Abstract
With most approaches to pattern discovery in time series the notion of a pattern is defined a priori and then an algorithm for the efficient discovery of patterns is proposed. But finding the intrinsic patterns in a collection of time series may require a search for the best pattern representation, too. For one dataset it may be important to consider absolute points in time, for other datasets only the shapes may be of interest. With some datasets reoccurring subseries match the pattern closely and with others only loosely. We propose an MDL-based approach to search not only for patterns, but for the intrinsic pattern representation. The preliminary results of this unsupervised method are promising, because in the examined (supervised) datasets the identified representations led to patterns that discriminate between classes.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Fu, T.-C.: A review on time series data mining. Engineering Applications of Artificial Intelligence 24(1), 164–181 (2011)
Grunwald, P.D.: The Minimum Description Length Principle. University Press Group Ltd. (2007)
Hill, K.: Hate To Break It To You, But Your Car Likely Has A Black Box ‘Spying’ On You Already (2012), http://onforb.es/I7BRLJ
Hu, B., Rakthanmanon, T., Hao, Y., Evans, S., Lonardi, S., Keogh, E.: Discovering the Intrinsic Cardinality and Dimensionality of Time Series Using MDL. In: Proc. 11th Int. Conf. on Data Mining (ICDM), pp. 1086–1091 (2011)
Huffman, D.: A Method for the Construction of Minimum-Redundancy Codes. Proceedings of the IRE 40(9), 1098–1101 (1952)
Keogh, E., Zhu, Q., Hu, B., Hao, Y., Xi, X., Wei, L., Ratanamahatana, C.A.: The UCR Time Series Classification/Clustering Homepage (2011)
Li, Y., Lin, J.: Approximate variable-length time series motif discovery using grammar inference. In: Proceedings of the Tenth International Workshop on Multimedia Data Mining - MDMKDD 2010, pp. 1–9 (2010)
Lin, J., Keogh, E., Wei, L., Lonardi, S.: Experiencing SAX: A novel symbolic representation of time series. Data Mining and Knowledge Discovery 15(2), 107–144 (2007)
Nevill-Manning, C.G., Witten, I.W.: Identifying Hierarchical Structure in Sequences: A linear-time algorithm. Journal of Artificial Intelligence Research 7, 67–82 (1997)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Schweier, A., Höppner, F. (2014). Finding the Intrinsic Patterns in a Collection of Time Series. In: Blockeel, H., van Leeuwen, M., Vinciotti, V. (eds) Advances in Intelligent Data Analysis XIII. IDA 2014. Lecture Notes in Computer Science, vol 8819. Springer, Cham. https://doi.org/10.1007/978-3-319-12571-8_25
Download citation
DOI: https://doi.org/10.1007/978-3-319-12571-8_25
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-12570-1
Online ISBN: 978-3-319-12571-8
eBook Packages: Computer ScienceComputer Science (R0)