• Journal of Korean Tunnelling and Underground Space Association
• /
• v.24 no.6
• /
• pp.583-598
• /
• 2022

As human-based tunnel inspections are affected by the subjective judgment of the inspector, making continuous history management difficult. There is a lot of deep learning-based automatic crack detection research recently. However, the large public crack datasets used in most studies differ significantly from those in tunnels. Also, additional work is required to build sophisticated crack labels in current tunnel evaluation. Therefore, we present a method to improve crack detection performance by inputting existing datasets into a deep learning model. We evaluate and compare the performance of deep learning models trained by combining existing tunnel datasets, high-quality tunnel datasets, and public crack datasets. As a result, DeepLabv3+ with Cross-Entropy loss function performed best when trained on both public datasets, patchwise classification, and oversampled tunnel datasets. In the future, we expect to contribute to establishing a plan to efficiently utilize the tunnel image acquisition system's data for deep learning model learning.

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.33 no.3
• /
• pp.101-109
• /
• 2021

Wave observations using a marine X-band radar are conducted by analyzing the backscattered radar signal from sea surfaces. Wave parameters are extracted using Modulation Transfer Function obtained from 3D wave number and frequency spectra which are calculated by 3D FFT of time series of sea surface images (42 images per minute). The accuracy of estimation of the significant wave height is, therefore, critically dependent on the quality of radar images. Wave observations during Typhoon Maysak and Haishen in the summer of 2020 show large errors in the estimation of the significant wave heights. It is because of the deteriorated radar images due to raindrops falling on the sea surface. This paper presents the algorithm developed to increase the accuracy of wave heights estimation from radar images by adopting convolution neural network(CNN) which automatically classify radar images into rain and non-rain cases. Then, an algorithm for deriving the Hs is proposed by creating different ANN models and selectively applying them according to the rain or non-rain cases. The developed algorithm applied to heavy rain cases during typhoons and showed critically improved results.

• Journal of Satellite, Information and Communications
• /
• v.10 no.4
• /
• pp.95-100
• /
• 2015

These days, satellite core technologies are being developed as a way to provide various information by considering simultaneously sending, wide area covering, highly precide, and anti-disaster technologies. Not only global positioning, and image but also space launcher, satellite bus, satellite payload, earth station are being convergently developed in a different technological field. Especially, it is required a lot of initial investing expenditure to provide the Earth observational information service based on the space technologies. Such a trend and change of satellite technologies Korea has realized the necessity for the domestic independent development of next generation earth observation satellites, and are preparing the profound items such as a detailed implementation plan for the efficient development project. Like the satellite advanced countries, it should be transparently carried out that an efficient implementation of the developing target related to the geostationary earth observation satellite development, establishment of technological auditing function and quality assurance system, implementation plan, progressing courses and results of the satellite development program by way of planning, evaluation and management. For these things cited above, it is necessary to operate systematically and continuously the professional structural system by the governmental department in order to control the geostationary earth observation satellite development project. Therefore, this study proposes a development project management improvement method of the Korea next generation geostationary earth observation satellite based on the development project management system of the domestic geostationary satellite system.

• Journal of radiological science and technology
• /
• v.28 no.1
• /
• pp.55-65
• /
• 2005

Research of actual condition of working conditions in the small and clinics, in the Seoul metropolitan city and Kyeonggido province. With the health care environmental change such as a rapid increase of the elderly people, rapid increase of health promotion needs, it is necessary to analyse and identity of the actual condition of working conditions for present and new radiological technologist. Research of general characteristics for the present radiological technologist. To research of the status employment, business scope, pay, working conditions, radiation safety management, equipment, and category association. Defining the problems of related working conditions, radiation safety management for the comprehensive methods to promote the rights the radiological technologist. A proposal for establishment legislature and system of the actual condition in the hospital for radiological technologist. Estimation for the demand and supply numbers of present radiological technologist and improvement of employment relations. Improved and refined scope business and duty regulation related to radiological technologist. Application for the establishment and development of promotion rights to utilize as basic data in a legislative and system frame of reference to implement the radiological technologist.

• Geophysics and Geophysical Exploration
• /
• v.11 no.1
• /
• pp.34-40
• /
• 2008

Underwater seismic refraction with advanced interpretation approaches makes important contributions to shallow marine exploration and geotechnical investigations in Australia's coastal areas. A series of case studies are presented to demonstrate the recent applications of continuous and static USR methods to river crossing and port infrastructure projects at various sites around Australia. In Sydney, static underwater seismic refraction (USR) with bottom-placed receivers and borehole seismic imaging assisted the development of improved geotechnical models that reduced construction risk for a tunnel crossing of the Lane Cove River. In Melbourne, combining conventional boomer reflection and continuous USR with near-bottom sources and receivers improved the definition of a buried, variably weathered basalt flow and assisted dredging assessment for navigation channel upgrades at Geelong Ports. Sand quality assessment with continuous USR and widely spaced borehole information assisted commercial decisions on available sand resources for the reclamation phase of development at the Port of Brisbane. Buried reefs and indurated layers occur in Australian coastal sediments with the characteristics of laterally limited, high velocity, cap layers within lower velocity materials. If these features are not recognised then significant error in depth determination to deeper refractors can occur. Application of advanced refraction inversion using wavefront eikonal tomography to continuous USR data obtained along the route of a proposed offshore pipeline near Fremantle allowed these layers and the underlying bedrock refractor to be accurately imaged. Static USR and the same interpretation approach was used to image the drowned granitic regolith beneath sediments and indurated layers in the northern area of Western Australia at a proposed new berthing site where deep piling was required. This allowed preferred piling sites to be identified, reducing overall pile lengths. USR can be expected to find increased application to shallow marine exploration and geotechnical investigations in Australia's coastal areas as economic growth continues and improved interpretation methods are developed.

• Journal of the Korean Society of Radiology
• /
• v.10 no.8
• /
• pp.597-602
• /
• 2016

Recent clinical field utilizes the aluminium filter in order to reduce the low-energy photons. However, the usage of the filter can cause adverse effect on the image quality because of the scattered dose that is generated by X-ray hardening phenomenon. Further, usage of filter with improper thickness can be a reason of dose creep phenomenon where unnecessary exposure is generated towards the patient. In this study, the author evaluated the RMS and the RSD analysis in order to have a quantitative evaluation for the effect of forward scattering dose by the filter on the image. as a result of the study, the FSR and the RSD was increased together with the increasing of thickness of the filter. In this study the RSD means the standard deviation of the mean value is relatively size. It can be understood that the signal-to-noise ratio decreases when the average value is taken as a signal and the standard deviation is judged as a noise. The signal-to-noise ratio can understanding as index of resolution at image. Based on these findings, it was quantitatively verified that there is a correlation of the image quality with the FSR by using an additional filter. The results, a 2.5 mmAl which is as recommended by NCRP in the tube voltage of 70 kVp or more showed the 14.6% on the RSD when the filter was not in used. these results are considered able to be utilized as basic data for the study about the filter to improve the quality of the image.

• Food Science and Preservation
• /
• v.14 no.4
• /
• pp.414-418
• /
• 2007

The physicochemical characteristics and sensory properties of Deodeok wine, formed by leaching of Deodeok at room temperature for 180 days, were investigated over the following range of Deodeok levels: 10, 15 and 20% (all w/v). The higher the level of Deodeok, the greater were the final values of total sugars, reducing sugars, total polyphenols, and crude saponins. The Hunter's b-value (yellowness) of Deodeok wine varied markedly with Deodeok levels, and yellowness was highest in Deodeok wine containing 20% (w/v) Deodeok. Non-volatile compounds, that form the basis of the liquor tax law, were 0.64, 1.38 and 2.11% (all w/v), respectively, at day 160. Of these values, that of 2.11% (w/v), the level of non-volatile compounds in Deodeok wine containing 20% (w/v) Deodeok, was in accord with the liquor tax law (that requires this figure to be 2.0%). Sensory evaluation showed that Deodeok wine containing 20% (w/v) Deodeok was superior to the other wines tested.

• Proceedings of the Korean Society of Dyers and Finishers Conference
• /
• 2011.03a
• /
• pp.29-29
• /
• 2011

아라미드 섬유는 열에 강한 튼튼한 방향족 폴리아마이드 섬유이다. 아마이드는 "85%이상의 아미드(CO-NH)기가 두 개의 방향족 고리에 직접 연결된 합성 폴리아미드로부터 제조된 섬유"로 정의된다. 아라미드 섬유는 크게 파라계와 메타계로 대별되는데 본 연구에서 사용한 파라계 아라미드는 인장강도, 강인성, 내열성이 뛰어나며 고강력 고탄성률을 지니고 있다. 일반적인 유기 섬유와는 다른 우수한 성질을 바탕으로 부직포, UD laminatig, staple 등의 형태로 크게 섬유보강 고무 복합재료 등의 각종 복합재료, 로프, 케이블, 방탄방호용과 같은 산업자재의 용도로 자동차, 우주항공, 정보통신, 국방, 등 다양한 관련 산업분야에서 사용이 확대되고 있는 고부가 소재이며 가격대비 성능비가 우수하기 때문에 세계적으로 산업용 섬유 및 초고성능 섬유시장에서 비중이 증가될 것으로 예상되고 있다. 본 연구에서는 Para-Aramid 필라멘트를 이용하여 ATY를 생산할 때 제조공정조건에 따른 ATY 물성을 알아보고 고강도를 요구하는 방화복, 고무 보강용 섬유 등의 소재에 맞는 ATY 사가공 최적공정조건을 도출하여 체계화된 data-base를 구축하여 생산성 향상 및 품질개선과 함께 산업자재용 직물개발에 응용하고자 한다. 아라미드를 ATY로 제조할 경우, 표면에 생기는 loop로 인하여 타소재와 접착시, 접착제 담지 성능이 향상되어 접착력이 상승되는 반면, 아라미드 ATY가 기존의 아라미드의 물성보다 저하되는 약점을 가지고 있으므로 이를 보완하기 위해 본 연구에서는 ATY 제조공정에서 중요 공정인자인 사속, heater 온도, over feed ratio를 변화시켜 시료를 제조하여 이들의 물성을 분석하여 최적의 물성을 갖는 ATY 사가공 공정을 도출함으로써 물성이 저하되는 문제를 보완 가능할 것으로 기대된다. 물성분석은 강신도, 초기탄성률을 각각 측정하여 인장특성을 확인하였으며, 습열수축률과 건열수축률을 측정하여 시료의 열수축률에 대해 측정을 하였다. 표면의 루프 발현 정도를 보기 위하여 Crimp Rigidity(CR%), 형태 불안정성(instability)등을 측정하였으며, 영상 현미경 시스템을 사용하여 ${\times}40$ 배율로 표면특성을 측정하였다.

• Journal of Korean Society for Geospatial Information Science
• /
• v.23 no.3
• /
• pp.57-67
• /
• 2015

Land characteristics should be surveyed in an accurate and objective manner as they are important data to the formation of land prices. The ambiguous survey and estimation guidelines, however, make it possible for surveyors to intervene with their subjective judgments. There is thus a definite need for improvement. It is also extremely important to survey the characteristics of individual land lots in an accurate and objective manner in order to estimate officially assessed land prices in a swift and accurate way. For objective land appraisal and evaluation, this study set out to objectively identify the characteristics of lots according to various topographical conditions by using UAV based high quality geospatial information, panorama VR images, and GIS analysis technique and thus make a contribution to a rational and consistent estimation system of officially assessed land prices. Trying to assess the technique proposed in the study, the investigator analyzed the old data about the officially assessed land prices of the subject areas and then the evaluation data of certified public appraisers.

• Journal of the Korea Computer Graphics Society
• /
• v.27 no.3
• /
• pp.65-74
• /
• 2021

3D reconstruction means that reconstructing the 3D shape of the object in an image and a video. We proposed a progressive occupancy network architecture that can recover not only the overall shape of the object but also the local details. Unlike the original occupancy network, which uses a feature vector embedding information of the whole image, we extract and utilize the different levels of image features depending on the receptive field size. We also propose a novel network architecture that applies the image features sequentially to the decoder blocks in the decoder and improves the quality of the reconstructed 3D shape progressively. In addition, we design a novel decoder block structure that combines the different levels of image features properly and uses them for updating the input point feature. We trained our progressive occupancy network with ShapeNet. We compare its representation power with two prior methods, including prior occupancy network(ONet) and the recent work(DISN) that used different levels of image features like ours. From the perspective of evaluation metrics, our network shows better performance than ONet for all the metrics, and it achieved a little better or a compatible score with DISN. For visualization results, we found that our method successfully reconstructs the local details that ONet misses. Also, compare with DISN that fails to reconstruct the thin parts or occluded parts of the object, our progressive occupancy network successfully catches the parts. These results validate the usefulness of the proposed network architecture.