1d-SAX: A Novel Symbolic Representation for Time Series

Simon Malinowski 1, * Thomas Guyet 1 René Quiniou 1 Romain Tavenard 2
* Corresponding author
1 DREAM - Diagnosing, Recommending Actions and Modelling
Inria Rennes – Bretagne Atlantique , IRISA-D7 - GESTION DES DONNÉES ET DE LA CONNAISSANCE
Abstract : SAX (Symbolic Aggregate approXimation) is one of the main symbolization techniques for time series. A well-known limitation of SAX is that trends are not taken into account in the symbolization. This paper proposes 1d-SAX a method to represent a time series as a sequence of symbols that each contain information about the average and the trend of the series on a segment. We compare the efficiency of SAX and 1d-SAX in terms of goodness-of-fit, retrieval and classification performance for querying a time series database with an asymmetric scheme. The results show that 1d-SAX improves performance using equal quantity of information, especially when the compression rate increases.
Complete list of metadatas

Cited literature [11 references]  Display  Hide  Download

https://halshs.archives-ouvertes.fr/halshs-00912512
Contributor : Romain Tavenard <>
Submitted on : Monday, December 2, 2013 - 11:29:24 AM
Last modification on : Thursday, February 7, 2019 - 5:55:48 PM
Long-term archiving on : Monday, March 3, 2014 - 9:10:09 AM

File

paper_IDA.pdf
Files produced by the author(s)

Identifiers

Citation

Simon Malinowski, Thomas Guyet, René Quiniou, Romain Tavenard. 1d-SAX: A Novel Symbolic Representation for Time Series. International Symposium on Intelligent Data Analysis, 2013, United Kingdom. pp.273-284, ⟨10.1007/978-3-642-41398-8_24⟩. ⟨halshs-00912512⟩

Share

Metrics

Record views

960

Files downloads

1119