dongdaeje and Jeogokje sections were included in the optimal location considering both flood damage reduction and water environment improvement.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.28 no.7
• /
• pp.1267-1273
• /
• 2022

Although the Korea shipbuilding industry has recently been receiving most of the orders for ships in the world, production processes are being disrupted due to a shortage of manpower at the production site. This is because the workers quit the shipyard as both work and wages were reduced due to the long slump in the shipbuilding industry. The main reason for the increase in orders was the large-scale orders for Qatar LNG carriers, and the situation in which the technical specifications required for ships are becoming more complex is also working to an advantage. Because the contract delivery time is of utmost importance for ships, the dock launch plan is the most important management item among the shipyard's major processes. The structure to be built in the dock may be a hull that has left the design work or a finished vessel, and in some cases, it is often at the level of some blocks of the hull. When launching, the hull is affected by the hogging or sagging moment due to the fluid force, and securing the safety of the structural strength of the block connection is of utmost importance. In a normal process, the connecting member launches after welding has been completed, but in actual shipbuilders, quick decision-making is needed on the conditions for securing structural safety to comply with the docking schedule. In this study, a detailed analysis method and applicability using a bending stress evaluation method and finite element analysis modelling were analyzed to rationally judge the above-mentioned problems from an engineering point of view. The main contents mentioned in the thesis can be used as good examples when conducting similar structural strength evaluations in the future.

• Journal of the Korean Geosynthetics Society
• /
• v.22 no.3
• /
• pp.37-46
• /
• 2023

In this paper, the physical properties, stress deformation and strength characteristics, density and permeability characteristics of silty sand (SM) by fines content were analyzed through indoor tests. also based on the results of the indoor tests, a compact analysis was performed according to the content of SM, and the applicability of SM ground to the compacted target layer was evaluated by comparing it with the measurement data of the actual problem site. As a result of indoor tests and compression analysis, SM changed its mechanical properties from sandy soil to viscous soil when the fine particle content was 35% or higher, and using field measurement data, SM was found to have a higher compression tendency than direct subsidence. Therefore, the mechanical characteristics of SM above Fc 35% are considered to be similar to that of viscous soil, which is different from the compression characteristics of the tendency of immediate subsidence to conventional sandy soil, so it is necessary to present the mechanical characteristics of SM through further research. The research findings highlight the importance of considering consolidation settlement in silty sand (SM) when evaluating soft soil conditions. These findings can aid in revising criteria for assessing weak ground conditions by providing essential engineering property data based on varying fines content in silty sand.

• Journal of the Korean Geotechnical Society
• /
• v.25 no.1
• /
• pp.77-88
• /
• 2009

Cone factors, $N_{kt}$, $N_{ke}$ and $N_{{\Delta}u}$, for estimating undrained shear strength of Busan clay are evaluated in this study. For this, CPTu and field vane tests are performed for clay layers at two sites, Busan new-port and Noksan, and also $CK_0U$ triaxial tests with undisturbed samples taken from the same site are carried out. From experimental results, it is observed that the undrained shear strengths of clay increases with depth, and the undrained shear strength obtained from triaxial tests is 1.5 times higher than one obtained from vane tests. The normalized undrained shear strengths of Busan clay from triaxial and vane shear tests are $0.26{\sim}0.44$ and $0.20{\sim}0.23$, respectively. In CPTu results, cone tip resistance ($q_c$) and pore pressure ($u_2$) linearly increase with depth, and the pore pressure ratio ($B_q$) of Busan clay is within the range of $0.3{\sim}1.0$. The cone factors, which are determined by comparing the CPTu results with $CK_0U$ triaxial and vane shear test results, are found to be $5{\sim}20$ and $10{\sim}35$, respectively. It is also observed that the cone factors are inversely proportional to the pore pressure ratio. From this, the prediction methods for evaluating the cone factors of Busan clay are developed.