Decision-Tree Induction from Time-Series Data Based on a Standard-Example Split Test

Abstract

This paper proposes a novel decision tree for a data set with time-series attributes. Our time-series tree has a value (i.e. a time sequence) of a time-series attribute in its internal node, and splits examples based on dissimilarity between a pair of time sequences. Our method selects, for a split test, a time sequence which exists in data by exhaustive search based on class and shape information. Experimental results confirm that our induction method constructs comprehensive and accurate decision trees. Moreover, a medical application shows that our time-series tree is promising for knowledge discovery. ICML Proceedings of the Twentieth International Conference on Machine Learning

Cite

Text

Yamada et al. "Decision-Tree Induction from Time-Series Data Based on a Standard-Example Split Test." International Conference on Machine Learning, 2003.

Markdown

[Yamada et al. "Decision-Tree Induction from Time-Series Data Based on a Standard-Example Split Test." International Conference on Machine Learning, 2003.](https://mlanthology.org/icml/2003/yamada2003icml-decision/)

BibTeX

@inproceedings{yamada2003icml-decision,
  title     = {{Decision-Tree Induction from Time-Series Data Based on a Standard-Example Split Test}},
  author    = {Yamada, Yuu and Suzuki, Einoshin and Yokoi, Hideto and Takabayashi, Katsuhiko},
  booktitle = {International Conference on Machine Learning},
  year      = {2003},
  pages     = {840-847},
  url       = {https://mlanthology.org/icml/2003/yamada2003icml-decision/}
}