학력
◾ KAIST 산업 및 시스템공학과 박사, 2006.03 - 2012.04
◾ KAIST 산업공학과 학사, 2001.03 - 2005.07
주요 경력
◾ Lunit Inc. Research Lead, 2017.03 - 2018.02
◾ Lunit Inc. Senior Researcher, 2015.01 - 2017.02
◾ 삼성전자 종합기술원 전문연구원, 2012.05 - 2014.12
연구 분야
◾ Deep learning and its applications
◾ Artificial intelligence
◾ Medical image analysis
◾ Machine learning
담당 교과목
◾ (학부) 산업정보시스템전공: 파이썬프로그래밍, 딥러닝
◾ (학부) ITM전공: Artificial Intelligence
◾ (대학원) 데이터사이언스: 데이터분석을 위한 수학, 인공신경망과 딥러닝
저널 논문
◾ M. Veta, [et al. including S. Hwang] (2019), "Predicting breast tumor proliferation from whole-slide images: the TUPAC16 challenge," Medical Image Analysis, 290(1), 218-228.
◾ J. G. Nam, S. Park, [et al. including S. Hwang] (2019), "Development and validation of deep Learning-based automatic detection algorithm for malignant pulmonary nodules on chest radiographs," Radiology, 290(1), 218-228.
◾ S. Hwang, and D. Kim (2018), "A scalable feature based clustering algorithm for sequences with many distinct items," International Journal of Fuzzy Logic and Intelligent Systems, 18(4), 316-325.
◾ S. Hwang, and M. K. Jeong (2018), "Robust relevance vector machine for classi cation with variational inference," Annals of Operations Research, 263(1-2), 21-43.
◾ S. Hwang, J. Yoo, C. Lee, and S. H. Lee (2016), "Collaborative crystal structure prediction," Expert Systems with Applications, 63, 222-230.
◾ Y.-S. Jeong, S. Hwang, and Y.-D. Ko (2015), "Quantitative analysis for plasma etch modeling using optical emission spectroscopy: prediction of plasma etch responses," Industrial Engineering and Management Systems, 14(4), 392-400.
◾ D. Kim, C. Lee, S. Hwang, and M. K. Jeong (2015), "A robust support vector regression with a linear-log concave loss function," Journal of Operational Research Society, 67(5), 735-742.
◾ S. Hwang, D. Kim, M. K. Jeong, and B.-J. Yum (2015), "Robust kernel based regression with bounded infuence for outliers," Journal of Operational Research Society, 66(8), 1385-1398.
◾ D. Mishra, [et al. including S. Hwang] (2015), "Effect of piezoelectricity on critical thickness for mis fit dislocation formation at InGaN/GaN interface," Computational Materials Science, 97, 254-262.
◾ S. Hwang, M. K. Jeong, and B.-J. Yum (2014), "Robust relevance vector machine with variational inference for improving virtual metrology accuracy," IEEE Transactions on Semiconductor Manufacturing, 27(1), 83-94.
◾ Y.-H. Cho, [et al. including S. Hwang] (2013), "Quantum efficiency affected by localized carrier distribution near the V-defect in GaN based quantum well," Applied Physics Letters, 103, 261101.
◾ S.-H. Park, [et al. including S. Hwang] (2013), "Partial strain relaxation effects on polarization anisotropy of semipolar (1122) InGaN/GaN quantum well structures," Applied Physics Letters, 103, 221108.
◾ Additive Ensemble Neural Networks, IEEE ACCESS, vol.8 pp.113192~113199, 2020황상흠
◾ A New Splitting Criterion for Better Interpretable Trees, IEEE ACCESS, vol.8 pp.62762~62774, 2020황상흠
◾ 한국어 기술문서 분석을 위한 BERT 기반의 분류모델, 한국전자거래학회지, vol.25 No.1 pp.203~214, 2020황상흠
학술대회
◾ S. Hwang, and S. Park, "Accurate lung segmentation via network-wise training of convolutional networks," The 3rd International Workshop on Deep Learning in Medical Image Analysis in MICCAI 2017, Sep. 2017.
◾ K. Paeng, S. Hwang, S. Park, and M. Kim, "A uni ed framework for tumor proliferation score prediction in breast histopathology," The 3rd International Workshop on Deep Learning in Medical Image Analysis in MICCAI 2017, Sep. 2017.
◾ S. Hwang, and H.-E. Kim, "Self-transfer learning for weakly supervised lesion localization," The 19th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), 239-246, Oct. 2016.
◾ S. Hwang, H.-E. Kim, J. Jeong, and H.-J. Kim, "A novel approach for tuberculosis screening based on deep convolutional neural networks," in Proceedings of SPIE Medical Imaging, 9785, Mar. 2016.
◾ S. Kim, [et al. including S. Hwang], \Deep convolutional neural network-based mitosis detection in invasive carcinoma of breast by smartphone-based histologic image acquisition," in Modern Pathology (USCAP Annual Meeting), 29, Mar. 2016.
◾ 이건규, 황상흠, 영역 분할 모델의 성능 향상을 위한 대조적 손실함수의 활용, 대한산업공학회 추계학술대회, 온라인, 2020황상흠
◾ Jiin Koo, Seungmoo Yang, Sangheum Hwang, A Comparison of the Performance of Deep Learning Models for Electric Load Forecasting, International Conference on Electric-Vehicle, Smart Grid and Information Technology, Online, 2020황상흠
◾ Jooyoung Moon, Jihyo Kim, Younghak Shin, Sangheum Hwang, Confidence-Aware Learning for Deep Neural Networks, Proceedings of the International Conference on Machine Learning, Online, 2020황상흠
◾ 황재문, 황상흠, 해부학적 구조를 반영한 흉부 X-ray 영상에서의 폐 영역 분할 모델, 대한산업공학회 추계학술대회 논문집, 서울대학교, 2019황상흠
◾ 문주영, 김지효, 황상흠, 심층 신경망의 과한 확신을 방지하는 새로운 정규화 방법, 대한산업공학회 추계학술대회 논문집, 서울대학교, 2019황상흠
◾ 김수민, 황상흠, 윤동희, 김도현, Unsupervised Feature Selection for Autoencoder, 대한산업공학회 춘계공동학술대회 논문집, 광주 김대중컨벤션센터, 2019황상흠
연구프로젝트
◾ Brain CT에 대한 뇌출혈검출 알고리즘 개발, 산학협력단, 2019.03.~2020.02.황상흠
◾ 확률 보정 기법 기반의 능동적 학습 방법의 개발, (주)엘지씨엔에스, 2019.03.~2019.12.황상흠
◾ 도메인 일반화를 위한 제약 최적화 기반의 딥러닝 알고리즘 개발, 한국연구재단, 2018.11.~2020.10.황상흠
◾ LGCNS Deep Learning 기반 비전검사 알고리즘 고도화 자문, (주)엘지씨엔에스, 2018.06.~2018.10.황상흠
◾ 인공지능 기술을 적용한 영상정보 식별에 관한 연구, 합동참모본부, 2018.06.~2018.11.황상흠
◾ 깊은 신경망 모형의 불균형 데이터 학습 양상에 대한 고찰, 산학협력단, 2018.04.~2019.03.황상흠
수상
◾ Inner Product based Deep Neural Networks, 2018 INFORMS International Conference Poster Competition, The Institute for Operations Research and the Management Sciences (INFORMS), 2018황상흠
