In the article by Sabeti et al., a new information theoretic anomaly detector for time series is introduced. The method is based on detecting changes in the compressability of a test segment of the time series as measured by the difference between complexities of a typical encoder and a universal encoder. The typical and universal encoders are respectively implemented with a tree-structured pattern dictionary, trained on an earlier segment of the time series, and a Lempel–Ziv encoder. The anomaly detector is illustrated for a chaotic time series with model shift and for early detection of anomalous heart rates and skin temperatures of patients after exposure to a respiratory virus.
Read the article, A Pattern Dictionary Method for Anomaly Detection, by Elyas Sabeti, Sehong Oh, Peter X. K. Song, and Alfred O. Hero.
Joint Statistical Meeting (JSM) 2021: Special Session
Session organizers: Yang Chen (Statistics), Alfred Hero (EECS), Tamas Gombosi (CLaSP), Ward Manchester (CLaSP), Univ. of Michigan.
Session I: August 9, Yang Chen, Chair
Session II: August 12, Alfred Hero, Chair
From July 7 to July 12 the IEEE International Symposium on Information Theory will take place in Paris France. Al Hero is General Co-Chair of the conference. The conference website is https://2019.ieee-isit.org/.
Hero is a Section Editor for the new SIAM Journal on Mathematics of Data Science.
SIAM Journal on Mathematics of Data Science (SIMODS) publishes work that advances mathematical, statistical, and computational methods in the context of data and information sciences. We invite papers that present significant advances in this context, including applications to science, engineering, business, and medicine.
Hero chaired panel on data privacy. Read the report on the Big Data in Finance Conference, a meeting hosted by US Office of Financial Research.
On Thursday and Friday, October 27-28, 2016, the Office of Financial Research and the University of Michigan’s Center on Finance, Law and Policy hosted a joint conference, “Big Data in Finance” in Ann Arbor, Michigan, which brought together a wide range of scholars, regulators, policymakers, and practitioners to explore how big data can be used to enhance financial stability and address other challenges in financial markets. More than 250 people attended from around the United States and abroad.
Watch the Panel on Data Privacy and Security
Read Panel-1-Data-Privacy-Security-Big-Data-in-Finance-conference-Final. He Chaired the panel.
Hero co-chaired the study for Interim report on the Envisioning the Data Science Discipline: The Undergraduate Experience, which was run by the US National Academies and funded by NSF.
Description of the report:
The need to manage, analyze, and extract knowledge from data is pervasive across industry, government, and academia. Scientists, engineers, and executives routinely encounter enormous volumes of data, and new techniques and tools are emerging to create knowledge out of these data, some of them capable of working with real-time streams of data. The nation’s ability to make use of these data depends on the availability of an educated workforce with necessary expertise. With these new capabilities have come novel ethical challenges regarding the effectiveness and appropriateness of broad applications of data analyses.
Hero is Committee Chair for the Committee on Applied and Theoretical Statistics (CATS), a sub-committee of the Board on Mathematical Science and Analytics (BMSA) of the US National Academies of Sciences, Engineering, Medicine.
CATS, established in 1978, promotes the statistical sciences, statistical education, statistics applications, and related issues affecting the statistics community. The mission and scope of CATS evolved over time as interdisciplinary collaboration increasingly shaped the character of scientific research. After a brief hiatus, CATS was reconstituted in 2011 and has since focused on improving the visibility and practice of statistics within government agencies not well connected to statistics, increasing attention to statistical issues of big data and data science, and helping agencies identify bottlenecks impairing their analysis capabilities. Its multidisciplinary members are experts from statistics and related fields and leaders in diverse areas of interdisciplinary research, including the analysis of large-scale data, computational biology and bioinformatics, spatial data, environmental science, neuroscience, health care policy, and complex computer experiments.