• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.21 no.2
• /
• pp.53-64
• /
• 2018

This study aims to quantitatively evaluate the conservation priorities of unexecuted urban parks in Seoul both from an ecological and public perspective. To this end, two methodologies, ecological network analysis based on graph and circuit theory and accessibility analysis, were employed in order to assess ecological connectivity of and public accessibility to unexecuted parks, respectively. This study applied linkage-mapping methods (shortest path and current flow betweenness centrality) of connectivity analysis to an integrated map of landscape permeability. The population-weighted accessibility to unexecuted parks was measured based on a negative exponential distance decay function. As a result, for both ecological connectivity and accessibility, Gwanaksan, Suraksan, and Bulamsan urban natural parks are found to be the most important (rank 1-3) to be conserved. For these sites, inner park areas with conservation priorities for connectivity and accessibility were identified. The findings of the study can be used for giving conservation priority to the unexecuted urban parks in terms of long-term sustainable urban planning.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.12 no.4
• /
• pp.1-10
• /
• 2009

This study has intended to build ecological networks in consideration of life-zones inside Cheongju city through biotope grade, GIS network analysis etc. This study consisted of following three steps. First, we selected core districts and core spot districts using land use patten and biotope grade. The core district included the first grade of biotope and forest land. The core district consisted of two sectors : east axis core, Uam mountain; west axis core, Bumo mountain. The core spot district included the first grade of biotope. The core spot districts consisted of two sectors : north axis base core, Myongshim park; south axis base core, Guryong park. Second, the base district included the second grade of biotope and park and school. We used buffering analysis within 500m of the base district and selected the new base district. Third, we connected core districts and base core districts using least cost analysis of GIS. Thus we built comprehensive ecological networks in consideration of life-zones through GIS.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.14 no.3
• /
• pp.143-155
• /
• 2011

Recently, in forest areas of Gyeonggi-Do where golf courses are developed indiscriminately due to the rapid increase in demand, two and three golf courses are being concentrated and combined to develop and it's occurring lots of problems. This study therefore, aims to examine their problems and propose environment-friendly improvements of combined development, by analyzing laws related to golf course's location and the current location status. The results of this study are as followings; Firstly, when analyzing related laws, it was found that unified standards should be established in relation to regulation of the external conditions of golf course sites and individual index. Secondly, standards of a proper separated distance are needed, when developing golf courses. Thirdly, we need to preferentially preserve areas where should be protected environmentally, and establish criteria approving golf courses built close to the boundary of a buffer area only, by introducing the concepts of a buffer area based on the UNESCO MAB. Lastly, we have to set up criteria considering Network elements for maintaining the connectivity of the ecosystem.

• Imaging Science in Dentistry
• /
• v.50 no.4
• /
• pp.331-337
• /
• 2020

Purpose: As cone-beam computed tomography (CBCT) has become the most widely used 3-dimensional (3D) imaging modality in the dental field, storage space and costs for large-capacity data have become an important issue. Therefore, if 3D data can be stored at a clinically acceptable compression rate, the burden in terms of storage space and cost can be reduced and data can be managed more efficiently. In this study, a deep learning network for super-resolution was tested to restore compressed virtual CBCT images. Materials and Methods: Virtual CBCT image data were created with a publicly available online dataset (CQ500) of multidetector computed tomography images using CBCT reconstruction software (TIGRE). A very deep super-resolution (VDSR) network was trained to restore high-resolution virtual CBCT images from the low-resolution virtual CBCT images. Results: The images reconstructed by VDSR showed better image quality than bicubic interpolation in restored images at various scale ratios. The highest scale ratio with clinically acceptable reconstruction accuracy using VDSR was 2.1. Conclusion: VDSR showed promising restoration accuracy in this study. In the future, it will be necessary to experiment with new deep learning algorithms and large-scale data for clinical application of this technology.

• Korean Journal of Remote Sensing
• /
• v.38 no.1
• /
• pp.33-43
• /
• 2022

This study presents a method to restore an optical satellite image with distortion and occlusion due to fog, haze, and clouds to one that minimizes degradation factors by referring to the same type of peripheral image. Specifically, the time and cost of re-photographing were reduced by partially occluding a region. To maintain the original image's pixel value as much as possible and to maintain restored and unrestored area continuity, a simulation restoration technique modified with the Cycle Generative Adversarial Network (CycleGAN) method was developed. The accuracy of the simulated image was analyzed by comparing CycleGAN and histogram matching, as well as the pixel value distribution, with the original image. The results show that for Site 1 (out of three sites), the root mean square error and R² of CycleGAN were 169.36 and 0.9917, respectively, showing lower errors than those for histogram matching (170.43 and 0.9896, respectively). Further, comparison of the mean and standard deviation values of images simulated by CycleGAN and histogram matching with the ground truth pixel values confirmed the CycleGAN methodology as being closer to the ground truth value. Even for the histogram distribution of the simulated images, CycleGAN was closer to the ground truth than histogram matching.

• Journal of Information Technology Services
• /
• v.22 no.5
• /
• pp.87-98
• /
• 2023

Traditionally, tooth restoration has been carried out by replicating teeth using plaster-based materials. However, recent technological advances have simplified the production process through the introduction of computer-aided design(CAD) systems. Nevertheless, dental restoration varies among individuals, and the skill level of dental technicians significantly influences the accuracy of the manufacturing process. To address this challenge, this paper proposes an approach to designing personalized tooth restorations using Generative Adversarial Network(GAN), a widely adopted technique in computer vision. The primary objective of this model is to create customized dental prosthesis for each patient by utilizing 3D data of the specific teeth to be treated and their corresponding opposite tooth. To achieve this, the 3D dental data is converted into a depth map format and used as input data for the GAN model. The proposed model leverages the network architecture of Pixel2Style2Pixel, which has demonstrated superior performance compared to existing models for image conversion and dental prosthesis generation. Furthermore, this approach holds promising potential for future advancements in dental and implant production.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.18 no.6
• /
• pp.97-110
• /
• 2015

This study aimed to classify damaged lands, to find what are the damage factors affecting the studied area, and to present a prescription in order to provide some benefit for the restoration of Regional Ecological Network at Chungnam province. Finally we classified damaged lands from 1st to 4th damaged lands according to relative intensity of damage. The main damage factors for the First Damage Lands were humus horizon, soil hardness and plant species richness. In the Second Damage Lands, those were soil hardness, plant species richness, number of plants and dominant plant species. In the Third Damage Lands, those were humus horizon, soil hardness, plant species richness, number of plants and dominant plant species. In the Fourth Damage Lands, those were humus horizon, organic matter, soil hardness, EC, T-N content, plant species richness, number of plants and dominant plant species. In every cases, the damage of soil and vegetation was originated due to development carried out by human being. The changes in soil condition were not big enough for it to affect plant growth, however, degradation of vegetation was still severe.

• Ecology and Resilient Infrastructure
• /
• v.6 no.1
• /
• pp.69-76
• /
• 2019

Ecosystem services are contributing to human welfare by enabling us to maintain our survival and quality of life. A metod of quantifying ecological functions is needed. We discussed the introduction and applications of ecosystem services to applied ecological engineering. The concept and assessment system of ecosystem services were applied to the economic valuation of river, the construction of blue-green-white network in urban area, ecological restoration, and integrated water management in Korea. The conceptual framework and assessment of ecosystem services can be used to promote value of ecological protection and restoration, helping stakeholders understand the benefits of ecosystems and increasing applications of the applied ecological engineering.

• Journal of Internet of Things and Convergence
• /
• v.8 no.2
• /
• pp.79-84
• /
• 2022

This paper presents an enhancement method of document restoration capability which is robust for security, loss, and contamination, It is based on two methods, that is, encryption and DnCNN(DeNoise Convolution Neural Network). In order to implement this encryption method, a mathematical model is applied as a spatial frequency transfer function used in optics of 2D image information. Then a method is proposed with optical interference patterns as encryption using spatial frequency transfer functions and using mathematical variables of spatial frequency transfer functions as ciphers. In addition, by applying the DnCNN method which is bsed on deep learning technique, the restoration capability is enhanced by removing noise. With an experimental evaluation, with 65% information loss, by applying Pre-Training DnCNN Deep Learning, the peak signal-to-noise ratio (PSNR) shows 11% or more superior in compared to that of the spatial frequency transfer function only. In addition, it is confirmed that the characteristic of CC(Correlation Coefficient) is enhanced by 16% or more.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.6 no.3
• /
• pp.79-85
• /
• 2003

Human beings have pursued development and economic betterment; thus, enhancing convenience and prosperity. A flourish of human civilization upon the industrialization results a massive urbanization. However, human beings have connived the environmental importance in the course of rapid urbanization. The environmental quality now becomes one of the most important factors that determine the quality of life in a city. Many studies were proceeded about the heat island effect in large cities. In general, most studies have been done to investigate urban microclimate phenomena using meteorological network or AWS (automatic weather station) data. Those preceding studies do not seem to sufficiently reflect the and thus, failed to show regional representative. In this study, temporal Landsat TM satellite imageries of May 20, 1987 and May 21, 1999 were 뻐d in order to detect the surface temperature of the study area using the band 6 ($10.4{\mu}m{\sim}12.5{\mu}m$). The surface temperature distribution detected by the band 6 of Landsat TM was over layed with the land cover classification data in order to investigate the temperature difference of the paved road and the riparian areas of the stream. As a result, a surface temperature difference as much as $3^{\circ}C$ between the paved road and the riparian areas with vegetation was observed. This study concludes that the land cover change is one of the main causes of urban heat island effect which may be closely affected by the paved areas and roads. Besides, the change of the atmospheric temperature followed by the urban secular change could have been confirmed. In the case of Yangjaecheon stream which underwent a heavy environmental restoration in 1995, the temperature was decreased as much as $0.6^{\circ}C$ after the restoration. The results of this study is expected to contribute to develop an urban space in harmony with the healthy human life and the environment respecting the crucial role of vegetation to stabilize the urban environmental dynamics.