Sleep analytics and online selective anomaly detection

Tahereh Babaie, Sanjay Chawla, Romesh Abeysuriya

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

We introduce a new problem, the Online Selective Anomaly Detection (OSAD), to model a specific scenario emerging from research in sleep science. Scientists have segmented sleep into several stages and stage two is characterized by two patterns (or anomalies) in the EEG time series recorded on sleep subjects. These two patterns are sleep spindle (SS) and K-complex. The OSAD problem was introduced to design a residual system, where all anomalies (known and unknown) are detected but the system only triggers an alarm when non-SS anomalies appear. The solution of the OSAD problem required us to combine techniques from both data mining and control theory. Experiments on data from real subjects attest to the effectiveness of our approach.

Original languageEnglish
Title of host publicationProceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
PublisherAssociation for Computing Machinery
Pages362-371
Number of pages10
ISBN (Print)9781450329569
DOIs
Publication statusPublished - 2014
Externally publishedYes
Event20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD 2014 - New York, NY
Duration: 24 Aug 201427 Aug 2014

Other

Other20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD 2014
CityNew York, NY
Period24/8/1427/8/14

Fingerprint

Electroencephalography
Control theory
Data mining
Time series
Sleep
Experiments

Keywords

  • anomaly/novelty detection
  • dynamic residue model
  • mining rich data types
  • sleep EEG anomalies

ASJC Scopus subject areas

  • Software
  • Information Systems

Cite this

Babaie, T., Chawla, S., & Abeysuriya, R. (2014). Sleep analytics and online selective anomaly detection. In Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 362-371). Association for Computing Machinery. https://doi.org/10.1145/2623330.2623699

Sleep analytics and online selective anomaly detection. / Babaie, Tahereh; Chawla, Sanjay; Abeysuriya, Romesh.

Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Association for Computing Machinery, 2014. p. 362-371.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Babaie, T, Chawla, S & Abeysuriya, R 2014, Sleep analytics and online selective anomaly detection. in Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Association for Computing Machinery, pp. 362-371, 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD 2014, New York, NY, 24/8/14. https://doi.org/10.1145/2623330.2623699
Babaie T, Chawla S, Abeysuriya R. Sleep analytics and online selective anomaly detection. In Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Association for Computing Machinery. 2014. p. 362-371 https://doi.org/10.1145/2623330.2623699
Babaie, Tahereh ; Chawla, Sanjay ; Abeysuriya, Romesh. / Sleep analytics and online selective anomaly detection. Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Association for Computing Machinery, 2014. pp. 362-371
@inproceedings{12393f59dc22416eab5061ab0bfa14bd,
title = "Sleep analytics and online selective anomaly detection",
abstract = "We introduce a new problem, the Online Selective Anomaly Detection (OSAD), to model a specific scenario emerging from research in sleep science. Scientists have segmented sleep into several stages and stage two is characterized by two patterns (or anomalies) in the EEG time series recorded on sleep subjects. These two patterns are sleep spindle (SS) and K-complex. The OSAD problem was introduced to design a residual system, where all anomalies (known and unknown) are detected but the system only triggers an alarm when non-SS anomalies appear. The solution of the OSAD problem required us to combine techniques from both data mining and control theory. Experiments on data from real subjects attest to the effectiveness of our approach.",
keywords = "anomaly/novelty detection, dynamic residue model, mining rich data types, sleep EEG anomalies",
author = "Tahereh Babaie and Sanjay Chawla and Romesh Abeysuriya",
year = "2014",
doi = "10.1145/2623330.2623699",
language = "English",
isbn = "9781450329569",
pages = "362--371",
booktitle = "Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining",
publisher = "Association for Computing Machinery",

}

TY - GEN

T1 - Sleep analytics and online selective anomaly detection

AU - Babaie, Tahereh

AU - Chawla, Sanjay

AU - Abeysuriya, Romesh

PY - 2014

Y1 - 2014

N2 - We introduce a new problem, the Online Selective Anomaly Detection (OSAD), to model a specific scenario emerging from research in sleep science. Scientists have segmented sleep into several stages and stage two is characterized by two patterns (or anomalies) in the EEG time series recorded on sleep subjects. These two patterns are sleep spindle (SS) and K-complex. The OSAD problem was introduced to design a residual system, where all anomalies (known and unknown) are detected but the system only triggers an alarm when non-SS anomalies appear. The solution of the OSAD problem required us to combine techniques from both data mining and control theory. Experiments on data from real subjects attest to the effectiveness of our approach.

AB - We introduce a new problem, the Online Selective Anomaly Detection (OSAD), to model a specific scenario emerging from research in sleep science. Scientists have segmented sleep into several stages and stage two is characterized by two patterns (or anomalies) in the EEG time series recorded on sleep subjects. These two patterns are sleep spindle (SS) and K-complex. The OSAD problem was introduced to design a residual system, where all anomalies (known and unknown) are detected but the system only triggers an alarm when non-SS anomalies appear. The solution of the OSAD problem required us to combine techniques from both data mining and control theory. Experiments on data from real subjects attest to the effectiveness of our approach.

KW - anomaly/novelty detection

KW - dynamic residue model

KW - mining rich data types

KW - sleep EEG anomalies

UR - http://www.scopus.com/inward/record.url?scp=84907033524&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84907033524&partnerID=8YFLogxK

U2 - 10.1145/2623330.2623699

DO - 10.1145/2623330.2623699

M3 - Conference contribution

AN - SCOPUS:84907033524

SN - 9781450329569

SP - 362

EP - 371

BT - Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining

PB - Association for Computing Machinery

ER -