Article

Optimizing time series discretization for knowledge discovery

Authors:

Fabian Mörchen,

Alfred UltschAuthors Info & Claims

KDD '05: Proceedings of the eleventh ACM SIGKDD international conference on Knowledge discovery in data mining

Pages 660 - 665

https://doi.org/10.1145/1081870.1081953

Published: 21 August 2005 Publication History

Abstract

Knowledge Discovery in time series usually requires symbolic time series. Many discretization methods that convert numeric time series to symbolic time series ignore the temporal order of values. This often leads to symbols that do not correspond to states of the process generating the time series and cannot be interpreted meaningfully. We propose a new method for meaningful unsupervised discretization of numeric time series called Persist. The algorithm is based on the Kullback-Leibler divergence between the marginal and the self-transition probability distributions of the discretization symbols. Its performance is evaluated on both artificial and real life data in comparison to the most common discretization methods. Persist achieves significantly higher accuracy than existing static methods and is robust against noise. It also outperforms Hidden Markov Models for all but very simple cases.

References

[1]

J. Bilmes. A Gentle Tutorial on the EM Algorithm and its Application to Parameter Estimation for Gaussian Mixture and Hidden Markov Models. Technical Report ICSI-TR-97-021, University of Berkeley, 1997.

[2]

C. Daw, C. Finney, and E. Tracy. A review of symbolic analysis of experimental data. Review of Scientific Instruments, 74:916--930, 2003.

[3]

J. Dougherty, R. Kohavi, and M. Sahami. Supervised and unsupervised discretization of continuous features. In Int. Conf. on Machine Learning, pages 194--202, 1995.

[4]

A. Gionis and H. Mannila. Finding recurrent sources in sequences. In Proc. 7th Int. Conf. on Computational Molecular Biology, pages 123--130, 2003.

Digital Library

[5]

S. K. Harms and J. Deogun. Sequential association rule mining with time lags. Journal of Intelligent Information Systems (JIIS), 2003.

Digital Library

[6]

M. L. Hetland and P. Saetrom. Temporal rule discovery using genetic programming and specialized hardware. In A. Lotfi, J. Garibaldi, and R. John, editors, Proc. 4th Int. Conf. on Recent Advances in Soft Computing, pages 182--188, 2002.

[7]

M. L. Hetland and P. Saetrom. The role of discretization parameters in sequence rule evolution. In Proc. 7th Int. Conf. on Knowledge-Based Intelligent Information & Engineering Systems, KES. Springer, 2003.

[8]

M. W. Kadous. Learning comprehensible descriptions of multivariate time series. In Proc. 16th Int. Conf. on Machine Learning, pages 454--463. Morgan Kaufmann, 1999.

Digital Library

[9]

E. Keogh. UCR Time Series Data Mining Archive, http://www.cs.ucr.edu/~eamonn/tsdma/index.html, 2002.

[10]

E. Keogh, S. Chu, D. Hart, and M. Pazzani. Segmenting time series: A survey and novel approach. In Data Mining in Time Series Databases. World Scientific Publishing Company, 2003.

[11]

E. Keogh and S. Kasetty. On the need for time series data mining benchmarks: A survey and empirical demonstration. In 8th ACM SIGKDD, Edmonton, Canada, pages 102--111, 2002.

Digital Library

[12]

E. Keogh, S. Lonardi, and B. Chiu. Finding surprising patterns in a time series database in linear time and space. In Proc. 8th ACM SIGKDD, Edmonton, Canada, July 2002.

Digital Library

[13]

E. J. Keogh, K. Chakrabarti, M. J. Pazzani, and S. Mehrotra. Dimensionality reduction for fast similarity search in large time series databases. Knowledge and Information Systems, 3(3):263--286, 2001.

[14]

R. Kohavi and M. Sahami. Error-based and entropy-based discretization of continuous features. In Proc. 2nd Int. Conf. on Knowledge Discovery and Data Mining, pages 114--119, 1996.

[15]

S. Kullback and R. A. Leibler. On information and sufficiency. Annals of Mathematical Statistics, 22:79--86, 1951.

[16]

J. Lin, E. Keogh, S. Lonardi, and B. Chiu. A symbolic representation of time series, with implications for streaming algorithms. In Proc. 8th ACM SIGMOD, DMKD workshop, pages 2--11, 2003.

Digital Library

[17]

H. Liu, F. Hussain, C. L. Tan, and M. Dash. Discretization: An enabling technique. Data Mining and Knowledge Discovery, (6):393--423, 2002.

Digital Library

[18]

J. Mäntyjärvi, J. Himberg, P. Kangas, U. Tuomela, and P. Huuskonen. Sensor signal data set for exploring context recognition of mobile devices. In 2nd Int. Conf. on Pervasive Computing, Linz/Vienna, Austria, 2004.

[19]

F. Mörchen and A. Ultsch. Discovering temporal knowlegde in multivariate time series. In Proc. GfKl 2004, Dortmund, Germany, 2004.

[20]

F. Mörchen, A. Ultsch, and O. Hoos. Extracting interpretable muscle activation patterns with time series knowledge mining. Int. Journal of Knowledge-Based & Intelligent Engineering Systems, 2005.

Digital Library

[21]

L. R. Rabiner. A tutorial on hidden markov models and selected applications in speech recognition. Proc. of IEEE, 77(2):257--286, 1989.

[22]

J. J. Rodriguez, C. J. Alonso, and H. Boström. Learning first order logic time series classifiers. In Proc. 10th Int. Conf. on Inductive Logic Programming, pages 260--275, 2000.

Digital Library

[23]

A. Ultsch. Pareto Density Estimation: Probability Density Estimation for Knowledge Discovery. In Proc. GfKl 2003, Cottbus, Germany, 2003.

Cited By

Shknevsky AShahar YMoskovitch R(2023)The Semantic Adjacency Criterion in Time Intervals MiningBig Data and Cognitive Computing10.3390/bdcc70401737:4(173)Online publication date: 9-Nov-2023
https://doi.org/10.3390/bdcc7040173
Tahan MGhasemzadeh MAsadi S(2023)A Novel Embedded Discretization-Based Deep Learning Architecture for Multivariate Time Series ClassificationIEEE Transactions on Industrial Informatics10.1109/TII.2022.318883919:4(5976-5984)Online publication date: Apr-2023
https://doi.org/10.1109/TII.2022.3188839
Cheng K(2023)Classification of Event Sequences Based on Temporal Relation Features2023 IEEE International Conference on Big Data and Smart Computing (BigComp)10.1109/BigComp57234.2023.00052(18-25)Online publication date: Feb-2023
https://doi.org/10.1109/BigComp57234.2023.00052
Show More Cited By

Index Terms

Optimizing time series discretization for knowledge discovery
1. Computing methodologies
  1. Machine learning

Recommendations

A Hellinger-based discretization method for numeric attributes in classification learning

Many classification algorithms require that training examples contain only discrete values. In order to use these algorithms when some attributes have continuous numeric values, the numeric attributes must be converted into discrete ones. This paper ...
A Method of Discretization of Continuous Attributes in Knowledge Discovery
CSA '13: Proceedings of the 2013 International Conference on Computer Sciences and Applications

Discretization of continuous attributes is an important preprocessing step in knowledge discovery. Most consecutive property boundaries are blurred. It is suitable for soft classification. This paper introduced the fuzzy set of continuous attribute ...
Discretization method of continuous attributes based on decision attributes
AICI'10: Proceedings of the 2010 international conference on Artificial intelligence and computational intelligence: Part II

The attributes in rough set must be discretized, but the general theory on discretization did not think about the decision attribute adequately during discretization of data, as a result, it leads to several redundant rules and lower calculation ...

Comments

Information & Contributors

Information

Published In

cover image ACM Conferences

KDD '05: Proceedings of the eleventh ACM SIGKDD international conference on Knowledge discovery in data mining

August 2005

844 pages

ISBN:159593135X

DOI:10.1145/1081870

General Chair:
Robert Grossman
University of Illinois at Chicago & Open Data Partners, USA
,
Program Chairs:
Roberto Bayardo
IBM Almaden Research, USA
,
Kristin Bennett
RPI, USA

Copyright © 2005 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Sponsors

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 21 August 2005

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Article

Conference

KDD05

Sponsor:

KDD05: The Eleventh ACM SIGKDD International Conference on Knowledge Discovery and Data Mining

August 21 - 24, 2005

Illinois, Chicago, USA

Acceptance Rates

Overall Acceptance Rate 1,133 of 8,635 submissions, 13%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

76
Total Citations
View Citations
1,232
Total Downloads

Downloads (Last 12 months)37
Downloads (Last 6 weeks)3

Reflects downloads up to 01 Sep 2024

Other Metrics

View Author Metrics

Citations

Cited By

Shknevsky AShahar YMoskovitch R(2023)The Semantic Adjacency Criterion in Time Intervals MiningBig Data and Cognitive Computing10.3390/bdcc70401737:4(173)Online publication date: 9-Nov-2023
https://doi.org/10.3390/bdcc7040173
Tahan MGhasemzadeh MAsadi S(2023)A Novel Embedded Discretization-Based Deep Learning Architecture for Multivariate Time Series ClassificationIEEE Transactions on Industrial Informatics10.1109/TII.2022.318883919:4(5976-5984)Online publication date: Apr-2023
https://doi.org/10.1109/TII.2022.3188839
Cheng K(2023)Classification of Event Sequences Based on Temporal Relation Features2023 IEEE International Conference on Big Data and Smart Computing (BigComp)10.1109/BigComp57234.2023.00052(18-25)Online publication date: Feb-2023
https://doi.org/10.1109/BigComp57234.2023.00052
Sheetrit EBrief MElisha O(2023)Predicting unplanned readmissions in the intensive care unit: a multimodality evaluationScientific Reports10.1038/s41598-023-42372-y13:1Online publication date: 18-Sep-2023
https://doi.org/10.1038/s41598-023-42372-y
Sarafian Ben Ari NMoskovitch R(2023)Predictive temporal patterns discoveryExpert Systems with Applications10.1016/j.eswa.2023.119974226(119974)Online publication date: Sep-2023
https://doi.org/10.1016/j.eswa.2023.119974
Harel OMoskovitch R(2023)TIRPClo: efficient and complete mining of time intervals-related patternsData Mining and Knowledge Discovery10.1007/s10618-023-00944-637:5(1806-1857)Online publication date: 30-Jun-2023
https://doi.org/10.1007/s10618-023-00944-6
Grzegorowski M(2023)Selected Aspects of Interactive Feature ExtractionTransactions on Rough Sets XXIII10.1007/978-3-662-66544-2_8(121-287)Online publication date: 1-Jan-2023
https://doi.org/10.1007/978-3-662-66544-2_8
Taktak MTriki S(2023)Overview of Time Series Classification Based on Symbolic Discretization for ECG ApplicationsAdvances in Computational Collective Intelligence10.1007/978-3-031-41774-0_58(740-752)Online publication date: 22-Sep-2023
https://doi.org/10.1007/978-3-031-41774-0_58
Hajizadeh Tahan MGhasemzadeh MAsadi S(2022)Development of fully convolutional neural networks based on discretization in time series classificationIEEE Transactions on Knowledge and Data Engineering10.1109/TKDE.2022.3177724(1-1)Online publication date: 2022
https://doi.org/10.1109/TKDE.2022.3177724
Mordvanyuk NLópez BBifet A(2022)TA4LKnowledge-Based Systems10.1016/j.knosys.2022.108554244:COnline publication date: 23-May-2022
https://dl.acm.org/doi/10.1016/j.knosys.2022.108554
Show More Cited By

View Options

Get Access

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Media

Figures

Other

Tables

View Table of Contents