您所在的位置: 首页 >> 学术活动 >> 正文

学术活动

Imbalanced Data Handling Methods and Evaluation Criteria
发布时间:2019-06-14     浏览量:   分享到:

报告题目Imbalanced Data Handling Methods and Evaluation Criteria

报告人Dr. Chaoyang Zhang, PhD,Professor of Computer Science,School of Computing University of Southern Mississippi, USA

报告时间15:00      2019年6月17

报告地点:长安校区 文津楼三段3412

主办团队:生物大数据计算研究团队

报告摘要

The big data analytics relies on advanced data mining and machine learning methods. It is important to ensure correct use of these machine learning approaches for solving a variety of real-world problems. In this talk I will present several challenges and critical problems of applying supervised learning algorithms to classification and prediction. The talk will focus on feature engineering methods, imbalanced data handling techniques and propriate evaluation criteria in supervised learning. As an example, I will introduce our new advances in data mining and machine learning, including deep learning, for quantitative structure-activity relationship (QSAR) modeling and toxicity analysis in environmental science. Additionally, I will also report our progress of deep transfer learning for pattern recognition and image classification in transportation systems and cancer diagnosis. These machine learning methods and techniques may be generalized and applied to the big data analysis in other areas.

报告人简介

Dr. Chaoyang Zhang is a tenured full professor of computer science in the School of Computing at the University of Southern Mississippi and has supervised thirteen Ph.D. students. He was the Director of School of Computing from 2008 to 2014. His research includes data mining, machine learning, deep learning, big data analytics, image processing and pattern classification, bioinformatics, medical informatics. Dr. Zhang, as principal investigator or co-principal investigator, received eighteen research grants with a total of five million dollars, supported by US National Science Foundation, Department of Defense, National Institute of Health, Homeland Security, American Heart Association, etc. Dr. Zhang has published more than eighty peer-reviewed journal articles and conference papers, one of which received the Sylvia Sorkin Greenfield Award (the best paper award of the Journal of Medical Physics, awarded by American Association of Physicists in Medicine in 2005). Dr. Zhang has been very active in academic service and leadership. He served on several National Science Foundation panels. He was the co-founder and Program Committee Chair of the International Joint Conferences on Bioinformatics, Systems Biology and Intelligent Computing, (IJCBS’09) ShangHai, China, August 2009. He also severed as 2010 ACM-BCB Steering Committee Co-Chair, 2009 IJCBS conference program committee chair. Dr. Zhang was elected to serve as President of the US Midsouth Computational Biology and Bioinformatics Society (MCBIOS) in 2014-2015 and he received MCBIOS Academic Service Award in 2018.