Suboptimal partitioning of time-series data for anomaly detection

Xin Jin, Soumik Sarkar, Kushal Mukherjee, Asok Ray

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

8 Citations (Scopus)

Abstract

The concepts of symbolic dynamics and partitioning of time series data have been used for feature extraction and anomaly detection. Although much attention has been paid to modeling of finite state machines from symbol sequences, similar efforts have not been expended for partitioning of time series data to optimally generate symbol sequences. This paper addresses this issue and proposes a partitioning method based on maximum migration of data points across cell boundaries. Various aspects of the proposed partitioning tool, such as identification of evolution characteristics of dynamical systems and adaptive selection of alphabet size, are discussed. Experimental results on an electronic circuit apparatus implementing the Duffing equation show that maximum-migration partitioning yields significant improvement over existing partitioning methods (e.g., maximum entropy partitioning) for the purpose of anomaly detection.

Original languageEnglish (US)
Title of host publicationProceedings of the 48th IEEE Conference on Decision and Control held jointly with 2009 28th Chinese Control Conference, CDC/CCC 2009
Pages1020-1025
Number of pages6
DOIs
StatePublished - Dec 1 2009
Event48th IEEE Conference on Decision and Control held jointly with 2009 28th Chinese Control Conference, CDC/CCC 2009 - Shanghai, China
Duration: Dec 15 2009Dec 18 2009

Publication series

NameProceedings of the IEEE Conference on Decision and Control
ISSN (Print)0191-2216

Other

Other48th IEEE Conference on Decision and Control held jointly with 2009 28th Chinese Control Conference, CDC/CCC 2009
CountryChina
CityShanghai
Period12/15/0912/18/09

Fingerprint

Anomaly Detection
Time Series Data
Time series
Partitioning
Maximum entropy methods
Finite automata
Feature extraction
Dynamical systems
Networks (circuits)
Migration
Maximum Entropy Method
Duffing Equation
Symbolic Dynamics
State Machine
Feature Extraction
Dynamical system
Electronics
Cell
Experimental Results
Modeling

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Modeling and Simulation
  • Control and Optimization

Cite this

Jin, X., Sarkar, S., Mukherjee, K., & Ray, A. (2009). Suboptimal partitioning of time-series data for anomaly detection. In Proceedings of the 48th IEEE Conference on Decision and Control held jointly with 2009 28th Chinese Control Conference, CDC/CCC 2009 (pp. 1020-1025). [5400158] (Proceedings of the IEEE Conference on Decision and Control). https://doi.org/10.1109/CDC.2009.5400158
Jin, Xin ; Sarkar, Soumik ; Mukherjee, Kushal ; Ray, Asok. / Suboptimal partitioning of time-series data for anomaly detection. Proceedings of the 48th IEEE Conference on Decision and Control held jointly with 2009 28th Chinese Control Conference, CDC/CCC 2009. 2009. pp. 1020-1025 (Proceedings of the IEEE Conference on Decision and Control).
@inproceedings{e9eae4fb694a45dbb11c4340e1527302,
title = "Suboptimal partitioning of time-series data for anomaly detection",
abstract = "The concepts of symbolic dynamics and partitioning of time series data have been used for feature extraction and anomaly detection. Although much attention has been paid to modeling of finite state machines from symbol sequences, similar efforts have not been expended for partitioning of time series data to optimally generate symbol sequences. This paper addresses this issue and proposes a partitioning method based on maximum migration of data points across cell boundaries. Various aspects of the proposed partitioning tool, such as identification of evolution characteristics of dynamical systems and adaptive selection of alphabet size, are discussed. Experimental results on an electronic circuit apparatus implementing the Duffing equation show that maximum-migration partitioning yields significant improvement over existing partitioning methods (e.g., maximum entropy partitioning) for the purpose of anomaly detection.",
author = "Xin Jin and Soumik Sarkar and Kushal Mukherjee and Asok Ray",
year = "2009",
month = "12",
day = "1",
doi = "10.1109/CDC.2009.5400158",
language = "English (US)",
isbn = "9781424438716",
series = "Proceedings of the IEEE Conference on Decision and Control",
pages = "1020--1025",
booktitle = "Proceedings of the 48th IEEE Conference on Decision and Control held jointly with 2009 28th Chinese Control Conference, CDC/CCC 2009",

}

Jin, X, Sarkar, S, Mukherjee, K & Ray, A 2009, Suboptimal partitioning of time-series data for anomaly detection. in Proceedings of the 48th IEEE Conference on Decision and Control held jointly with 2009 28th Chinese Control Conference, CDC/CCC 2009., 5400158, Proceedings of the IEEE Conference on Decision and Control, pp. 1020-1025, 48th IEEE Conference on Decision and Control held jointly with 2009 28th Chinese Control Conference, CDC/CCC 2009, Shanghai, China, 12/15/09. https://doi.org/10.1109/CDC.2009.5400158

Suboptimal partitioning of time-series data for anomaly detection. / Jin, Xin; Sarkar, Soumik; Mukherjee, Kushal; Ray, Asok.

Proceedings of the 48th IEEE Conference on Decision and Control held jointly with 2009 28th Chinese Control Conference, CDC/CCC 2009. 2009. p. 1020-1025 5400158 (Proceedings of the IEEE Conference on Decision and Control).

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

TY - GEN

T1 - Suboptimal partitioning of time-series data for anomaly detection

AU - Jin, Xin

AU - Sarkar, Soumik

AU - Mukherjee, Kushal

AU - Ray, Asok

PY - 2009/12/1

Y1 - 2009/12/1

N2 - The concepts of symbolic dynamics and partitioning of time series data have been used for feature extraction and anomaly detection. Although much attention has been paid to modeling of finite state machines from symbol sequences, similar efforts have not been expended for partitioning of time series data to optimally generate symbol sequences. This paper addresses this issue and proposes a partitioning method based on maximum migration of data points across cell boundaries. Various aspects of the proposed partitioning tool, such as identification of evolution characteristics of dynamical systems and adaptive selection of alphabet size, are discussed. Experimental results on an electronic circuit apparatus implementing the Duffing equation show that maximum-migration partitioning yields significant improvement over existing partitioning methods (e.g., maximum entropy partitioning) for the purpose of anomaly detection.

AB - The concepts of symbolic dynamics and partitioning of time series data have been used for feature extraction and anomaly detection. Although much attention has been paid to modeling of finite state machines from symbol sequences, similar efforts have not been expended for partitioning of time series data to optimally generate symbol sequences. This paper addresses this issue and proposes a partitioning method based on maximum migration of data points across cell boundaries. Various aspects of the proposed partitioning tool, such as identification of evolution characteristics of dynamical systems and adaptive selection of alphabet size, are discussed. Experimental results on an electronic circuit apparatus implementing the Duffing equation show that maximum-migration partitioning yields significant improvement over existing partitioning methods (e.g., maximum entropy partitioning) for the purpose of anomaly detection.

UR - http://www.scopus.com/inward/record.url?scp=77950792341&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77950792341&partnerID=8YFLogxK

U2 - 10.1109/CDC.2009.5400158

DO - 10.1109/CDC.2009.5400158

M3 - Conference contribution

AN - SCOPUS:77950792341

SN - 9781424438716

T3 - Proceedings of the IEEE Conference on Decision and Control

SP - 1020

EP - 1025

BT - Proceedings of the 48th IEEE Conference on Decision and Control held jointly with 2009 28th Chinese Control Conference, CDC/CCC 2009

ER -

Jin X, Sarkar S, Mukherjee K, Ray A. Suboptimal partitioning of time-series data for anomaly detection. In Proceedings of the 48th IEEE Conference on Decision and Control held jointly with 2009 28th Chinese Control Conference, CDC/CCC 2009. 2009. p. 1020-1025. 5400158. (Proceedings of the IEEE Conference on Decision and Control). https://doi.org/10.1109/CDC.2009.5400158