• Journal of Korea Water Resources Association
• /
• v.57 no.7
• /
• pp.437-449
• /
• 2024

Rainfall-runoff prediction studies using deep learning while considering catchment attributes have been gaining attention. In this study, we selected two models: the Transformer model, which is suitable for large-scale data training through the self-attention mechanism, and the LSTM-based multi-state-vector sequence-to-sequence (LSTM-MSV-S2S) model with an encoder-decoder structure. These models were constructed to incorporate catchment attributes and predict the inflow of 10 multi-purpose dam watersheds in South Korea. The experimental design consisted of three training methods: Single-basin Training (ST), Pretraining (PT), and Pretraining-Finetuning (PT-FT). The input data for the models included 10 selected watershed attributes along with meteorological data. The inflow prediction performance was compared based on the training methods. The results showed that the Transformer model outperformed the LSTM-MSV-S2S model when using the PT and PT-FT methods, with the PT-FT method yielding the highest performance. The LSTM-MSV-S2S model showed better performance than the Transformer when using the ST method; however, it showed lower performance when using the PT and PT-FT methods. Additionally, the embedding layer activation vectors and raw catchment attributes were used to cluster watersheds and analyze whether the models learned the similarities between them. The Transformer model demonstrated improved performance among watersheds with similar activation vectors, proving that utilizing information from other pre-trained watersheds enhances the prediction performance. This study compared the suitable models and training methods for each multi-purpose dam and highlighted the necessity of constructing deep learning models using PT and PT-FT methods for domestic watersheds. Furthermore, the results confirmed that the Transformer model outperforms the LSTM-MSV-S2S model when applying PT and PT-FT methods.

• Information Systems Review
• /
• v.18 no.1
• /
• pp.79-103
• /
• 2016

The Korean Army has to construct a system that will enable it to cope immediately with the flexible military relationships in Northeast Asia by systematizing and improving the efficiency of operations. These improvements include building a smart and strong army, concentrating on cost-effective combat skills, maximizing the utilization of private resources, and establishing a military structure based on information and technology. Accordingly, this study proposes solutions to solve the problems affecting the success of outsourcing in the defense industry. Unlike outsourcing in other government ministries, outsourcing in the national defense sector may be unrealistic because this strategy is related to the renovation project of the Ministry of the National Defense. In general, the objective of outsourcing in the defense industry, similar to other businesses, is to improve efficiency and not to reduce troops and national defense budget. Several factors, such as identification and security guarantee, risk reduction, cost saving, quality improvement, the reliability of enterprise, and professional technology, are necessary to ensure outsourcing success in the national defense sector. In terms of effectiveness, the improvement in service quality significantly influences outsourcing success in the national defense sector. Eventually, the national defense forces must be strengthened to prevent the provocative actions of North Korea and other threats by improving identification, sense of national security, and quality unlike the current outsourcing of the government, as well as emulating German GEBB or PMC, which utilizes social capital.

• Journal of the Korean Geotechnical Society
• /
• v.38 no.3
• /
• pp.35-42
• /
• 2022

The N-value from the Standard Penetration Test (SPT), which is one of the representative in-situ test, is an important index that provides basic geological information and the depth of the bearing layer for the design of geotechnical structures. In the aspect of time and cost-effectiveness, there is a need to carry out a representative sampling test. However, the various variability and uncertainty are existing in the soil layer, so it is difficult to grasp the characteristics of the entire field from the limited test results. Thus the spatial interpolation techniques such as Kriging and IDW (inverse distance weighted) have been used for predicting unknown point from existing data. Recently, in order to increase the accuracy of interpolation results, studies that combine the geotechnics and deep learning method have been conducted. In this study, based on the SPT results of about 22,000 holes of ground survey, a comparative study was conducted to predict the depth of the bearing layer using deep learning methods and IDW. The average error among the prediction results of the bearing layer of each analysis model was 3.01 m for IDW, 3.22 m and 2.46 m for fully connected network and PointNet, respectively. The standard deviation was 3.99 for IDW, 3.95 and 3.54 for fully connected network and PointNet. As a result, the point net deep learing algorithm showed improved results compared to IDW and other deep learning method.

• Journal of Cadastre & Land InformatiX
• /
• v.54 no.1
• /
• pp.89-102
• /
• 2024

The recent advancements in Smart City and Digital Twin technologies have highlighted the critical role of integrating GIS and BIM in urban planning and construction projects. This integration ensures the consistency and accuracy of information, facilitating smooth information exchange. However, achieving interoperability requires standardization and effective project integration management strategies. This study proposes interoperability solutions for the integration of GIS and BIM for managing various projects. The research involves an in-depth analysis of the IFC schema and data structures based on the latest IFC4 version and proposes methods to ensure the consistency of reference point coordinates and coordinate systems. The study was conducted by setting the EPSG:5186 coordinate system, used by the National Geographic Information Institute's digital topographic map, and applying virtual shift origin coordinates. Through BIMvision, the results of the shape and error check coordinates' movement in the BIM model were reviewed, confirming that the error check coordinates moved consistently with the reference point coordinates. Additionally, it was verified that even when the coordinate system was changed to EPSG:5179 used by Naver Map and road name addresses, or EPSG:5181 used by Kakao Map, the BIM model's shape and coordinates remained consistently unchanged. Notably, by inputting the EPSG code information into the IFC file, the potential for coordinate system interoperability between projects was confirmed. Therefore, this study presents an integrated and systematic management approach for information sharing, automation processes, enhanced collaboration, and sustainable development of GIS and BIM. This is expected to improve compatibility across various software platforms, enhancing information consistency and efficiency across multiple projects.

• Journal of the Society of Disaster Information
• /
• v.16 no.3
• /
• pp.472-478
• /
• 2020

Purpose: The purpose of the study is to help economic and safe construction by accurately predicting the initial strength of high-strength concrete (70MPa) for each type of cement, securing reliability of concrete quality, and drawing accurately the timing of form deformed, tensioning time of PS concrete, and openning of traffic after road repair with maturity. Method: Calculate the maturity by measuring the hydration heat with cement type for each age, and measure the strength of concrete with age to predict the strength corresponding to the any maturity. Result: In estimating the time required for traffic opening in road repair, ASTM C1074 was theoretically estimated at 16.4 hours for high-strength concrete, but in this study, maturity was calculated at 307, 14.4 hours for OPC and maturity at 2700, 34 hours for LHPC and maturity 200, 8 hours for ESPC. Conclusion: The timing of form deformed of structures using high-strength concrete and the opening of traffic of road repair may be much faster than in the case of concrete using OPC below the design basis strength 40MPa applied by ACI Committee 347.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.10 no.10
• /
• pp.1842-1847
• /
• 2006

This paper is the environmental impact assessment of at road design in the light of the sense for the real from the virtual reality. For In this papers, This study developed 3D-model and virtual reality contents by suggesting the environmental impact assessment based on GIS in the road design. Ant through this process, it's possible to visualize the environmental impact assessment by constructing the 3D-model and simulation. The 3D-model can be a method to show the road effectively by maximizing the road's shape visually after the construction. The main construction which composes polyhedron model that is generated from digital map and aerial photo is built by mapping the real texture, so the Sense for the Real was more heightened. Through this study, it must be made to shorten a long time exhausting period of conference and construct more real road after due scene consideration by specific and various low-cost strategy in the environmental impact assessment afterwards.

• Journal of Korean Society for Geospatial Information Science
• /
• v.13 no.4 s.34
• /
• pp.39-46
• /
• 2005

This paper use virtual running after possible traffic capacity application for optimal route location. General road is designed the design after we examine an alternate adequacy investigation and an execution design sufficiently. Various road user's requirement must be reflected from the beginning. But it is difficult to contain the various suitable design criteria because we consider the existing 2-dimension element. First of all, this study chose optimal route, used traffic assignment and 3D simulation. Then selected optimal route through the consistent road construction by analyzing road driving simulation of 3-dimension data and the urban landscape. possible traffic capacity and virtual running will be able to do the urban landscape analysis harmonizing with the environment; equally, it could be objectively solve the problem of a civil appeal.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.17 no.8
• /
• pp.38-45
• /
• 2016

The objective of this research is to develop a method of improving MEP facility management based on 3D reverse engineering. Recently, 3D image scanning-based reverse engineering has been implemented in the fields of architecture, construction and (manufacturing). In the case where there are many objects and the MEP system is complicated, 3D reverse engineering is applied in semiconductor factories, because facility maintenance works cause the 2D drawing to be different from the original one. The 3D point cloud data obtained from 3D image scanning contains accurate data and can increase the efficiency of complicated MEP facility maintenance works. For this purpose, the present research studied the technology trends and analyzed the process of 3D reverse engineering. Based on the results, a method of improving MEP facility management is established and its effects described.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.26 no.6
• /
• pp.591-598
• /
• 2008

Recently, the government has improvement projects of dangerous road for the site that has very high accident rate due to bad geometric structures of the road. Although, route selecting of the road is a basic and important process, but the process of route selecting must consider the technical, safety and environment factor together. Also, the technology for the 3-dimensional terrain model can be used as an important factor in planning and designing for selecting alternative route projects. In the course of experimenting with the 3-dimensional topography generated by the combination of the digital map and drawing of route, the technology as been developed to offer the multi-dimensional access to the potential construction sites from the nearby main roads. This 3-dimensional digital elevation model has made it possible to make various terrain analysis base on GIS, which provides real-time virtual access to the designated construction sites for development planning and construction projects. Therefore, this study presents a reasonable plan for route selecting from some alternative routes through subjective evaluation and classify the methods linked basic design of road construction.

• Journal of the Society of Disaster Information
• /
• v.15 no.4
• /
• pp.540-547
• /
• 2019

Purpose: This paper is for the improvement of the fire gate performance that occurs between the construction company and the residents. A survey was conducted on experts in the construction to prepare the causes and measures for the suit. Method: The application of the Analytic Hierarchy Process(AHP) resulted in the following conclusions. Results: TIn the 2nd tier, 28percent of the "strengthening standards for installation of fire prevention zones" included in the "institutional strengthening of stnadards" of the 1st tier had higher importance. In the 3rd tier, "strengthening the installation standards by floor area" and "strengthening the standard of fire-resistant structures" showed high importance. Conclusion: The results suggest that detailed legal criteria for detailed installation criteria with varying site conditions are needed.