Subsequence matching on structured time series data

Huanmei Wu, Steve B. Jiang, Betty Salzberg, Hiroki Shirato, Gregory C. Sharp, David Kaeli

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

39 Citations (Scopus)

Abstract

Subsequence matching in time series databases is a useful technique, with applications in pattern matching, prediction, and rule discovery. Internal structure within the time series data can be used to improve these tasks, and provide important insight into the problem domain. This paper introduces our research effort in using the internal structure of a time series directly in the matching process. This idea is applied to the problem domain of respiratory motion data in cancer radiation treatment. We propose a comprehensive solution for analysis, clustering, and online prediction of respiratory motion using subsequence similarity matching. In this system, a motion signal is captured in real time as a data stream, and is analyzed immediately for treatment and also saved in a database for future study. A piecewise linear representation of the signal is generated from a finite state model, and is used as a query for sub-sequence matching. To ensure that the query subsequence is representative, we introduce the concept of subsequence stability, which can be used to dynamically adjust the query subsequence length. To satisfy the special needs of similarity matching over breathing patterns, a new subsequence similarity measure is introduced. This new measure uses a weighted L 1 distance function to capture the relative importance of each source stream, amplitude, frequency, and proximity in time. From the subsequence similarity measure, stream and patient similarity can be denned, which are then used for offline and online applications. The matching results are analyzed and applied for motion prediction and correlation discovery. While our system has been customized for use in radiation therapy, our approach to time series modeling is general enough for application domains with structured time series data.

Original languageEnglish (US)
Title of host publicationProceedings of the ACM SIGMOD International Conference on Management of Data
EditorsJ. Widom, F. Ozcan, R. Chirkova
Pages682-693
Number of pages12
DOIs
StatePublished - 2005
EventSIGMOD 2005: ACM SIGMOD International Conference on Management of Data - Baltimore, MD, United States
Duration: Jun 14 2005Jun 16 2005

Other

OtherSIGMOD 2005: ACM SIGMOD International Conference on Management of Data
CountryUnited States
CityBaltimore, MD
Period6/14/056/16/05

Fingerprint

Time series
Pattern matching
Radiotherapy
Radiation

ASJC Scopus subject areas

  • Computer Science(all)

Cite this

Wu, H., Jiang, S. B., Salzberg, B., Shirato, H., Sharp, G. C., & Kaeli, D. (2005). Subsequence matching on structured time series data. In J. Widom, F. Ozcan, & R. Chirkova (Eds.), Proceedings of the ACM SIGMOD International Conference on Management of Data (pp. 682-693) https://doi.org/10.1145/1066157.1066235

Subsequence matching on structured time series data. / Wu, Huanmei; Jiang, Steve B.; Salzberg, Betty; Shirato, Hiroki; Sharp, Gregory C.; Kaeli, David.

Proceedings of the ACM SIGMOD International Conference on Management of Data. ed. / J. Widom; F. Ozcan; R. Chirkova. 2005. p. 682-693.

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

Wu, H, Jiang, SB, Salzberg, B, Shirato, H, Sharp, GC & Kaeli, D 2005, Subsequence matching on structured time series data. in J Widom, F Ozcan & R Chirkova (eds), Proceedings of the ACM SIGMOD International Conference on Management of Data. pp. 682-693, SIGMOD 2005: ACM SIGMOD International Conference on Management of Data, Baltimore, MD, United States, 6/14/05. https://doi.org/10.1145/1066157.1066235
Wu H, Jiang SB, Salzberg B, Shirato H, Sharp GC, Kaeli D. Subsequence matching on structured time series data. In Widom J, Ozcan F, Chirkova R, editors, Proceedings of the ACM SIGMOD International Conference on Management of Data. 2005. p. 682-693 https://doi.org/10.1145/1066157.1066235
Wu, Huanmei ; Jiang, Steve B. ; Salzberg, Betty ; Shirato, Hiroki ; Sharp, Gregory C. ; Kaeli, David. / Subsequence matching on structured time series data. Proceedings of the ACM SIGMOD International Conference on Management of Data. editor / J. Widom ; F. Ozcan ; R. Chirkova. 2005. pp. 682-693
@inproceedings{b31a294d73954f78ab4a63475b385687,
title = "Subsequence matching on structured time series data",
abstract = "Subsequence matching in time series databases is a useful technique, with applications in pattern matching, prediction, and rule discovery. Internal structure within the time series data can be used to improve these tasks, and provide important insight into the problem domain. This paper introduces our research effort in using the internal structure of a time series directly in the matching process. This idea is applied to the problem domain of respiratory motion data in cancer radiation treatment. We propose a comprehensive solution for analysis, clustering, and online prediction of respiratory motion using subsequence similarity matching. In this system, a motion signal is captured in real time as a data stream, and is analyzed immediately for treatment and also saved in a database for future study. A piecewise linear representation of the signal is generated from a finite state model, and is used as a query for sub-sequence matching. To ensure that the query subsequence is representative, we introduce the concept of subsequence stability, which can be used to dynamically adjust the query subsequence length. To satisfy the special needs of similarity matching over breathing patterns, a new subsequence similarity measure is introduced. This new measure uses a weighted L 1 distance function to capture the relative importance of each source stream, amplitude, frequency, and proximity in time. From the subsequence similarity measure, stream and patient similarity can be denned, which are then used for offline and online applications. The matching results are analyzed and applied for motion prediction and correlation discovery. While our system has been customized for use in radiation therapy, our approach to time series modeling is general enough for application domains with structured time series data.",
author = "Huanmei Wu and Jiang, {Steve B.} and Betty Salzberg and Hiroki Shirato and Sharp, {Gregory C.} and David Kaeli",
year = "2005",
doi = "10.1145/1066157.1066235",
language = "English (US)",
pages = "682--693",
editor = "J. Widom and F. Ozcan and R. Chirkova",
booktitle = "Proceedings of the ACM SIGMOD International Conference on Management of Data",

}

TY - GEN

T1 - Subsequence matching on structured time series data

AU - Wu, Huanmei

AU - Jiang, Steve B.

AU - Salzberg, Betty

AU - Shirato, Hiroki

AU - Sharp, Gregory C.

AU - Kaeli, David

PY - 2005

Y1 - 2005

N2 - Subsequence matching in time series databases is a useful technique, with applications in pattern matching, prediction, and rule discovery. Internal structure within the time series data can be used to improve these tasks, and provide important insight into the problem domain. This paper introduces our research effort in using the internal structure of a time series directly in the matching process. This idea is applied to the problem domain of respiratory motion data in cancer radiation treatment. We propose a comprehensive solution for analysis, clustering, and online prediction of respiratory motion using subsequence similarity matching. In this system, a motion signal is captured in real time as a data stream, and is analyzed immediately for treatment and also saved in a database for future study. A piecewise linear representation of the signal is generated from a finite state model, and is used as a query for sub-sequence matching. To ensure that the query subsequence is representative, we introduce the concept of subsequence stability, which can be used to dynamically adjust the query subsequence length. To satisfy the special needs of similarity matching over breathing patterns, a new subsequence similarity measure is introduced. This new measure uses a weighted L 1 distance function to capture the relative importance of each source stream, amplitude, frequency, and proximity in time. From the subsequence similarity measure, stream and patient similarity can be denned, which are then used for offline and online applications. The matching results are analyzed and applied for motion prediction and correlation discovery. While our system has been customized for use in radiation therapy, our approach to time series modeling is general enough for application domains with structured time series data.

AB - Subsequence matching in time series databases is a useful technique, with applications in pattern matching, prediction, and rule discovery. Internal structure within the time series data can be used to improve these tasks, and provide important insight into the problem domain. This paper introduces our research effort in using the internal structure of a time series directly in the matching process. This idea is applied to the problem domain of respiratory motion data in cancer radiation treatment. We propose a comprehensive solution for analysis, clustering, and online prediction of respiratory motion using subsequence similarity matching. In this system, a motion signal is captured in real time as a data stream, and is analyzed immediately for treatment and also saved in a database for future study. A piecewise linear representation of the signal is generated from a finite state model, and is used as a query for sub-sequence matching. To ensure that the query subsequence is representative, we introduce the concept of subsequence stability, which can be used to dynamically adjust the query subsequence length. To satisfy the special needs of similarity matching over breathing patterns, a new subsequence similarity measure is introduced. This new measure uses a weighted L 1 distance function to capture the relative importance of each source stream, amplitude, frequency, and proximity in time. From the subsequence similarity measure, stream and patient similarity can be denned, which are then used for offline and online applications. The matching results are analyzed and applied for motion prediction and correlation discovery. While our system has been customized for use in radiation therapy, our approach to time series modeling is general enough for application domains with structured time series data.

UR - http://www.scopus.com/inward/record.url?scp=29844444491&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=29844444491&partnerID=8YFLogxK

U2 - 10.1145/1066157.1066235

DO - 10.1145/1066157.1066235

M3 - Conference contribution

AN - SCOPUS:29844444491

SP - 682

EP - 693

BT - Proceedings of the ACM SIGMOD International Conference on Management of Data

A2 - Widom, J.

A2 - Ozcan, F.

A2 - Chirkova, R.

ER -