Fri, September 25, 2020, 09:00 – 10:30AM (PDT), 12:00 – 1:30PM (EST)
Online Video Review: https://www.youtube.com/watch?v=Z-nRybK3EDA
Abstract
In both industrial applications and in scientific reproducibility, data quality is increasingly important—especially so for high-impact users such as medical and policy experts. Data quality has been historically challenging to monitor due to its high-dimensional nature, the increasing scale at which it must be performed, and the moving target posed by evolution of both the data model and its underlying real-world process. In this talk, Yu will first discuss how her volunteer team fought to have brought data transparency to CovidNet. Then, Kyle will present his team’s novel approach to continuous data quality monitoring, which combines semantic analysis with time series anomaly detection methods, ending with some examples showing issues (known and benign) detected in the 1point3acres dataset. Prof Shan Lu will also provide an example how the high quality data source can be highly useful for even non-biological scientists to produce meaningful analysis in a situation like COVID-19 pandemic.
Bio
Yu Guo is the cofounder of 1Point3Acres, an online community for overseas Chinese with 20M users, and works full time at Uber ATG, as a Sr. Engineering Manager and head of Machine Learning Platform for the self-driving car. She has led engineering and data science teams at companies including Uber, and Airbnb. She holds a Ph.D. degree in Biostatistics from Harvard University and a bachelor's degree in Mathematics from Nankai University.
Kyle Kirwan is the cofounder and CEO of Toro Data Labs, makers of a monitoring and anomaly-detection system for data quality. As a former member of Uber’s data platform, he led the development of internal metadata tools used for data cataloging, quality, lineage, and latency for their petabyte scale data lake. He holds a B.S. in Industrial and Systems Engineering from the University of Florida.
Shan Lu is a Professor of Medicine at the University of Massachusetts Medical School. He is a world leading vaccine expert and served as the president of International Society for Vaccines (ISV). He has done extensive research in developing novel vaccines against emerging infectious disease including HIV and SARS. He is a pioneer in the discovery of DNA vaccines. The novel DNA prime/protein boost HIV vaccine developed from his lab is currently on clincial development in human studies. He is also the Editor-in-Chief of EMI (Emerging Microbes & Infections). He is also a board certified physician practicing at Massachusetts for over 20 years.
@Dahshu 2020
