• 한국의학물리학회지:의학물리
• /
• 제31권3호
• /
• pp.111-123
• /
• 2020

Deep learning (DL) is a subset of machine learning and artificial intelligence that has a deep neural network with a structure similar to the human neural system and has been trained using big data. DL narrows the gap between data acquisition and meaningful interpretation without explicit programming. It has so far outperformed most classification and regression methods and can automatically learn data representations for specific tasks. The application areas of DL in radiation oncology include classification, semantic segmentation, object detection, image translation and generation, and image captioning. This article tries to understand what is the potential role of DL and what can be more achieved by utilizing it in radiation oncology. With the advances in DL, various studies contributing to the development of radiation oncology were investigated comprehensively. In this article, the radiation treatment process was divided into six consecutive stages as follows: patient assessment, simulation, target and organs-at-risk segmentation, treatment planning, quality assurance, and beam delivery in terms of workflow. Studies using DL were classified and organized according to each radiation treatment process. State-of-the-art studies were identified, and the clinical utilities of those researches were examined. The DL model could provide faster and more accurate solutions to problems faced by oncologists. While the effect of a data-driven approach on improving the quality of care for cancer patients is evidently clear, implementing these methods will require cultural changes at both the professional and institutional levels. We believe this paper will serve as a guide for both clinicians and medical physicists on issues that need to be addressed in time.

• 복식문화연구
• /
• 제32권2호
• /
• pp.247-259
• /
• 2024

This study assessed the effectiveness of brand image communication on consumer perceptions of cruelty-free fashion brands. Brand messaging data were gathered from postings on the official Instagram accounts of three cruelty-free fashion brands and consumer perception data were gathered from Tweets containing keywords related to each brand. Web crawling and natural language processing were performed using Python and sentiment analysis was conducted using the BERT model. By analyzing Instagram content from Stella McCartney, Patagonia, and Freitag from their inception until 2021, this study found these brands all emphasize environmental aspects but with differing focuses: Stella McCartney on ecological conservation, Patagonia on an active outdoor image, and Freitag on upcycled products. Keyword analysis further indicated consumers perceive these brands in line with their brand messaging: Stella McCartney as high-end and eco-friendly, Patagonia as active and environmentally conscious, and Freitag as centered on recycling. Results based on the assessment of the alignment between brand-driven images and consumer-perceived images and the sentiment evaluation of the brand confirmed the outcomes of brand communication performance. The study revealed a correlation between brand image and positive consumer evaluations, indicating that higher alignment of ethical values leads to more positive consumer assessments. Given that consumers tend to prioritize search keywords over brand concepts, it's important for brands to focus on using visual imagery and promotions to effectively convey brand communication information. These findings highlight the importance of brand communication by emphasizing the connection between ethical brand images and consumer perceptions.

• 지구물리와물리탐사
• /
• 제1권1호
• /
• pp.49-56
• /
• 1998

탄성파토모그래피는 고해상의 자료분석을 필요로 하는 환경이나 토목 등 공학적 응용분야에서 지하구조를 결정하기 위해 널리 사용되는 방법이다. 지금까지의 탄성파토모그래피는 대부분 주시역산에 의존해 왔으나 최근에는 파형정보를 이용하는 역산기법들이 활발히 연구되고 있다. 본 연구에서는 이러한 파형정보를 이용하여 음파 매질에서의 이차원 전파형 역산 알고리듬을 개발하였다. 전파형 역산은 Born역산의 약산란장 가정이나 주시역산의 고 주파수 가정이 필요 없는,분해능이 가장 좋은 방법이다. 그러나 초기추정값이 실제 모델과 많이 다를 경우 국부 최소값에 빠진다는 단점이 있다. 본 연구에서는 주시 역산을 통해 배경값을 추정하고 이를 초기추정 값으로 주어 전 파형 역산을 수행하는 알고리듬을 개발하였다. 본 알고리듬을 인공탄성파자료에 적용한 결과, 주시 역산 결과를 전파형 역산의 초기치로 사용할 경우 오차의 수렴속도가 매우 빠르고 분해능이 뛰어난 영상을 제공함을 확인할 수 있었다. 이는 주시역산을 통한 배경값 추정이 전파형 역산의 국부 최소값 문제와 계산 시간의 문제를 효과적으로 해결할 수 있는 방안임을 시사한다. 또한 축소모형실험자료에 대하여 본 알고리듬을 적용한 결과 재구성된 속도구조가 실제 모형과 잘 일치함을 알 수 있었고, 이를 통하여 현장자료에 대한 적용가능성을 확인하였다.

• 대한토목학회논문집
• /
• 제38권4호
• /
• pp.505-516
• /
• 2018

교량 유지관리 전략 수립 시 현재 상태를 기반으로 미래 상태를 예측할 수 있어야 하며, 상태예측모델의 신뢰도가 높아질수록 효과적인 유지관리 의사결정이 가능하다. 그러나 인력기반 반복 주기적인 현행유지관리는 관리자가 목표하는 관리(등급)수준의 교량 상태를 정확히 예측하지 못해서 막대한 보수 보강비용이 발생될 가능성이 있고, 합리적인 유지관리 의사결정을 도모하는데 어려움을 겪는다. 이에 따라 본 논문에서는 국내 교량 점검 이력 데이터를 이용하여 불확실성을 고려한 교량 부재별 대표 상태예측모델을 개발하고, 개발된 상태예측모델을 실제 유지관리 대상 교량에 보다 높은 정확도로 적용 가능한 베이지안 업데이트 기법을 제안하였다. 또한, 모니터링 업데이트 상태예측모델 기반 예방적 유지관리가 기존 현행유지관리 대비 비용 효율성 측면에서 유리함을 제안하기 위해 각각의 유지관리비용 산출에 따른 교량 점검 타당성 분석을 수행하였다.

• 해양환경안전학회:학술대회논문집
• /
• 해양환경안전학회 2003년도 춘계학술발표회
• /
• pp.191-200
• /
• 2003

Gunsan coastal area is one of region increasing pollution problems. One of the most important factors that cause eutrophication is nutrient materials containing nitrogen and phosphorus which stem from excreation of terrestial sources. At this study, the three-dimensional numerical hydrodynamic and ecosystem model, which was developed by Institute for Resources and Environment of Japan, were applied to analyze the processes affecting the eutrophication. The residual currents, which were obtained by integrating the simulated tidal currents over 1 tidal cycle, showed the presence of a typical. Density driven currents were generated westward at surface and eastward at the bottom in Geum estuary area where the fresh waters are flowing into. The ecosystem model was calibrated with the data surveyed in the field of the study area in annual average. The simulated results of DIN were fairly good coincided with the observed values within relative error of 32.39%. correlation coefficient(r) of 0.99. In the case of DIP, the simulated results were fairly good coincided with the observed values within relative error of 24.26%, correlation coefficient (r) of 0.82. The simulations of DIN and DIP concentrations were performed using ecosystem model under the conditions of 20 ∼ 80% pollution load reductions from pollution sources. In study area, concentration of DIN and DIP were reduced to 20∼80% and under 10% in case of the 80% reduction of the input loads from fresh water respectively. But pollution loads from sediment had hardly affected DIN and DIP concentration. For the environment management of coastal areas, in case of Kunsan area, the most important pollution sources affecting eutrophication phenomenon were found to be the input loads from fresh water.

• 한국정보교육학회:학술대회논문집
• /
• 한국정보교육학회 2011년도 동계학술대회
• /
• pp.211-217
• /
• 2011

소셜 네트워크 서비스의 부각과 다매체 환경에서의 사용자 참여 확대와 같은 최근 IT 기술 환경의 변화로 이러닝 시스템 역시 다양한 환경에서 변화하고 있다. 메타데이터는 시스템 간의 상호운용성을 위한 데이터의 규약이며, 이러닝 메타데이터는 국내외 기판에 의해 표준화가 이루어지고 있으나, 주변 환경의 다양한 변화를 고려하는 메타데이터 요소의 제안이 요구되는 상황이다. 본 논문에서는 지능형 학습 시스템을 위한 메타데이터 모형을 분석 및 설계하는 방법을 연구 제안하고, 표준 메타데이터인 KEM 3.0을 기반으로 향후 필요할 것으로 예상되는 메타데이터 요소의 요구사항을 도출하였다. 도출된 요구사항을 바탕으로 요구사항을 중요도에 따라 분류할 수 있는 카노 모형에 따라 3-Layer 모델로 설계하였다. 향후 본 논문의 모형 설계를 기반으로 이러닝 기술 환경의 변화를 반영한 지능형 학습 시스템을 개발하여 국제적 표준화로 발전되기를 기대한다.

• 한국수소및신에너지학회논문집
• /
• 제24권4호
• /
• pp.295-301
• /
• 2013

Long-term global energy-demand growth is expected to increase driven by strong energy-demand growth from developing countries. Fusion power offers the prospect of an almost inexhaustible source of energy for future generations, even though it also presents so far insurmountable scientific and engineering challenges. One of the challenges is safe handling of hydrogen isotopes. Metal hydrides such as depleted uranium hydride or ZrCo hydride are used as a storage medium for hydrogen isotopes reversibly. The metal hydrides bind with hydrogen very strongly. In this paper, we carried out a modeling and simulation work for absorption/desorption of hydrogen by ZrCo in a horizontal annulus cylinder bed. A comprehensive mathematical description of a metal hydride hydrogen storage vessel was developed. This model was calibrated against experimental data obtained from our experimental system containing ZrCo metal hydride. The model was capable of predicting the performance of the bed for not only both the storage and delivery processes but also heat transfer operations. This model should thus be very useful for the design and development of the next generation of metal hydride hydrogen isotope storage systems.

• Asian Pacific Journal of Cancer Prevention
• /
• 제16권13호
• /
• pp.5377-5383
• /
• 2015

Background: Participation is one of the major factors affecting the long-term success of population-based prostate cancer screening programs. The aim of this study was to explore strong factors linked to participation in prostate cancer screening among older Jordanian adults using the Health Belief Model (HBM). Materials and Methods: Data were obtained from Jordanian older adults, aged 40 years and over, who visited a comprehensive health care center within the Ministry of Health. A pilot test was conducted to investigate the internal consistency of the the Champion Health Belief Model Scale for prostate cancer screening and the clarity of survey questions. Sample characteristics and rates of participation in prostate cancer screening were examined using means and frequencies. Important factors associated with participation in prostate cancer screening were examined using bivariate correlation and multivariate logistic regression analysis. Results: About 13% of the respondents had adhered to prostate cancer screening guidelines over the previous decade. Four out of the seven HBM-driven factors (perceived susceptibility, benefits and barriers to PSA test, and health motivation) were statistically significant. Those with greater levels of susceptibility, benefits of PSA test and health motivation and lower levels of barriers to PSA testing were more likely to participate in prostate cancer screening. Family history, presence of urinary symptoms, age, and knowledge about prostate cancer significantly predicted the participation in prostate cancer screening. Conclusions: Health professionals should focus more on the four modifiable HBMrelated factors to encourage older adults to participate in prostate cancer screening. Intervention programs, which lower perceived barriers to PSA testing and increase susceptibility, benefits of PSA testing and health motivation, should be developed and implemented.

• 시스템엔지니어링학술지
• /
• 제18권2호
• /
• pp.75-93
• /
• 2022

Machine learning (ML) data-driven meta-model is proposed as a surrogate model to reduce the excessive computational cost of the physics-based model and facilitate the real-time prediction of a nuclear power plant's transient response. To forecast the transient response three machine learning (ML) meta-models based on recurrent neural networks (RNNs); specifically, Long Short Term Memory (LSTM), Gated Recurrent Unit (GRU), and a sequence combination of Convolutional Neural Network (CNN) and LSTM are developed. The chosen accident scenario is a control element assembly withdrawal at power concurrent with the Loss Of Offsite Power (LOOP). The transient response was obtained using the best estimate thermal hydraulics code, MARS-KS, and cross-validated against the Design and control document (DCD). DAKOTA software is loosely coupled with MARS-KS code via a python interface to perform the Best Estimate Plus Uncertainty Quantification (BEPU) analysis and generate a time series database of the system response to train, test and validate the ML meta-models. Key uncertain parameters identified as required by the CASU methodology were propagated using the non-parametric Monte-Carlo (MC) random propagation and Latin Hypercube Sampling technique until a statistically significant database (181 samples) as required by Wilk's fifth order is achieved with 95% probability and 95% confidence level. The three ML RNN models were built and optimized with the help of the Talos tool and demonstrated excellent performance in forecasting the most probable NPP transient response. This research was guided by the Systems Engineering (SE) approach for the systematic and efficient planning and execution of the research.

• 천문학논총
• /
• 제39권1호
• /
• pp.1-12
• /
• 2024

In this study, we investigated the time signal devices of Deungnu (circa 1270) and Gungnu (1354), the water clocks produced during the Yuan Dynasty (1271-1368). These clocks influenced Heumgyeonggaknu (1438) of the Joseon Dynasty (1392-1910), exemplifying the automatic water clocks of the Yuan Dynasty. Deungnu, Gungnu, and Heumgyeonggaknu can be considered as automatic mechanical clocks capable of performances. The Jega-Yeoksang-Jip (Collection of Calendrical and Astronomical Theories of Various Chinese Masters) contains records of Deungnu extracted from the History of the Yuan Dynasty. We interpreted these records and analyzed reproduction models and technical data previously produced in China. The time signal device of Deungnu featured a four-story structure, with the top floor displaying the four divine constellations, the third floor showcasing models of these divinities, the second floor holding 12-h jacks and a 100-Mark ring, and the first floor with four musicians and a 100-Mark Time-Signal Puppet providing a variety of visual attractions. We developed a 3D model of Deungnu, proposing two possible mechanical devices to ensure that the Time-Signal Puppet simultaneously pointed to the 100-Mark graduations in the east, west, south, and north windows: one model reduced the rotation ratio of the 100-Mark ring to 1/4, whereas the other model maintained the rotation ratio using four separate 100-Mark rings. The power system of Deungnu was influenced by Suunuisangdae (the water-driven astronomical clock tower) of the Northern Song Dynasty (960-1127); this method was also applied to Heumgyeonggaknu in the Joseon Dynasty. In conclusion, these automatic water clocks of East Asia from the 13th to 15th centuries symbolized creativity and excellence, representing scientific devices that were the epitome of clock-making technology in their times.