• Convergence Security Journal
• /
• v.21 no.1
• /
• pp.191-200
• /
• 2021

Artificial intelligence technology is developing in an environment where a lot of data is produced due to the development of computing technology, a cloud environment that can store data, and the spread of personal mobile phones. Among these artificial intelligence technologies, the deep neural network provides excellent performance in image recognition and image classification. There have been many studies on image detection for forest fires and fire prevention using such a deep neural network, but studies on detection of cigarette smoking were insufficient. Meanwhile, military units are establishing surveillance systems for various facilities through CCTV, and it is necessary to detect smoking near ammunition stores or non-smoking areas to prevent fires and explosions. In this paper, by reflecting experimentally optimized numerical values such as activation function and learning rate, we did the detection of smoking pictures and non-smoking pictures in two cases. As experimental data, data was constructed by crawling using pictures of smoking and non-smoking published on the Internet, and a machine learning library was used. As a result of the experiment, when the learning rate is 0.004 and the optimization algorithm Adam is used, it can be seen that the accuracy of 93% and F1-score of 94% are obtained.

• Composites Research
• /
• v.36 no.5
• /
• pp.303-309
• /
• 2023

In this paper, a Progressive Damage and Failure Analysis (PDFA) modeling method was developed using ABAQUS/EXPLICIT to predict in-plane damage and delamination for Open-Hole Compression (OHC) testing. The proposed PDFA model was constructed based on Hashin criteria and cohesive behavior. The strength and stiffness of OHC specimens with three types of stacking sequences [(45/-45/0₂)₃]_s , [(45/0/-45/90)₃]_s and [45/-45/0/45/-45/90/(45/-45)₂]_s were compared to comprehensively evaluate the validity of the Finite Element(FE) model of PDFA. The strength and stiffness of the OHC specimens were predicted relatively well, with less than a percentage error 10.0 %. For the numerical simulation case for each layup, the damage initiation/evolution of OHC specimens were evaluated for delamination and tension/compression matrix damage before and after failure.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.41 no.7
• /
• pp.754-764
• /
• 2016

To understand and analyze SNS(Social Network Service) two important classes of networks, small-world and scale-free networks have gained a lot of research interests. In this study, a generalized network generation method is developed, which can produce small-world network, scale-free network, or network with the properties of both small-world and scale-free by controlling two input parameters. By tuning one parameter we can represent the small-world property and by tuning the other one we can represent both scale-free and small-world properties. For the network measures to represent small-world and scale-free properties clustering coefficient, average shortest path distance and power-law property are used. Using the model proposed in this study we can have more clear understanding about relationships between small-world network and scale-free network. Using numerical examples we have verified the effects of two parameters on clustering coefficient, average shortest path distance and power-law property. Through this investigation it can be shown that small-world network, scale-free network or both can be generated by tuning two input parameters properly.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.31 no.1D
• /
• pp.157-166
• /
• 2011

This study is to mention necessity of building Green-way by foreign theoretical backgrounds and analyzing cases of internal and external, and is purposed on assessment of projects in operation internal by above necessity. For these assessments, looking into cases of green-way plan of external and defining issues by comparing with internal cases to suggest solutions. Green-way planning methods can be classified in physical and non-physical aspects. From among these, for case of non-physical method, its environments of each nation, region, local are all different from each other and can not be turned into a numerical value and quantification, as well. Therefore, analyzing and suggesting the directions on the basis of physical method. Understanding the improvements degree of physical environment of before and after implementation of projects by using successful cases of external similar to actual state of internal. By these process, inflecting to suggest a seek way of applied to internal projects. Local aspects, doesn't have the specific analyzed data of improvement of pedestrian environment and building green-way and are shortage of implementation of projects also. For that reason this study is to look into the status and plans of building green-way in Seoul and analyzing the 7 completed region cases. And suggesting issues of projects and the direction of national and local green-way projects.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.35 no.2
• /
• pp.307-318
• /
• 2015

In this study, the efficiency of two-dimensional inundation analysis using road network was demonstrated in order to reduce the simulation time of numerical model in urban area. For this objective, three simulation conditions were set up: Case 1 considered only inundation within road zone, while Case 2 and 3 considered inundation within road and building zone together. Accordingly, Case 1 used grids generated based on road network, while Case 2 and 3 used uniform and non-uniform grids for whole study area, respectively. Three simulation conditions were applied to Samsung drainage where flood damage occurred due to storm event on Sep. 21, 2010. The efficiency of suggested method in this study was verified by comparison the accuracy and simulation time of Case 1 and those of Case 2 and 3. The results presented that the simulation time was fast in the order of Case 1, 2 and 3, and the fit of inundation area between each case was more than 85% within road zone. Additionally, inundation area of building zone estimated from inundation rating index gave a similar agreement under each case. As a result, it is helpful for study on real-time inundation forecast warning to use a proposed method based on road network and inundation rating index for building zone.

• Journal of Korean Society of Transportation
• /
• v.19 no.3
• /
• pp.101-113
• /
• 2001

Since late 1970s. one of the principal research areas in transportation problem is dynamic traffic assignment (DTA). Although many models have been developed regarding DTA, yet they have some limits of describing real traffic patterns. This reason comes from the fact that DTA model has the time varying constraints such as state equation, flow propagation constraint, first in first out(FIFO) rule and queuing evolution. Thus, DTA model should be designed to satisfy these constraints as well as dynamic route choice condition, dynamic user equilibrium. In this respect, link-based DTA models have difficulty in satisfying such constraints because they have to satisfy the constraints for each link, while path-based DTA models may easily satisfy them. In this paper we develop a path-based DTA model. The model includes point queue theory to describe the queue evolution and simulation loading method for depicting traffic patterns in more detail. From a numerical test, the model shows promising results.

• Journal of the Korea Computer Graphics Society
• /
• v.18 no.2
• /
• pp.1-8
• /
• 2012

High dynamic range (HDR) images represent a far wider numerical range of exposures than common digital images. Thus it can accurately store intensity levels of light found in the specific scenes generated by light sources in the real world. Although a kind of professional HDR cameras which support fast accurate capturing has been developed, high costs prevent from employing those in general working environments. The common method to produce a HDR image with lower cost is to take a set of photos of the target scene with a range of exposures by general purpose cameras, and then to transform them into a HDR image by commercial softwares. However, the method needs complicate and accurate camera calibration processes. Furthermore, creating HDR environment maps which are used to produce high quality imaging contents includes delicate time-consuming manual processes. In this paper, we present an automatic HDR panorama environment map generating system which was constructed to make the complicated jobs of taking pictures easier. And we show that our system can be effectively applicable to photo-realistic compositing tasks which combine 3D graphic models with a 2D background scene using image-based lighting techniques.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.22 no.3
• /
• pp.16-20
• /
• 2018

Steel Fiber reinforced self-compacting concrete (SFRSCC) has been widely used in a number of structures, such as ordinary civil infrastructures, sky scrapers, nuclear power plants, hospitals, dams, channels and etc. Thanks to its short and discrete reinforcing fibers, its performance, including tensile strength, ductility, toughness and flexural strength gets much better in comparison with ordinary self-compacting concrete (SCC) without any reinforcing fibers. Despite all these aforementioned advantages of SFRSCC, its performance highly depends on fiber's orientation. In case of short discrete fibers, the orientation of fibers is completely random and cannot be controlled during pumping process. If fibers distribution inside hardened state concrete are randomly distributed, it leads to less resistance potential of concrete element, especially in terms of flexural and tensile strength. The maximum expected strength may not be achieved. Therefore, fiber alignment has been considered as one of the important factors in SFRSCC. To address this issue, this study investigates the effects of concrete matrix's density and inlet velocity on fiber alignment during the pumping process using a finite element method.

• 한국지구물리탐사학회:학술대회논문집
• /
• 1999.08a
• /
• pp.92-116
• /
• 1999

Tomographic approaches to image underground structure using electrical properties, can be divided into DC resistivity, electromagnetic, and radar tomography, based on the operating frequency. DC resistivity and radar tomography methods have been recently applied to site investigation for engineering purpose in Korea. This paper review these two tomography methods, through the case histories acquired in Korea. As another method of borehole radar survey, borehole radar reflection method is included, and its inherent problem and solution are discussed, how to find the azimuth angle of reflector using direction-finding-antenna. Since the velocity anisotropy of radar wave has been commonly encountered in field data, anisotropic radar tomography is discussed in this paper. In DC resistivity tomography, two subjects are focussed, electrode arrays, and borehole effect owing to the conductive fluid in borehole. Using the numerical modeling data, various kinds of electrode ways are compared, and borehole effect is illustrated. Most of the case histories presented in this paper are compared with known geology, core logging data, and/or Televiewer images.

• Archives of design research
• /
• v.19 no.2 s.64
• /
• pp.151-162
• /
• 2006

The purpose of this thesis is to upgrade brand logo's equity by objective and professional evaluating tool. A brand logo is the main factor in making brand equity, but many times a brand logo is decided without objective judgment because making a logo is considered an intuitive process. To minimize the poor judgment by non-experts, a brand logo needs objective numerical grading tool. Thus, a brand logo is a factor in making a brand identity, not only brand image. That is why brand logo must be chosen by an expert's object judgment. The concrete method to obtain a objective, and at the same time professional grading tool which can De used for the developing and verifying process for a brand logo is as below-first, considering brand judgment from various angles through existing literature, I found various logo grading factors and then extracted them with professional identity designer's subjective consideration. second, applying extracted factors to actual logo grading, verify as a efficient design management tool