Possibilistic Bayes Modelling for Predictive Analytics

Christer Carlsson; Markku Heikkilä; Jozsef Mezei

doi:10.1109/CINTI.2014.7028671

Possibilistic Bayes Modelling for Predictive Analytics

Christer Carlsson, Markku Heikkilä, Jozsef Mezei

Research output: Chapter in Book/Conference proceeding › Conference contribution › Scientific › peer-review

6 Citations (Scopus)

Abstract

Studies in the process industry (and also common sense) show that the most cost effective way to keep production processes running is through predictive maintenance,i.e. to carry out optimal maintenance actions just in time before a process fails. Modern processes are highly auto mated; data is collected with sensor technology that forms a big data context and offers challenges to identify coming failures from very large sets of data. Modern analytics develops algorithms that are fast and effective enough to create possibilities for optimal JIT (Just-in Time) maintenance decisions.

Original language	Undefined/Unknown
Title of host publication	CINTI 2014 • 15th IEEE International Symposium on Computational Intelligence and Informatics
Publisher	IEEE Computer Society Institute of Electrical and Electronic Engineers
Pages	–
ISBN (Print)	978-1-4799-5337-0
DOIs	https://doi.org/10.1109/CINTI.2014.7028671
Publication status	Published - 2014
MoE publication type	A4 Article in a conference publication
Event	conference; 2014-11-19; 2014-11-21 - Obuda University, Budapest, Hungary Duration: 19 Nov 2014 → 21 Nov 2014

Conference

Conference	conference; 2014-11-19; 2014-11-21
Period	19/11/14 → 21/11/14

Access to Document

10.1109/CINTI.2014.7028671

http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7028671

Cite this

@inproceedings{7160f65acaee4e0ab2e2cae0d7e8dc0e,

title = "Possibilistic Bayes Modelling for Predictive Analytics",

abstract = "Studies in the process industry (and also common sense) show that the most cost effective way to keep production processes running is through predictive maintenance,i.e. to carry out optimal maintenance actions just in time before a process fails. Modern processes are highly auto mated; data is collected with sensor technology that forms a big data context and offers challenges to identify coming failures from very large sets of data. Modern analytics develops algorithms that are fast and effective enough to create possibilities for optimal JIT (Just-in Time) maintenance decisions.",

author = "Christer Carlsson and Markku Heikkil{\"a} and Jozsef Mezei",

year = "2014",

doi = "10.1109/CINTI.2014.7028671",

language = "Odefinierat/ok{\"a}nt",

isbn = "978-1-4799-5337-0",

pages = "–",

booktitle = "CINTI 2014 • 15th IEEE International Symposium on Computational Intelligence and Informatics",

publisher = "IEEE Computer Society Institute of Electrical and Electronic Engineers",

note = "conference; 2014-11-19; 2014-11-21 ; Conference date: 19-11-2014 Through 21-11-2014",

}

Possibilistic Bayes Modelling for Predictive Analytics. / Carlsson, Christer ; Heikkilä, Markku ; Mezei, Jozsef.
CINTI 2014 • 15th IEEE International Symposium on Computational Intelligence and Informatics. IEEE Computer Society Institute of Electrical and Electronic Engineers, 2014. p. –.

Research output: Chapter in Book/Conference proceeding › Conference contribution › Scientific › peer-review

TY - GEN

T1 - Possibilistic Bayes Modelling for Predictive Analytics

AU - Carlsson, Christer

AU - Heikkilä, Markku

AU - Mezei, Jozsef

PY - 2014

Y1 - 2014

N2 - Studies in the process industry (and also common sense) show that the most cost effective way to keep production processes running is through predictive maintenance,i.e. to carry out optimal maintenance actions just in time before a process fails. Modern processes are highly auto mated; data is collected with sensor technology that forms a big data context and offers challenges to identify coming failures from very large sets of data. Modern analytics develops algorithms that are fast and effective enough to create possibilities for optimal JIT (Just-in Time) maintenance decisions.

AB - Studies in the process industry (and also common sense) show that the most cost effective way to keep production processes running is through predictive maintenance,i.e. to carry out optimal maintenance actions just in time before a process fails. Modern processes are highly auto mated; data is collected with sensor technology that forms a big data context and offers challenges to identify coming failures from very large sets of data. Modern analytics develops algorithms that are fast and effective enough to create possibilities for optimal JIT (Just-in Time) maintenance decisions.

U2 - 10.1109/CINTI.2014.7028671

DO - 10.1109/CINTI.2014.7028671

M3 - Konferensbidrag

SN - 978-1-4799-5337-0

SP - –

BT - CINTI 2014 • 15th IEEE International Symposium on Computational Intelligence and Informatics

PB - IEEE Computer Society Institute of Electrical and Electronic Engineers

T2 - conference; 2014-11-19; 2014-11-21

Y2 - 19 November 2014 through 21 November 2014

ER -