Teams link https://teams.microsoft.com/meet/36452437613448?p=kHkDYm1MkYrHDnUju9
Add to Google Calendar
Abstract
Time series are a ubiquitous data type, appearing in all medical, scientific and industrial domains. The plunging costs of sensors and storage mean that we are producing tens of millions of terabytes of time series each day. Exploring such data for actionable nuggets of information is challenging. Moreover, the main bottleneck is not CPU time or memory, but human attention.
In this talk I will argue that Time Series Motif Discovery is the perfect tool for discovering novel, unexpected and actionable data in massive datasets. Moreover, I will show that motif discovery’s reputation as being difficult and/or intractable is unwarranted. There are now easy-to-use off-the-shelf tools that allow real-time motif discovery in almost all circumstances.
I will illustrate the talk with many real-world examples from medicine, science (animal and human studies) and industry.
Short Bio
Dr. Keogh is a Distinguished Professor of Computer Science at the University of California. He is the inventor of many of the most commonly used time series data mining primitives including, PAA, LBkeogh, UCR-Suite, the Matrix Profile, SAX, Time Series Motifs and Time Series Shapelets. The last six ideas have gone on to garner at least a thousand citations each.
With 32 papers, he is the most prolific author in the Data Mining and Knowledge Discovery journal and a top-ten most prolific author in ACM SIGKDD, IEEE ICDM and SIAM SDM (with 32/47/27 papers respectively).
He has won numerous awards, including: The Bell Labs Bronze Prize 2021, the ACM SIGKDD 2022 Test of Time Paper Award, the 2021 IEEE ICDM Research Contributions Award, Two Google Faculty Awards, and best paper awards at SIGKDD (twice), SIGMOD (1), ICDM (three times) and SDM. He is the creator of the UCR Time Series Classification Archive, which has been used in more than 5,000 research papers.
More information at News U. Porto