• Current Optics and Photonics
• /
• 제7권3호
• /
• pp.237-247
• /
• 2023

In middle- and long-distance imaging systems, due to the atmospheric turbulence caused by temperature, wind speed, humidity, and so on, light waves propagating in the air are distorted, resulting in image-quality degradation such as geometric deformation and fuzziness. In remote sensing, astronomical observation, and traffic monitoring, image information loss due to degradation causes huge losses, so effective restoration of degraded images is very important. To restore images degraded by atmospheric turbulence, an image-restoration method based on improved compound multibranch feature fusion (CMFNetPro) was proposed. Based on the CMFNet network, an efficient channel-attention mechanism was used to replace the channel-attention mechanism to improve image quality and network efficiency. In the experiment, two-dimensional random distortion vector fields were used to construct two turbulent datasets with different degrees of distortion, based on the Google Landmarks Dataset v2 dataset. The experimental results showed that compared to the CMFNet, DeblurGAN-v2, and MIMO-UNet models, the proposed CMFNetPro network achieves better performance in both quality and training cost of turbulent-image restoration. In the mixed training, CMFNetPro was 1.2391 dB (weak turbulence), 0.8602 dB (strong turbulence) respectively higher in terms of peak signal-to-noise ratio and 0.0015 (weak turbulence), 0.0136 (strong turbulence) respectively higher in terms of structure similarity compared to CMFNet. CMFNetPro was 14.4 hours faster compared to the CMFNet. This provides a feasible scheme for turbulent-image restoration based on deep learning.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2023년도 학술발표회
• /
• pp.2-2
• /
• 2023

기후변화가 가속화로 인해 수재해의 빈도와 강도 예측이 어려워짐에 따라 실시간 홍수 모니터링에 대한 수요가 증가하고 있다. 합성개구레이다는 광원과 날씨에 무관하게 촬영이 가능하여 수재해 발생시에도 영상을 확보할 수 있다. 합성개구레이다를 활용한 수체 탐지 알고리즘 개발이 활발히 연구되어 왔고, 딥러닝의 발달로 CNN을 활용하여 높은 정확도로 수체 탐지가 기능해졌다. 하지만, CNN 기반 수체 탐지 모델은 훈련시 높은 정량적 정확성 지표를 달성하여도 추론 후 정성적 평가시 경계와 소하천에 대한 탐지 정확성이 떨어진다. 홍수 모니터링에서 특히 중요한 정보인 경계와 좁은 하천에 대해서 정확성이 떨어짐에 따라 실생활 적용이 어렵다. 이에 경계를 강화한 적대적 학습 기반의 수체 탐지 모델을 개발하여 더 세밀하고 정확하게 탐지하고자 한다. 적대적 학습은 생성적 적대 신경망(GAN)의 두 개의 모델인 생성자와 판별자가 서로 관여하며 더 높은 정확도를 달성할 수 있도록 학습이다. 이러한 적대적 학습 개념을 수체 탐지 모델에 처음으로 도입하여, 생성자는 실제 라벨 데이터와 유사하게 수체 경계와 소하천까지 탐지하고자 학습한다. 반면 판별자는 경계 거리 변환 맵과 합성개구레이다 영상을 기반으로 라벨데이터와 수체 탐지 결과를 구분한다. 경계가 강화될 수 있도록, 면적과 경계를 모두 고려할 수 있는 손실함수 조합을 구성하였다. 제안 모델이 경계와 소하천을 정확히 탐지하는지 판단하기 위해, 정량적 지표로 F1-score를 사용하였으며, 육안 판독을 통해 정성적 평가도 진행하였다. 기존 U-Net 모델이 탐지하지 못하던 영역에 대해 제안한 경계 강화 적대적 수체 탐지 모델이 수체의 세밀한 부분까지 탐지할 수 있음을 증명하였다.

• 대한한방부인과학회지
• /
• 제36권3호
• /
• pp.78-94
• /
• 2023

Objectives: The purpose of this study is to review the trends of clinical trials of traditional herbal medicine Gyejibongnyeong-hwan for chronic pelvic inflammatory disease in CNKI. Methods: We searched relevant studies using Chinese National Knowledge Infrastructure (CNKI). Data retrieval was carried out by December 20^th, 2021. We analyzed characteristics of study subjects, treatment period, composition of prescription, outcome and adverse event of selected studies and the risk of bias was assessed by using Cochrane's risk of bias tool. Results: Among the total 988 studies, 10 studies met the inclusion criteria. All of the studies were randomized controlled studies and written in Chinese. In all studies, Gyejibongnyeong-hwan was effective in improving chronic pelvic inflammatory disease. Conclusions: This study suggests that Gyejibongnyeong-hwan can be effective in treating chronic pelvic inflammatory disease compared to antibiotics treatment. Further large and well-established randomized placebo controlled trials will be needed.

• Nutrition Research and Practice
• /
• 제17권2호
• /
• pp.269-283
• /
• 2023

BACKGROUND/OBJECTIVES: This study aimed to examine the food security status of urban poor adolescents and its association with diet quality. SUBJECTS/METHODS: A cross-sectional survey was conducted among 188 adolescents aged 13-18 yrs living in Kuala Lumpur, Malaysia. Household food insecurity and dietary intake data were collected using the Radimer/Cornell hunger and food insecurity instrument and 2-day 24-h dietary recalls, respectively. Diet quality was determined using the Malaysian Healthy Eating Index (HEI). Weight and height were measured and body mass index-for-age, as well as height-for-age z scores were calculated. RESULTS: The present study revealed that 47.9% of the adolescents experienced household food insecurity, 24.5% experienced individual food insecurity, 18.6% household food security, and 9.0% child hunger. The mean score of diet quality was 56.83 ± 10.09, with a significantly lower HEI score among food insecure adolescents (household food insecure, individual food insecure, and child hunger) than household food secure adolescents (P = 0.001). The differences between food secure and food insecure households were found to be significant for energy (P = 0.001) and nutrients including proteins (P = 0.006), carbohydrates (P = 0.005), dietary fiber (P = 0.001), folate (P < 0.001), and vitamin C (P = 0.006). The multiple linear regression showed that adolescents who experienced food insecurity (β = -0.328; P = 0.003) were found to be significantly associated with poor diet quality (F = 2.726; P < 0.01), wherein 13.3% of the variation in the diet quality was explained by the food security status. CONCLUSIONS: Experiencing food insecurity contributed to poor diet quality among urban poor adolescents. Further longitudinal studies are needed to comprehensively understand this association to improve food insecurity and diet quality among urban poor communities.

• Geomechanics and Engineering
• /
• 제32권3호
• /
• pp.347-359
• /
• 2023

With the development of infrastructure, there is a critical shortage of filling materials all over the word. However, a large amount of silt accumulated in the lower reaches of the Yellow River is treated as waste every year, which will cause environmental pollution and waste of resources. Microbial induced calcium carbonate precipitation (MICP) technology, with the advantage of efficient, economical and environmentally friendly protection, is selected to solidify the abandoned Yellow River silt with poor mechanical properties into high-quality filling material in this paper. Based on unconfined compressive strength (UCS) test, determination of calcium carbonate (CaCO₃) content and scanning electron microscope (SEM) test, the effects of cementation solution concentration, treatment times and relative density on the solidification effect were studied. The results show that the loose silt particles can be effectively solidified together into filling material with excellent mechanical properties through MICP technology. The concentration of cementation solution have a significant impact on the solidification effect, and the reasonable concentration of cementation solution is 1.5 mol/L. With the increase of treatment times, the pores in the soil are filled with CaCO₃, and the UCS of the specimens after 10 times of treatment can reach 2.5 MPa with a relatively high CaCO₃ content of 26%. With the improvement of treatment degree, the influence of relative density on the UCS increases gradually. Microscopic analysis revealed that after MICP reinforcement, CaCO₃ adhered to the surface of soil particles and cemented with each other to form a dense structure.

• 한국환경보건학회지
• /
• 제49권1호
• /
• pp.30-36
• /
• 2023

Background: Among various pollutants, fine particle (PM_2.5, defined as particle less than 2.5 nm in aerodynamic diameter) shows the most consistent association with adverse health effects. There is scientific evidence documenting a variety of adverse health outcomes due to exposure to PM_2.5. Objectives: This study aims to assess the health benefits of that would be achieved by meeting the World Health Organization's air quality guidelines for PM_2.5 using AirQ+ and BenMAP. Methods: We estimated PM_2.5 related health benefits in Korea from implementing the World Health Organization's air quality guidelines (annual average 5 ㎍/m³ and 10 ㎍/m³) and Korea's National Ambient Air Quality Standard (annual average 15 ㎍/m³). We used World Health Organization's AirQ+ and U.S. Environmental Protection Agency's Environmental Benefits Mapping and Analysis Program. Results: The annual number of avoided PM_2.5 related premature deaths exceeding WHO guideline levels was assessed using both AirQ+ and BenMAP. We estimated that the health benefits of attaining the World Health Organization's air quality guidelines for PM_2.5 (annual average 5 ㎍/m³) would suggest an annual reduction of 26,128 (95% confidence interval [CI]: 17,363~34,024) and 26,853 (95% CI: 18,527~34,944) premature deaths. Conclusions: Our study provided useful information to policy makers and confirms that the reduction of PM_2.5 concentration would result in significant health benefits in Korea.

• 융합신호처리학회논문지
• /
• 제23권3호
• /
• pp.173-178
• /
• 2022

최근 인공지능, 빅데이터, IoT 등의 다양한 컴퓨팅 기술이 발달하고 있다. 특히 콘텐츠 및 의료 산업 등 여러 분야에서 인공지능 기반의 딥페이크(Deepfake) 기술이 다양하게 활용되고 있다. 딥페이크 기술이란 딥러닝과 fake의 합성어로, AI의 핵심기술인 딥러닝을 통해 사람의 얼굴이나 신체를 합성하여 억양, 목소리 등을 따라 하게 만드는 기술이다. 본 논문은 딥페이크 기술을 활용하여 애니메이션 모델과 실제 인물사진의 합성을 통한 가상 캐릭터생성을 연구한다. 이를 통해 애니메이션 제작과정에서 일어나는 여러 가지 비용 손실을 최소화하고 작가들의 작업을 지원할 수 있다. 또한, 딥페이크 오픈소스가 인터넷에 퍼짐에 따라 많은 문제들이 나타나면서 딥페이크 기술을 악용한 범죄가 성행하고 있다. 본 연구를 통해서 딥페이크 기술을 성인물이 아닌 아동물에 적용하여 이 기술에 대한 새로운 관점을 제시한다.

• Journal of Korean Neurosurgical Society
• /
• 제65권3호
• /
• pp.430-438
• /
• 2022

Objective : Dermoid cysts are uncommon in spinal cord tumors, and the phenomenon of their spontaneous rupture into the syrinx cavity is quite rare. We aimed to analyze the imaging characteristics and etiologies, and propose some surgical strategies, for this uncommon phenomenon. Methods : We retrospectively reviewed 14 cases with spinal dermoid cysts that ruptured into the cervical and thoracic syrinx cavity. There were six male and eight female cases, aged 21 to 46 years, who had lipid droplets in the syrinx cavity from C1 to L3. The dermoid cysts were always located at the conus. Based on patients' complaints, clinical manifestations, and imaging results, we adopted tumor excision and/or syrinx cavity aspiration in one stage or multiple stages. Results : Three patients had only a syrinx cavity aspiration surgery due to a history of dermoid cyst excision. Eight patients had dermoid cyst resection and syrinx cavity aspiration in one stage. One patient was operated upon in two stages due to the development of new symptoms at nine months follow-up. Two patients underwent only tumor resection since they did not show similar symptoms or signs caused by the cervicothoracic syrinx. The axial magnetic resonance imaging indicated that the lipid droplets were always not at the center but were eccentric. The clinical effect was satisfactory during the follow-up period in this group. Conclusion : The lipid droplets filled the spinal syrinx cavity, not entirely confined to the central canal. Based on the chief complaints and associated signs, we adopted different surgical strategies and had satisfactory clinical results.

• Wind and Structures
• /
• 제34권2호
• /
• pp.231-257
• /
• 2022

Transmission lines systems are important components of the electrical power infrastructure. However, these systems are vulnerable to damage from high wind events such as hurricanes. This study presents the results from a 1:50 scale aeroelastic model of a multi-span transmission lines system subjected to simulated hurricane winds. The transmission lines system considered in this study consists of three lattice towers, four spans of conductors and two end-frames. The aeroelastic tests were conducted at the NSF NHERI Wall of Wind Experimental Facility (WOW EF) at the Florida International University (FIU). A horizontal distortion scaling technique was used in order to fit the entire model on the WOW turntable. The system was tested at various wind speeds ranging from 35 m/s to 78 m/s (equivalent full-scale speeds) for varying wind directions. A system identification (SID) technique was used to evaluate experimental-based along-wind aerodynamic damping coefficients and compare with their theoretical counterparts. Comparisons were done for two aeroelastic models: (i) a self-supported lattice tower, and (ii) a multi-span transmission lines system. A buffeting analysis was conducted to estimate the response of the conductors and compare it to measured experimental values. The responses of the single lattice tower and the multi-span transmission lines system were compared. The coupling effects seem to drastically change the aerodynamic damping of the system, compared to the single lattice tower case. The estimation of the drag forces on the conductors are in good agreement with their experimental counterparts. The incorporation of the change in turbulence intensity along the height of the towers appears to better estimate the response of the transmission tower, in comparison with previous methods which assumed constant turbulence intensity. Dynamic amplification factors and gust effect factors were computed, and comparisons were made with code specific values. The resonance contribution is shown to reach a maximum of 18% and 30% of the peak response of the stand-alone tower and entire system, respectively.

• 천문학회보
• /
• 제46권1호
• /
• pp.41.2-41.2
• /
• 2021

In this study, we generate He I 1083 nm images from Solar Dynamic Observatory (SDO)/Atmospheric Imaging Assembly (AIA) images using a novel deep learning method (pix2pixHD) based on conditional Generative Adversarial Networks (cGAN). He I 1083 nm images from National Solar Observatory (NSO)/Synoptic Optical Long-term Investigations of the Sun (SOLIS) are used as target data. We make three models: single input SDO/AIA 19.3 nm image for Model I, single input 30.4 nm image for Model II, and double input (19.3 and 30.4 nm) images for Model III. We use data from 2010 October to 2015 July except for June and December for training and the remaining one for test. Major results of our study are as follows. First, the models successfully generate He I 1083 nm images with high correlations. Second, the model with two input images shows better results than those with one input image in terms of metrics such as correlation coefficient (CC) and root mean squared error (RMSE). CC and RMSE between real and AI-generated ones for the model III with 4 by 4 binnings are 0.84 and 11.80, respectively. Third, AI-generated images show well observational features such as active regions, filaments, and coronal holes. This work is meaningful in that our model can produce He I 1083 nm images with higher cadence without data gaps, which would be useful for studying the time evolution of chromosphere and coronal holes.