http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Lee, Chang Kyu,Lee, Na Eun,Hong, Samin,Kang, Eunmin,Rho, Seung Soo,Seong, Gong Je,Hong, Young Jae,Kim, Chan Yun Wolters Kluwer Health, Inc. All rights reserved. 2016 Journal of glaucoma Vol.25 No.4
<P>Purpose: To evaluate clinical risk factors of disease progression after cataract surgery using phacoemulsification with posterior chamber intraocular lens implantation, in eyes with chronic angle-closure glaucoma (CACG) and coexisting cataract. Design: Retrospective study. Methods: The data of 56 eyes of 45 CACG patients who had undergone uncomplicated phacoemulsification with posterior chamber intraocular lens implantation were retrospectively analyzed. Disease progression was defined as glaucomatous optic nerve change or visual field (VF) deterioration according to the European Glaucoma Society guideline. Correlations between VF progression and various preoperative and postoperative factors were determined by chi(2) and independent t tests. Linear regression analysis [(odds ratio (OR)] was used to determine predictive risk factors for disease progression using univariate and multivariate analyses. Results: The mean postoperative follow-up period was 45.13 +/- 17.54 (24 to 84) months. Fourteen eyes (25%) with cataracts diagnosed with CACG progressed after phacoemulsification, but the remaining 42 eyes (75%) did not. According to univariate analysis, disease progression was significantly associated with older age, more number of preoperative/postoperative antiglaucoma drugs, higher scores of preoperative pattern standard deviation, and lower scores of preoperative and postoperative visual field index (VFI) (P < 0.05). Using multivariate analysis, a lower score of preoperative VFI (OR: 0.86, P = 0.044) and lower postoperative intraocular pressure (IOP) reduction, which was not sustained below 20% less than the preoperative mean IOP, were significantly correlated with disease progression after cataract surgery (OR: 8.44, P = 0.048). Conclusions: CACG patients with low preoperative VFI and high postoperative IOP are at risk for disease progression even after uncomplicated cataract surgery.</P>
Support Vector Machine을 이용한 암호화된 신용평가 모델 학습
이은민(Eunmin Lee),이주희(Joohee Lee) 한국정보통신학회 2023 한국정보통신학회 종합학술대회 논문집 Vol.27 No.1
최근 빅데이터를 다루기 위한 기계학습과 클라우드 컴퓨팅 기술이 발전함에 따라 개인정보를 보호하는 기계학습(Privacy-Preserving Machine Learning)이 화두가 되고 있다. 동형암호는 암호화된 상태에서 데이터의 연산이 가능하며, 양자컴퓨터를 이용한 공격에도 안전한 차세대 암호 기술이다. 본 연구에서는 개인정보보호를 위한 동형암호화된 기계학습 시나리오 중, 금융 데이터를 바탕으로 채무 불이행 확률을 예측하고 대출 여부를 결정하기 위한 신용평가 모델을 학습하는 방법을 다룬다. 먼저, 신용평가 모델을 학습하고 활용하는 일련의 과정에 대해 구체적인 시나리오를 구성하고, 안전성 요구조건을 정의한다. 또한, 신용평가에서 분류 정확도가 높은 Support Vector Machine(SVM) 학습 알고리즘을 사용하여 신용평가에 최적화된 분류 모델을 학습시킨다. 이때 SVM 학습 알고리즘으로는 동형암호 연산 적용에 적합하게 변환할 수 있는 LS(Linear Square)-SVM 모델을 적용하여 효율적인 신용평가 모델 학습 시스템을 제안한다. 본 연구를 통해 데이터 소유자의 민감한 개인정보를 보호하는 암호화된 신용평가 모델 학습이 가능하며, 학습 결과로 얻은 SVM 모델을 사용하여 신용평가 예측 결과의 정확도를 높일 수 있다. Recently, the development of machine learning and cloud computing has led to the rise of Privacy-Preserving Machine Learning (PPML). Homomorphic encryption enables computations over encrypted data without decryption, and it is secure against adversaries that use quantum computers. This study focuses on learning a credit evaluation model to determine loan eligibility using homomorphic encryption. The study outlines a concrete scenario for learning and using the credit evaluation model in a privacy-preserving way and defines the security requirements. To optimize the credit evaluation model, we use a Support Vector Machine (SVM) training algorithm with high classification accuracy. This paper proposes an efficient credit evaluation model learning system using LS(Linear Square)-SVM model, which is recomposed to an HE-friendly computation. It enables learning of a credit evaluation model over encrypted data while protecting user’s sensitive information and increases the accuracy of credit evaluation predictions.
Compatibility Analysis of the Turbo Controller Area Network (TURBO CAN)
Choi, Eunmin,Han, Sungmin,Lee, Jaeseok,Lee, Seonghun,Kang, Suwon,Choi, Ji-Woong IEEE 2018 IEEE Transactions on Vehicular Technology VT Vol.67 No.6
<P>Given the increased amount of data traffic in in-vehicle networks with more systems now included in vehicles, enormous amounts of research have recently focused on providing reliable and inexpensive quality of service for in-vehicle communication systems. To support high-speed data processing while maintaining backward compatibility with controller area network (CAN) for in-vehicle communication systems, the turbo controller area network (TURBO CAN) was proposed, combining the standard baseband CAN signal with a passband modulated signal. In this paper, we demonstrate both an improvement in the performance and the validity of the backward compatibility of the TURBO CAN system. To be specific, we provide passband channel modeling of the CAN system based on the channel gain and the noise characteristics as measured in an actual vehicle environment. Using these measurements, we also provide proper criteria for determining the power constraint of the passband signal to achieve a highly compatible system by analyzing the channel capacity of TURBO CAN as well as the bit error rate of a standard CAN receiver.</P>