• International conference on construction engineering and project management
• /
• 2022.06a
• /
• pp.312-318
• /
• 2022

Robot-based layout automation has been recently promoted for the purpose of improving productivity and quality. Marking robots have various functional demands to secure marking precision and environmental adaptability. In particular, in order to automate marking work of building structure, correction of the marking line through position recognition of rebars placed is required. Because the rebars must maintain a constant cover thickness from the formwork surface, if the rebars are out of planned position, the rebar or marking line need to be corrected to secure the cover thickness. Thus, the marking robot for structural work needs to have the function for determining the position correction of the rebar or the marking line. In order to judge the correction of marking line, it is required to measure the distance between the planned marking line and the rebar placed. Therefore, this study proposes an algorithm that can measure the distance between the planned line and the rebar, and correct marking line for the automatic operation of the marking robot. The results of this study will be utilized as a core function for unmanned operation of the marking robot and contribute to securing precise marking by reflecting construction errors.

• Journal of the Korean Society for information Management
• /
• v.35 no.4
• /
• pp.141-164
• /
• 2018

Recently, as the amount of academic literature has increased rapidly and complex researches have been actively conducted, researchers have difficulty in analyzing trends in previous research. In order to solve this problem, it is necessary to classify information in units of academic papers. However, in Korea, there is no academic database in which such information is provided. In this paper, we propose an automatic classification system that can classify domestic academic literature into multiple classes. To this end, first, academic documents in the technical science field described in Korean were collected and mapped according to class 600 of the DDC by using K-Means clustering technique to construct a learning set capable of multiple classification. As a result of the construction of the training set, 63,915 documents in the Korean technical science field were established except for the values in which metadata does not exist. Using this training set, we implemented and learned the automatic classification engine of academic documents based on deep learning. Experimental results obtained by hand-built experimental set-up showed 78.32% accuracy and 72.45% F1 performance for multiple classification.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.39 no.3
• /
• pp.133-139
• /
• 2021

Currently, the process of constructing a high-definition road map has a high proportion of manual labor, so there are limitations in construction time and cost. Research to automate map production with high-definition road maps using artificial intelligence is being actively conducted, but since the construction of training data for the map construction is also done manually, there is a need to automatically build training data. Therefore, in this study, after converting to images using point clouds acquired by a mobile mapping system, the road marking areas were extracted through image reclassification and overlap analysis using thresholds. Then, a methodology was proposed to automatically construct training data for deep learning data for the high-definition road map through the classification of the polygon types in the extracted regions. As a result of training 2,764 lane data constructed through the proposed methodology on a deep learning-based PointNet model, the training accuracy was 99.977%, and as a result of predicting the lanes of three color types using the trained model, the accuracy was 99.566%. Therefore, it was found that the methodology proposed in this study can efficiently produce training data for high-definition road maps, and it is believed that the map production process of road markings can also be automated.

• Journal of the Korean GEO-environmental Society
• /
• v.15 no.6
• /
• pp.57-65
• /
• 2014

Recently, Construction business is changing from on the ground to underground space because of deficit of developing space, creation of green space and of incremental of land compensation expenses. Meanwhile, 3D Topographic, Marine and Cadastral maps need to have Spatial Interrelation. Also, understanding of the information is also needed. Spatial information object registration system is impossible to contact and understanding intelligence mutually because the former one is managed as automatic ID system. Therefore, 3D Object information ID System of underground space is managed based on Object Identifier. Construction of Spatial information integration ID System is required and it will offer Division Code (Ground, Index, Underground) and depth information. We are defined and classified Under Spatial Information in this paper. Moreover, we developed the integration ID System based on UFID for cadastral information Construction. We supposed underground spatial information DB Construction and a developed the way of exploiting 3D cadastral information system through the study. The research result will be the base data of Standard ID system, DB Construction and system Development of National spatial data which is considered together with spatial interrelation.

• Journal of Construction Engineering and Project Management
• /
• v.1 no.1
• /
• pp.18-23
• /
• 2011

Conservation of energy and fuel is the trend in smart building design. Radio Frequency Integrated Circuit (RFIC) technology is often used in temperature sensing and signal transmission to manage indoor temperature, but it is rarely applied to the shell of the building. Heat retention and poor insulation in building shells are the largest causes of high energy consumption by indoor air conditioning. Through combining RFIC technology with temperature sensors, this study will develop smart temperature information material that can be embedded in concrete. In addition to accurately evaluating the effectiveness of shell insulation material, the already-designed Building Physiology Information System can monitor long-term temperature changes, leading to smarter building health management.

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.6 no.2
• /
• pp.196-204
• /
• 1994

Studied was impact assessment of sea dike construction in Saemankeum. To represent complexity of the geometry and topography of the region a flexible finite grid system are adopted. Combined fine and coarse meshes based on automatic mesh generator were applied in pre-processing. A nonlinear periodic finite element model. TEANL, was implied in this analysis, which gave good results compared to the observed data. It was predicted that the front region of dike connecting Shinsi-Karyeok-Daehang-Pyunsan will behave as a closed rectangular bay with wide width, which may affect significantly to the circulation and dispersion mechanism in the region.

• Korean Journal of Construction Engineering and Management
• /
• v.13 no.5
• /
• pp.103-112
• /
• 2012

Republic of Korea is recently becoming an advanced country with increasing standard of living. This is causing a lack of employment in the construction industry because of high labor costs and it is resulting rapid increase in foreign labors. Modular Method of Construction can be defined as 50%~90% of the entire process is completed in factory, and transferred to construction field to install. The main purpose of this process is to minimize the entire process that possibly can be done at construction field in order to maximize the quality. The current local usage of Modular Method of Construction started at Shin Ki Elementary School during 2003 and it is widely used for military facilities. It should be used more because it has strengths of spending short time period to complete and low production costs. It can make a change if Modular Method of Construction is applied. Toyota is currently producing vehicle with conveyor system and if Modular Method of Construction is applied, then it is possible to reduce the waste of labor, and automatic production time. Expansion of the modular Market can be expected by applying this method because it will improve producing costs, high quality, and enforced process. This research tried to solve the problem of factory's manufacturing production by applying local Modular Method of Construction to provide suggestions and analyze the profitability with applied conveyor system. It is depending on produced model, but this research's model will take 20 months including assessment of payback period.

• Proceedings of the Korean Society of Tribologists and Lubrication Engineers Conference
• /
• 2002.10b
• /
• pp.455-456
• /
• 2002

Wear is one of the main factors causing breakdown and fault of machine, so ferrography technique analyzing wear particles can be an effective way for condition monitoring and fault diagnosis. On the base of the forward multilayer neural network, a nodes self-deleting neural network model is provided in this paper. This network can itself deletes the nodes to optimize its construction. On the basis of the nodes self-deleting neural network, an intelligent ferrography diagnosis expert system (IFDES) for wear particles recognition and wear diagnosis is described. This intelligent expert system can automatically slim lip knowledge by learning from samples and realize basically the entirely automatic processing from wear particles recognition to wear diagnosis.

• Journal of the Korean Society for Railway
• /
• v.2 no.3
• /
• pp.54-60
• /
• 1999

In this paper, design and construction process for the standardized electric motor car according to standard specification is described. Aluminum extrusion profiles and power and control system made domestically are used in the electric motor car. Also, plug-sliding door system for noise reduction and automatic train control system are developed and applied. Through the development of the electric motor car, most electric and control systems can be substituted by domestic standard systems, and safety and reliability of electric motor cars can be secured.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2015.07a
• /
• pp.516-517
• /
• 2015

The automatic traffic sign detection and recognition has been one of the highly researched and an important component of advanced driver assistance systems (ADAS). They are designed especially to warn the drivers of imminent dangers such as sharp curves, under construction zone, etc. This paper presents a traffic sign recognition (TSR) system using morphological operations and multiple descriptors. The TSR system is realized in three stages: segmentation, shape classification and recognition stage. The system is designed to attain maximum accuracy at the segmentation stage with the inclusion of morphological operations and boost the computation time at the shape classification stage using MB-LBP descriptor. The proposed system is tested on the German traffic sign recognition benchmark (GTSRB) and on Korean traffic sign dataset.