BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Europe/Stockholm
X-LIC-LOCATION:Europe/Stockholm
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=-1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20191206T142453Z
LOCATION:Substanz 1\, 2
DTSTART;TZID=Europe/Stockholm:20180626T083000
DTEND;TZID=Europe/Stockholm:20180626T100000
UID:isc_hpc_ISC High Performance 2018_sess113_post125@linklings.com
SUMMARY:(RP15) Automatic Classification of System Logs
DESCRIPTION:Research Poster\n\n(RP15) Automatic Classification of System L
 ogs\n\nGhiasvand, Ciorba\n\nSystem logs (syslogs) are a valuable source of
  information for analyzing computing systems behavior.\nThe message part o
 f each syslog entry includes detailed information about its respective eve
 nt.\nSyslog is the de-facto logging protocol of high-performance computing
  systems.\nThe standard draft of the Syslog protocol (RFC5424) provides ge
 neral guidelines for generating syslogs.\nHowever, the message part of sys
 tem logs is unstructured and every software generates its syslog messages 
 independently.\nAutomatic methods are required to efficiently analyze the 
 large number of syslog entries generated by large scale computing systems.
 \nThe unstructured nature of the syslog messages is a major challenge towa
 rds automatic syslog analysis.\nAutomatic text classification is a well-kn
 own approach to address this challenge (Suryawanshi et. al, 2015; Leydesdo
 rff et. al, 2017).\nHowever, to use this approach, the target classes must
  be predefined.\nThe common method for detecting the target classes is to 
 apply machine learning techniques (deep learning) on text samples to gener
 ate a specific classifier for the respective sample text formats.\nThe pre
 sent study proposes a general and automatic classification method for syst
 em logs.\nThe proposed method takes advantage of the high repetition of fr
 equent system log entries and automatically generates accurate classifiers
  (in the form of regular expressions).\nThe preliminary results of analyzi
 ng one month of system logs of a production high-performance computer indi
 cate a very high classification accuracy.\nThe classification accuracy is 
 directly related with the amount of available system logs.\nThe classifier
 s are dynamically updated according to the new log entries.\n\nPasses: Con
 ference Pass, Exascale Systems\n\nTag: Conference Pass, Exascale Systems
URL:https://2018.isc-program.com/presentation/?id=post125&sess=sess113
END:VEVENT
END:VCALENDAR