Comparison of Robotic Versus Laparoscopic Cyst Excision and Hepaticojejunostomy for Choledochal Cyst in Children

Eunhae Cho,Jung Man Namgoong,DaeYeon Kim,SeongChul Kim,Hyunhee Kwon,YuJung Cho 대한외과학회 2018 대한외과학회 학술대회 초록집 Vol.2018 No.11

공연예술에서 광고포스터의 이미지 특성을 활용한 딥러닝 기반 관객예측

조유정(Yujung Cho),강경표(Kyungpyo Kang),권오병(Ohbyung Kwon) 한국전자거래학회 2021 한국전자거래학회지 Vol.26 No.2

공연예술 기관에서의 공연에 대한 흥행 예측은 공연예술 산업 및 기관에서 매우 흥미롭고도 중요한 문제이다. 이를 위해 출연진, 공연장소, 가격 등 정형화된 데이터를 활용한 전통적인 예측방법론, 데이터마이닝 방법론이 제시되어 왔다. 그런데 관객들은 공연안내 포스터에 의하여 관람 의도가 소구되는 경향이 있음에도 불구하고, 포스터 이미지 분석을 통한 흥행 예측은 거의 시도되지 않았다. 그러나 최근 이미지를 통해 판별하는 CNN 계열의 딥러닝 방법이 개발되면서 포스터 분석의 가능성이 열렸다. 이에 본 연구의 목적은 공연 관련 포스터 이미지를 통해 흥행을 예측할 수 있는 딥러닝 방법을 제안하는 것이다. 이를 위해 KOPIS 공연예술 통합전산망에 공개된 포스터 이미지를 학습데이터로 하여 Pure CNN, VGG-16, Inception-v3, ResNet50 등 딥러닝 알고리즘을 통해 예측을 수행하였다. 또한 공연 관련 정형데이터를 활용한 전통적 회귀분석 방법론과의 앙상블을 시도하였다. 그 결과 흥행 예측 정확도 85%를 상회하는 높은 판별 성과를 보였다. 본 연구는 공연예술 분야에서 이미지 정보를 활용하여 흥행을 예측하는 첫 시도이며 본 연구에서 제안한 방법은 연극 외에 영화, 기관 홍보, 기업 제품 광고 등 포스터 기반의 광고를 하는 영역으로도 적용이 가능할 것이다. The prediction of box office performance in performing arts institutions is an important issue in the performing arts industry and institutions. For this, traditional prediction methodology and data mining methodology using standardized data such as cast members, performance venues, and ticket prices have been proposed. However, although it is evident that audiences tend to seek out their intentions by the performance guide poster, few attempts were made to predict box office performance by analyzing poster images. Hence, the purpose of this study is to propose a deep learning application method that can predict box office success through performance-related poster images. Prediction was performed using deep learning algorithms such as Pure CNN, VGG-16, Inception-v3, and ResNet50 using poster images published on the KOPIS as learning data set. In addition, an ensemble with traditional regression analysis methodology was also attempted. As a result, it showed high discrimination performance exceeding 85% of box office prediction accuracy. This study is the first attempt to predict box office success using image data in the performing arts field, and the method proposed in this study can be applied to the areas of poster-based advertisements such as institutional promotions and corporate product advertisements.

동계 스포츠 속 과학기술 : 유니폼 및 장비에 관하여

조유정(Cho, Yujung),구영석(Koo, Youngseok) 한국생활과학회 2020 한국생활과학회 학술대회 Vol.2020 No.11

인공지능의 사회적 수용도에 따른 키워드 검색량 기반 주가예측모형 비교연구

조유정(Yujung Cho),손권상(Kwonsang Sohn),권오병(Ohbyung Kwon) 한국지능정보시스템학회 2021 지능정보연구 Vol.27 No.1

Recently, investors interest and the influence of stock-related information dissemination are being considered as significant factors that explain stock returns and volume. Besides, companies that develop, distribute, or utilize innovative new technologies such as artificial intelligence have a problem that it is difficult to accurately predict a companys future stock returns and volatility due to macro-environment and market uncertainty. Market uncertainty is recognized as an obstacle to the activation and spread of artificial intelligence technology, so research is needed to mitigate this. Hence, the purpose of this study is to propose a machine learning model that predicts the volatility of a companys stock price by using the internet search volume of artificial intelligence-related technology keywords as a measure of the interest of investors. To this end, for predicting the stock market, we using the VAR(Vector Auto Regression) and deep neural network LSTM (Long Short-Term Memory). And the stock price prediction performance using keyword search volume is compared according to the technologys social acceptance stage. In addition, we also conduct the analysis of sub-technology of artificial intelligence technology to examine the change in the search volume of detailed technology keywords according to the technology acceptance stage and the effect of interest in specific technology on the stock market forecast. To this end, in this study, the words artificial intelligence, deep learning, machine learning were selected as keywords. Next, we investigated how many keywords each week appeared in online documents for five years from January 1, 2015, to December 31, 2019. The stock price and transaction volume data of KOSDAQ listed companies were also collected and used for analysis. As a result, we found that the keyword search volume for artificial intelligence technology increased as the social acceptance of artificial intelligence technology increased. In particular, starting from AlphaGo Shock, the keyword search volume for artificial intelligence itself and detailed technologies such as machine learning and deep learning appeared to increase. Also, the keyword search volume for artificial intelligence technology increases as the social acceptance stage progresses. It showed high accuracy, and it was confirmed that the acceptance stages showing the best prediction performance were different for each keyword. As a result of stock price prediction based on keyword search volume for each social acceptance stage of artificial intelligence technologies classified in this study, the awareness stages prediction accuracy was found to be the highest. The prediction accuracy was different according to the keywords used in the stock price prediction model for each social acceptance stage. Therefore, when constructing a stock price prediction model using technology keywords, it is necessary to consider social acceptance of the technology and sub-technology classification. The results of this study provide the following implications. First, to predict the return on investment for companies based on innovative technology, it is most important to capture the recognition stage in which public interest rapidly increases in social acceptance of the technology. Second, the change in keyword search volume and the accuracy of the prediction model varies according to the social acceptance of technology should be considered in developing a Decision Support System for investment such as the big data-based Robo-advisor recently introduced by the financial sector.

Columnar variant of papillary carcinoma in the thyroglossal duct cyst with progression to lung metastasis

Yujung Yun,Hye Jung Park,Young Ki Lee,Yongin Cho,Beoduel Kang,Hyun Ju Kim,Jung-Hee Lee,Moo-Nyun Jin,Dong Yeob Shin 영남대학교 의과대학 2014 Yeungnam University Journal of Medicine Vol.31 No.2

Thyroglossal duct cyst (TGDC) carcinoma generally shows a favorable prognosis. If metastasis is present latently, it may not threaten the patient’s life immediately. It has been shown, however, that larger than 1 cm papillary carcinoma (PC), level VI metastasis to the lymph node (LN), which is the nearest to the thyroid, independently predicts a worse prognosis. In the case presented herein, a 61-year-old female patient was diagnosed with an about 3 cm PC in the TGDC, particularly the columnar variant subtype, one of the aggressive variants. She had occult papillary thyroid microcarcinoma, but no LN metastasis. Even though she underwent the Sistrunk procedure and total thyroidectomy with central compartment neck dissection followed by high-dose radioactive iodine remnant ablation, however, the cancer cells spread to level IV neck LN, and finally to the lung. Therefore, when a patient is diagnosed with an aggressive histologic variant of PC in the TGDC, even without LN metastasis, the invasive surgical approach and close postoperative surveillance are necessary, with consideration of the risk of disease progression. Therefore, if it is possible to stratify the risk for patients, higher-risk patients can be offered a more invasive therapeutic approach.

Columnar variant of papillary carcinoma in the thyroglossal duct cyst with progression to lung metastasis

Yun, Yujung,Park, Hye Jung,Lee, Young Ki,Cho, Yongin,Kang, Beoduel,Kim, Hyun Ju,Lee, Jung-Hee,Jin, Moo-Nyun,Shin, Dong Yeob Yeungnam University College of Medicine 2014 Yeungnam University Journal of Medicine Vol.31 No.2

Thyroglossal duct cyst (TGDC) carcinoma generally shows a favorable prognosis. If metastasis is present latently, it may not threaten the patient's life immediately. It has been shown, however, that larger than 1 cm papillary carcinoma (PC), level VI metastasis to the lymph node (LN), which is the nearest to the thyroid, independently predicts a worse prognosis. In the case presented herein, a 61-year-old female patient was diagnosed with an about 3 cm PC in the TGDC, particularly the columnar variant subtype, one of the aggressive variants. She had occult papillary thyroid microcarcinoma, but no LN metastasis. Even though she underwent the Sistrunk procedure and total thyroidectomy with central compartment neck dissection followed by high-dose radioactive iodine remnant ablation, however, the cancer cells spread to level IV neck LN, and finally to the lung. Therefore, when a patient is diagnosed with an aggressive histologic variant of PC in the TGDC, even without LN metastasis, the invasive surgical approach and close postoperative surveillance are necessary, with consideration of the risk of disease progression. Therefore, if it is possible to stratify the risk for patients, higher-risk patients can be offered a more invasive therapeutic approach.

SIP P2P 스팸 방지를 위한 인증 및 SDP 암호화 키 교환 기법

장유정(Yujung Jang),정수환(Souhwan Jung),최재식(Jaesic Choi),최재덕(Jaeduck Choi),원유재(Yoojae Won),조영덕(Youngduk Cho) 한국통신학회 2007 韓國通信學會論文誌 Vol.32 No.12B

본 논문에서는 SIP 기반의 VoIP 망에서 발생할 수 있는 스팸 위협에 대해 분석하고 이를 차단하기 위해 UA와 프락시 서버 간에 인증 및 SDP를 암호화할 수 있는 키 교환 기법을 제안한다. 기존 HTTP 다이제스트 인증은호 설정 시 마다 사용자 인증을 위해 매 번 challenge 값을 전송해야 하므로 많은 메시지 교환 과정이 요구되고 SDP에 대한 기밀성도 제공하지 않는다. 제안 기법은 본 논문에서 분석한 스팸 위협을 차단하기 위해 등록 과정에서 세션 마스터 키 및 초기 nonce를 교환하고 이 키를 인증 키 및 암호화 키로 유도해 사용하므로 호 설정 시 challenge 값 전송에 따른 메시지 교환 과정과 S/MIME 또는 TLS 적용 시 발생하는 오버헤드를 줄일 수 있다. This paper analyzes spam threats and proposes key exchange scheme for user authentication and SDP encryption to protect potential spam threats in SIP-based VoIP services. The existing HTTP digest authentication scheme exchanges many message because challenge is sent for every establishment of the session and doesn't provide a confidentiality of SDP. To protect SPIT, our scheme exchanges initial nonce and a session master key for authentication and SDP encryption during registration. In our scheme, the challenge and response procedure is not necessary and the communication overhead is much less than applying S/MIME or TLS.

Direct conversion of fibroblasts to osteoblasts as a novel strategy for bone regeneration in elderly individuals

Chang, Yujung,Cho, Byounggook,Kim, Siyoung,Kim, Jongpil Nature Publishing Group UK 2019 Experimental and molecular medicine Vol.51 No.5

<▼1><P>Mortality caused by age-related bone fractures or osteoporosis is steadily increasing worldwide as the population ages. The pace of the development of bone regeneration engineering to treat bone fractures has consequently increased in recent years. A range of techniques for bone regeneration, such as immunotherapy, allografts, and hydrogel therapy, have been devised. Cell-based therapies using bone marrow-derived mesenchymal stem cells and induced pluripotent stem cells derived from somatic cells are considered to be suitable approaches for bone repair. However, these cell-based therapies suffer from a number of limitations in terms of efficiency and safety. Somatic cells can also be directly differentiated into osteoblasts by several transcription factors. As osteoblasts play a central role in the process of bone formation, the direct reprogramming of fibroblasts into osteoblasts may hence be a new way to treat bone fractures in elderly individuals. Here, we review recent developments regarding the therapeutic potential of the direct reprogramming of cells for bone regeneration.</P></▼1><▼2><P><B>Fractures: reprogramming cells to reduce risk in the elderly</B></P><P>Reprogramming cells that produce connective tissue to form bone instead could help prevent fractures in the elderly. Bones weaken with age, and fractures are a significant health risk in ageing populations. Most current bone regeneration treatments use stem cells, which can differentiate into any type of cell and have infinite capacity to divide; however, they are difficult to source and can lead to tumor formation. Jongpil Kim at Dongguk University in South Korea and coworkers have reviewed a new method that uses genetic signals to transform connective tissue-forming cells into bone-producing cells. The reprogrammed cells have been shown to generate new bone at the desired site, and because they have already lost their capacity for infinite division, tumor formation risk is greatly reduced. This method shows promise to expand treatment options for fractures and osteoporosis.</P></▼2>

Growth patterns over 2 years after birth according to birth weight and length percentiles in children born preterm

Kim Seulki,Choi Yujung,Lee Seonhwa,Ahn Moon Bae,Kim Shin Hee,Cho Won Kyung,Cho Kyung Soon,Jung Min Ho,Suh Byung Kyu 대한소아내분비학회 2020 Annals of Pediatirc Endocrinology & Metabolism Vol.25 No.3

Purpose: To analyze growth patterns over 2 years after birth according to preterm infant birth weight and length percentiles. Methods: Anthropometric measurements of 82 preterm infants were retrospectively reviewed. Preterm infants with birth weight or length below the 10th percentile were classified as small for gestational age (SGA) (n=19) and those between the 10th and 89th percentile as appropriate for gestational age (AGA) (n=63). The association between the length standard deviation score (SDS) at 2 years of corrected age and clinical factors were analyzed. Results: The length SDS of the SGA group was significantly increased at 6 months (-1.30±1.71) and 24 months (-0.97±1.06) of corrected age. The length SDS was lower in the SGA group than those in the AGA group at 6 months (-1.30±1.71 vs. -0.25±1.15, P=0.004), 18 months (-0.97±1.39 vs. -0.03±1.29, P=0.015), and 24 months (-0.97±1.06 vs. -0.29±1.12, P=0.022,). The percentage of children with a length SDS of <-2 (growth failure) at 24 months was 15.8% in the SGA group and 4.8% in the AGA group (P=0.108). Multiple linear regression analysis demonstrated that length at 24 months of corrected age was negatively correlated with birth length below the 10th percentile (coefficient β=-0.91, P=0.001) and duration of stay in the neonatal intensive care unit (NICU) (coefficient β=-0.01, P=0.001). Conclusion: Despite the fact that catch-up growth occurs during the early period of infancy in a large portion of preterm SGA infants, a significant portion of these infants show growth failure at 24 months of age. Growth over 2 years after birth is affected by birth length and duration of stay in the NICU in preterm children.

ASAM XIL 기반 Test Automation Tool을 이용한 HILs 평가환경 확장 사례

김용회(Yonghoe Kim),조유정(Yujung Cho),김범섭(Beomseop Kim) 한국자동차공학회 2023 한국자동차공학회 학술대회 및 전시회 Vol.2023 No.11

This study explores how ASAM XIL-based Test Automation can improve the quality of automakers. We will explain the basic concept and structure of ASAM XIL and demonstrate the integration of Test Automation solutions such as National Instruments (NI) and Vector using the Test Automation Tool based on the ASAM XIL standard called X-Studio. This covers how to improve the scalavility of test cases, as well as the flexibility of automation validation and evaluation environment deployment.