BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Chicago
X-LIC-LOCATION:America/Chicago
BEGIN:DAYLIGHT
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
TZNAME:CDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
TZNAME:CST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260522T150117Z
LOCATION:D167/174
DTSTART;TZID=America/Chicago:20181111T163000
DTEND;TZID=America/Chicago:20181111T170000
UID:submissions.supercomputing.org_SC18_sess221_ws_mlhpce109@linklings.com
SUMMARY:Automated Parallel Data Processing Engine with Application to Larg
 e-Scale Feature Extraction
DESCRIPTION:Xin Xing (Georgia Institute of Technology) and Bin Dong, Jonat
 han Ajo-Franklin, and Kesheng Wu (Lawrence Berkeley National Laboratory)\n
 \nAs new scientific instruments generate ever more data, we need to parall
 elize advanced data analysis algorithms such as machine learning to harnes
 s the available computing power. The success of commercial Big Data system
 s demonstrated that it is possible to automatically parallelize these algo
 rithms. However, these Big Data tools have trouble handling the complex an
 alysis operations from scientific applications. To overcome this difficult
 y, we have started to build an automated parallel data processing engine f
 or science, known as SystemA1. This paper provides an overview of this dat
 a processing engine, and a use case involving a complex feature extraction
  task from a large-scale seismic recording technology, called distributed 
 acoustic sensing (DAS). The key challenge associated with DAS is that it p
 roduces a vast amount of noisy data. The existing methods used by the DAS 
 team for extracting useful signals like traveling seismic waves from this 
 data are very time-consuming. Our parallel data processing engine reduces 
 the job execution time from 100s of hours to 10s of seconds, and achieves 
 95% parallelization efficiency. We are implementing more advanced techniqu
 es including machine learning using SystemA, and plan to work with more sc
 ientific applications.\n\nTag: Applications, Deep Learning, Machine Learni
 ng\n\nRegistration Category: Workshop Reg Pass\n\n
END:VEVENT
END:VCALENDAR