• The Journal of the Convergence on Culture Technology
• /
• v.9 no.5
• /
• pp.605-611
• /
• 2023

Accidents at construction sites have a very high rate of fatalities due to the nature of being prone to severe injury patients. In order to reduce the mortality rate of severely injury patients, quick response is required, and some systems that detect accidents using AI technology and cameras have been devised to respond quickly to accidents. However, since existing accident detection systems use only a single camera, there are blind spots, Thus, they cannot detect all accidents at a construction site. Therefore, in this paper, we present the system that minimizes the detection blind spot by using multiple cameras. Our implemented system extracts feature points from the images of multiple cameras with the YOLO-pose library, and inputs the extracted feature points to a Long Short Term Memory-based recurrent neural network in order to detect accidents. In our experimental result, we confirme that the proposed system shows high accuracy while minimizing detection blind spots by using multiple cameras.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1998.06a
• /
• pp.208-212
• /
• 1998

This paper suggests the method to recognize the various defect patterns of cold mill strip using binary decision tree constructed by genetic algorithm automatically. In case of classifying the complex the complex patterns with high similarity like the defect patterns of cold mill strip, the selection of the optimal feature set and the structure of recognizer is important for high recognition rate. In this paper genetic algorithm is used to select a subset of the suitable features at each node in binary decision tree. The feature subset of maximum fitness is chosen and the patterns are classified into two classes by linear decision function. After this process is repeated at each node until all the patterns are classified respectively into individual classes. In this way , binary decision tree classifier is constructed automatically. After construction binary decision tree, the final recognizer is accomplished by the learning process of neural network using a set of standard p tterns at each node. In this paper, binary decision tree classifier is applied to recognition of the defect patterns of cold mill strip and the experimental results are given to show the usefulness of the proposed scheme.

• Journal of the Korean Society of Earth Science Education
• /
• v.1 no.1
• /
• pp.111-118
• /
• 2008

This study is aimed at analyzing earth conception the nine pre service teachers who are majoring in earth science education and classifying a special feature from the ontological categories. Open ended questionnaires and semi structured interviews which meant to contribute to identifying ontological categories of concepts involving study area were designed. Pre service teachers' ontological category about earth conception most showed to dynamic and proto process. In the results show that many pre service teachers recognize simply the conception to a material, a condition and a conversion of the state changing. Most of the pre service teachers show their intermediate understanding level about the earth inner construction according to the analyzed results of the drawing tasks and interviews. The main alternative conceptions show them through a definition of the plate, a wording definition between lithosphere and asthenosphere, a feature of the plate boundary, a heat convection in the earth inner, the earth inner heat source, the earth inner structure, a physical feature of the mantle.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2002.11a
• /
• pp.804-807
• /
• 2002

Edge of image have a many information about input image. There is a many applications to using a edge detection and uses by variable special effect. Edge detection is a field of image analysis, image segmentation using a pixel make the one field for decision of image construction. In this paper, image segmentation through many ways of edge detection for image segmentation. First of all, it analyze feature of image and extract by feature of each image, to adopt way of edge detection to selective. It realize edge detection efficiently, consider to feature of language through using a java image segmentation.

• Tunnel and Underground Space
• /
• v.17 no.3 s.68
• /
• pp.234-243
• /
• 2007

In this paper, it was aimed to enhance core processes required in establishing hydrogeological models constructed using borehole investigation results. Water Conducting Feature(WCF) information was extracted from borehole investigation, and HydroDFN model was constructed based on the WCF information. The HydroDFN model was sub-divided by cubic blocks, and equivalent permeability of each sub-divided block was calculated and compared with the results of hydraulic test at the borehole. Through these analysis processes, suggestion for identifying and prescribing WCF parameters in the construction of HydroDFN model was made.

• International Journal of High-Rise Buildings
• /
• v.8 no.3
• /
• pp.229-234
• /
• 2019

This report introduces the structural design of Hibiya Mitsui Tower built in Tokyo Midtown Hibiya. The upper part of this tower is used for offices and the lower portion is for commercial facilities and a cinema complex which need the large open spaces. The 192m-high building has 35 floors above ground and 4 below ground. The structure is a steel frame using CFT columns to feature the high-performance oil dampers and the buckling restrained braces for vibration control. First, an outline of the structural design of this building is presented. Second, we introduce the transfer frame adopted to realize the large open spaces in the lower part, and the long column supporting the corner part of the high-rise building to avoid making a shade on the adjacent Hibiya Park, which are the feature of this building. Finally, we present an outline of the latest highly efficient semi-active oil dampers adopted in this building, and the vibration responses of this tower.

• Proceedings of the Korean Institute Of Construction Engineering and Management
• /
• 2008.11a
• /
• pp.591-596
• /
• 2008

Success or failure highly depends on delivery method in construction projects. This paper mainly focused on operation model for technical proposal in Large construction projects. This operational model uses Technical Proposal-Based Tender. This project studied order and delivery method in large construction projects. And delivery systems of international and domestic market are researched, and then condition of delivery system and problems are derived from them. Especially, it researched that it is hard to reflect special feature in large construction projects. As a result of having referenced idea as describe above, this paper will be studied by this process. First, definition of delivery method and large construction projects is researched. Second, delivery systems of international and domestic market are checked. Third, problems and condition of delivery system in large construction projects are investigated. Fourth, application of operation model for technical proposal-based tender are presented in large construction projects.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.4 no.3
• /
• pp.305-323
• /
• 2010

This paper proposes an efficient and yet powerful local descriptor called phase-space partition based descriptor (PPD). This descriptor is designed for the mobile image matching and retrieval. PPD, which is inspired from SIFT, also encodes the salient aspects of the image gradient in the neighborhood around an interest point. However, without employing SIFT's smoothed gradient orientation histogram, we apply the region based gradient statistics in phase space to the construction of a feature representation, which allows to reduce much computation requirements. The feature matching experiments demonstrate that PPD achieves favorable performance close to that of SIFT and faster building and matching. We also present results showing that the use of PPD descriptors in a mobile image retrieval application results in a comparable performance to SIFT.

• Proceedings of the Polymer Society of Korea Conference
• /
• 2006.10a
• /
• pp.189-189
• /
• 2006

The self-assembly of supramolecular dendrimers allows the rapid construction of nanosized structures with regularly ordered features that depend on the shape of the molecules and the relative strength of the intra-and intermolecular interactions. Here we report on a dramatic improvement in the degree of control and selectivity in the orientation of fan-shaped supramolecular molecules over a large area, which has been achieved by confined geometries and applied fields. The order and orientation of supramolecular dendrimers can be controlled by surface anchoring in confined geometries. POM, SEM, TEM, AFM and XRD results show that the molecules form the complicated defect-ordering in the microchannels with different feature sizes. We show that these defect domains are strongly influenced by the boundary and feature size of the surfaces. This technique can be used to create a grain size in the plane of the film that is much larger than that which can be achieved using previously reported soft-material based pattering.

• ETRI Journal
• /
• v.41 no.6
• /
• pp.750-759
• /
• 2019

Presently, the extraction of hand-crafted features is still the dominant method in radar emitter recognition. To solve the complicated problems of selection and updation of empirical features, we present a novel automatic feature extraction structure based on deep learning. In particular, a convolutional neural network (CNN) is adopted to extract high-level abstract representations from the time-frequency images of emitter signals. Thus, the redundant process of designing discriminative features can be avoided. Furthermore, to address the performance degradation of a single platform, we propose the construction of an ensemble learning-based architecture for multi-platform fusion recognition. Experimental results indicate that the proposed algorithms are feasible and effective, and they outperform other typical feature extraction and fusion recognition methods in terms of accuracy. Moreover, the proposed structure could be extended to other prevalent ensemble learning alternatives.