BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CERN//INDICO//EN
BEGIN:VEVENT
SUMMARY:Anomaly Detection for DQM: automation and ML techniques
DTSTART:20260527T150000Z
DTEND:20260527T160000Z
DTSTAMP:20260609T034300Z
UID:indico-event-18167@indico.global
DESCRIPTION:Speakers: Rob White\n\nSuccessful operation of large particle 
 detectors like the Compact Muon Solenoid (CMS) at the CERN Large Hadron Co
 llider requires rapid\, in-depth assessment of data quality. We introduce 
 the “AutoDQM” system for Automated Data Quality Monitoring using advan
 ced statistical techniques and unsupervised machine learning. Anomaly dete
 ction algorithms based on the beta-binomial probability function and princ
 ipal component analysis are tested on the full set of proton-proton collis
 ion data collected by the CMS Level 1 Trigger in 2022. AutoDQM identifies 
 anomalous “bad” data affected by significant detector malfunction at a
  rate 4 – 6 times higher than “good” data\, demonstrating its effect
 iveness as a general data quality monitoring tool.\n \nJoin Zoom Meetingh
 ttps://cern.zoom.us/j/66923142456?pwd=pVCSHwJ6Mo5SbbNbceRuagSOVPR823.1Meet
 ing ID: 669 2314 2456Passcode: 367220\n\nhttps://indico.global/event/18167
 /
LOCATION:Berry Lecture Room (3.21)
URL:https://indico.global/event/18167/
END:VEVENT
END:VCALENDAR