http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
정소현(Sohyun Jeong),장선미(Sunmee Jang) 대한약학회 2019 약학회지 Vol.63 No.2
The development of systematic and structural tool evaluating drug Benefit-Risk Assessment (BRA) has long been a hot issue in pharmaceutical and regulatory division worldwide. It has been proposed to conduct drug BRA during the whole drug life due to the unknown adverse events by long term drug use or unconfirmed drug efficacy and safety in specific groups of people by the golden rule of drug approval evidence, randomized controlled trials being widely comprehended. We aimed to collect and review BRA tools and strategies in the advanced countries, international organizations, and Korea in order to get the trends and knowledges of BRA to advance the BRA system in Korea. ICH and WHO did not support a specific BRA model but stated the basic principles and formats. EMA & IMI conducted a rigorous project to present and suggest quantitative and qualitative BRA methods. They highlighted using ProACT-URL and Effects Table in regulatory decision process and suggested to utilize quantitative Multiple Criteria Decision Analysis in BRA. FDA suggested simple and qualitative approach of Benefit Risk Framework (BRF), in the concern of potential bias induced by quantitative approach. Korea also has been following up the advanced BRA tools consistently but requires establishment of localized BRA strategy satisfying its own perspectives. From these contexts, Korea needs to build up a task force or tangible environment to actively discuss and implement BRA tools.
딥러닝 표정 인식을 활용한 실시간 온라인 강의 이해도 분석
이자연,정소현,신유원,이은혜,하유빈,최장환,Lee, Jaayeon,Jeong, Sohyun,Shin, You Won,Lee, Eunhye,Ha, Yubin,Choi, Jang-Hwan 한국멀티미디어학회 2020 멀티미디어학회논문지 Vol.23 No.12
Due to the spread of COVID-19, the online lecture has become more prevalent. However, it was found that a lot of students and professors are experiencing lack of communication. This study is therefore designed to improve interactive communication between professors and students in real-time online lectures. To do so, we explore deep learning approaches for automatic recognition of students' facial expressions and classification of their understanding into 3 classes (Understand / Neutral / Not Understand). We use 'BlazeFace' model for face detection and 'ResNet-GRU' model for facial expression recognition (FER). We name this entire process 'Degree of Understanding (DoU)' algorithm. DoU algorithm can analyze a multitude of students collectively and present the result in visualized statistics. To our knowledge, this study has great significance in that this is the first study offers the statistics of understanding in lectures using FER. As a result, the algorithm achieved rapid speed of 0.098sec/frame with high accuracy of 94.3% in CPU environment, demonstrating the potential to be applied to real-time online lectures. DoU Algorithm can be extended to various fields where facial expressions play important roles in communications such as interactions with hearing impaired people.
식품의약품안전청의 의약품안전사용정보방 웹사이트 구축을 위한 컨텐츠 개발
지은희(Eunhee Ji),박효영(Hyo Yung Park),노혜진(Hyejin Noh),이동은(Dong Eun Lee),한나영(Nayoung Han),정소현(Sohyun Jeong),김인화(In-Wha Kim),신완균(Wan Gyoon Shin),오정미(Jung Mi Oh) 대한약학회 2012 약학회지 Vol.56 No.3
The purpose of this study was to construct database for a drug safety information website to serve as an access point of up-to-date resources for a wide variety of drug-safety information helping patients and healthcare professionals make well-informed decisions about medication use. All the contents developed were confirmed by the council of advisors who were the experts in drug safety. The detailed contents of database on frequently prescribed drug including 9 NSAIDs, 19 antibiotics, 24 cardiovascular, 21 metabolic, 14 respiratory, 20 digestive, 22 hormonal, 10 genitourinary, 10 anti-allergic, 27 antifungal/antiviral, and 71 neuropsychiatric agents were developed based on the approved drug labeling of the Korean FDA. A separately searchable database of drug-specific safety information for patients and health professionals was constructed for users in need of different depth of knowledge on using medications safely. The safety information on highly prevalent chronic diseases and drug classes was also developed. Finally the most recent global drug safety news was provided. The consumer directed information was developed in layman’s terms as means of proving user-friendly information. The creation of this type of website is part of the Korean FDA’s ongoing initiative to address and promote the safe use of medications for the public.