BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Denver
X-LIC-LOCATION:America/Denver
BEGIN:DAYLIGHT
TZOFFSETFROM:-0700
TZOFFSETTO:-0600
TZNAME:MDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0600
TZOFFSETTO:-0700
TZNAME:MST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20200129T163556Z
LOCATION:603
DTSTART;TZID=America/Denver:20191117T144500
DTEND;TZID=America/Denver:20191117T150000
UID:submissions.supercomputing.org_SC19_sess135_ws_urgent102@linklings.com
SUMMARY:Statistical Parameter Selection for Clustering Persistence Diagram
s
DESCRIPTION:Workshop\n\nStatistical Parameter Selection for Clustering Per
sistence Diagrams\n\nKontak, Vidal, Tierny\n\nIn urgent decision making ap
plications, ensemble simulations are an important way to determine differe
nt outcome scenarios based on currently available data. In this paper, we
will analyze the output of ensemble simulations by considering socalled pe
rsistence diagrams, which are reduced representations of the original data
, motivated by the extraction of topological features. Based on a recently
published progressive algorithm for the clustering of persistence diagram
s, we determine the optimal number of clusters, and therefore the number o
f significantly different outcome scenarios, by the minimization of establ
ished statistical score functions. Furthermore, we present a proof-of-conc
ept prototype implementation of the statistical selection of the number of
clusters and provide the results of an experimental study, where this imp
lementation has been applied to real-world ensemble data sets.\n\nTag: Wor
kshop Reg Pass, Big Data, Computational Science, Data Analytics, Data Mana
gement, Societal Challenges\n\nRegistration Category: Workshop Reg Pass, B
ig Data, Computational Science, Data Analytics, Data Management, Societal
Challenges
URL:https://sc19.supercomputing.org/presentation/?id=ws_urgent102&sess=ses
s135
END:VEVENT
END:VCALENDAR