Multilinear function factorisation for time series feature extraction

Michael Burke, Joan Lasenby

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

3 Citations (Scopus)

Abstract

This work applies a variety of multilinear function factorisation techniques to extract appropriate features or attributes from high dimensional multivariate time series for classification. Recently, a great deal of work has centred around designing time series classifiers using more and more complex feature extraction and machine learning schemes. This paper argues that complex learners and domain specific feature extraction schemes of this type are not necessarily needed for time series classification, as excellent classification results can be obtained by simply applying a number of existing matrix factorisation or linear projection techniques, which are simple and computationally inexpensive. We highlight this using a geometric separability measure and classification accuracies obtained though experiments on four different high dimensional multivariate time series datasets.

Original languageEnglish
Title of host publication2013 18th International Conference on Digital Signal Processing, DSP 2013
PublisherIEEE, Institute of Electrical and Electronics Engineers
ISBN (Print)9781467358057
DOIs
Publication statusPublished - 2013
Externally publishedYes
EventInternational Conference on Digital Signal Processing 2013 - Santorini, Greece
Duration: 1 Jul 20133 Jul 2013
Conference number: 18th

Conference

ConferenceInternational Conference on Digital Signal Processing 2013
Abbreviated titleDSP 2013
CountryGreece
CitySantorini
Period1/07/133/07/13

Keywords

  • Decomposition
  • Feature extraction
  • Multilinear function factorisation
  • Tensor factorisation
  • Time series classification

Cite this