Applied data science : using machine learning for alarm verification : a novel alarm verification service applying various machine learning algorithms can identify false alarms

Stampfli, Jan; Stockinger, Kurt

doi:10.21256/zhaw-3785

Please use this identifier to cite or link to this item: https://doi.org/10.21256/zhaw-3785

Publication type:	Contribution to magazine or newspaper
Title:	Applied data science : using machine learning for alarm verification : a novel alarm verification service applying various machine learning algorithms can identify false alarms
Authors:	Stampfli, Jan Stockinger, Kurt
DOI:	10.21256/zhaw-3785
Published in:	ERCIM News
Volume(Issue):	107
Page(s):	10
Issue Date:	Oct-2016
Publisher / Ed. Institution:	European Research Consortium for Informatics and Mathematics
ISSN:	0926-4981 1564-0094
Language:	English
Subjects:	Machine learning; Alarm verfication
Subject (DDC):	006: Special computer methods
Abstract:	False alarms triggered by sensors of alarm systems are a frequent and costly inconvenience for the emergency services and owners of alarm systems. Around 90% of false alarms are caused by either technical failures such as network down times or human error. To remedy this problem, we develop a novel alarm verification service by leveraging the power of an alarm data warehouse. In addition, we apply various machine learning algorithms to identify false alarms. The goal of our system is to help human responders in their decision about whether or not to trigger costly intervention forces.
URI:	https://digitalcollection.zhaw.ch/handle/11475/7432
Fulltext version:	Published version
License (according to publishing contract):	Not specified
Departement:	School of Engineering
Organisational Unit:	Institute of Computer Science (InIT)
Published as part of the ZHAW project:	SAVE - Smart Alarms & Verified Events
Appears in collections:	Publikationen School of Engineering

Files in This Item:

File	Description	Size	Format
210931.pdf		117.82 kB	Adobe PDF	View/Open

Show full item record

Stampfli, J., & Stockinger, K. (2016). Applied data science : using machine learning for alarm verification : a novel alarm verification service applying various machine learning algorithms can identify false alarms. ERCIM News, 107, 10. https://doi.org/10.21256/zhaw-3785

Stampfli, J. and Stockinger, K. (2016) ‘Applied data science : using machine learning for alarm verification : a novel alarm verification service applying various machine learning algorithms can identify false alarms’, ERCIM News, 107, p. 10. Available at: https://doi.org/10.21256/zhaw-3785.

J. Stampfli and K. Stockinger, “Applied data science : using machine learning for alarm verification : a novel alarm verification service applying various machine learning algorithms can identify false alarms,” ERCIM News, vol. 107, p. 10, Oct. 2016, doi: 10.21256/zhaw-3785.

STAMPFLI, Jan und Kurt STOCKINGER, 2016. Applied data science : using machine learning for alarm verification : a novel alarm verification service applying various machine learning algorithms can identify false alarms. ERCIM News. Oktober 2016. Bd. 107, S. 10. DOI 10.21256/zhaw-3785

Stampfli, Jan, and Kurt Stockinger. 2016. “Applied Data Science : Using Machine Learning for Alarm Verification : A Novel Alarm Verification Service Applying Various Machine Learning Algorithms Can Identify False Alarms.” ERCIM News 107 (October): 10. https://doi.org/10.21256/zhaw-3785.

Stampfli, Jan, and Kurt Stockinger. “Applied Data Science : Using Machine Learning for Alarm Verification : A Novel Alarm Verification Service Applying Various Machine Learning Algorithms Can Identify False Alarms.” ERCIM News, vol. 107, Oct. 2016, p. 10, https://doi.org/10.21256/zhaw-3785.