Decision forest: An algorithm for classifying multivariate time series

Ning He, Le Yang Li, Osamu Yoshie

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Nowadays with time series accounting for an increasingly large fraction of world's supply of data, there has been an explosion of interest in mining time series data. This paper proposes an approach of creating a new data structure automatically, for multivariate time series classifi cation. For more accurate and comprehensive classifi cation, induction of valuable rules named soft discretisation decision forest is illustrated comparing with other machine learning methods such as traditional neural network, SVM and nearest neighbour algorithms. Moreover, some real time series instances from the training dataset will be selected as class dedicated patterns. And a splitting stage using fuzzy theory is prepared for comparing attributes of time series. The ideas of authors are confi rmed by simulation results with a set of Japanese vowel time series capably.

Original languageEnglish
Pages (from-to)203-216
Number of pages14
JournalInternational Journal of Business Intelligence and Data Mining
Volume7
Issue number3
DOIs
Publication statusPublished - 2012 Oct

Fingerprint

Multivariate Time Series
Time series
Fuzzy Theory
Time Series Data
Positive ions
Explosion
Mining
Nearest Neighbor
Proof by induction
Data Structures
Machine Learning
Discretization
Attribute
Neural Networks
Explosions
Data structures
Learning systems
Multivariate time series
Neural networks
Simulation

Keywords

  • Classification
  • Decision forest
  • Fuzzy partitioning
  • Multivariate time series
  • Soft discretisation
  • Supervised clustering

ASJC Scopus subject areas

  • Management Information Systems
  • Information Systems and Management
  • Statistics, Probability and Uncertainty

Cite this

Decision forest : An algorithm for classifying multivariate time series. / He, Ning; Li, Le Yang; Yoshie, Osamu.

In: International Journal of Business Intelligence and Data Mining, Vol. 7, No. 3, 10.2012, p. 203-216.

Research output: Contribution to journalArticle

@article{38387d77081548e39f77907a013dd92b,
title = "Decision forest: An algorithm for classifying multivariate time series",
abstract = "Nowadays with time series accounting for an increasingly large fraction of world's supply of data, there has been an explosion of interest in mining time series data. This paper proposes an approach of creating a new data structure automatically, for multivariate time series classifi cation. For more accurate and comprehensive classifi cation, induction of valuable rules named soft discretisation decision forest is illustrated comparing with other machine learning methods such as traditional neural network, SVM and nearest neighbour algorithms. Moreover, some real time series instances from the training dataset will be selected as class dedicated patterns. And a splitting stage using fuzzy theory is prepared for comparing attributes of time series. The ideas of authors are confi rmed by simulation results with a set of Japanese vowel time series capably.",
keywords = "Classification, Decision forest, Fuzzy partitioning, Multivariate time series, Soft discretisation, Supervised clustering",
author = "Ning He and Li, {Le Yang} and Osamu Yoshie",
year = "2012",
month = "10",
doi = "10.1504/IJBIDM.2012.049555",
language = "English",
volume = "7",
pages = "203--216",
journal = "International Journal of Business Intelligence and Data Mining",
issn = "1743-8187",
publisher = "Inderscience Enterprises Ltd",
number = "3",

}

TY - JOUR

T1 - Decision forest

T2 - An algorithm for classifying multivariate time series

AU - He, Ning

AU - Li, Le Yang

AU - Yoshie, Osamu

PY - 2012/10

Y1 - 2012/10

N2 - Nowadays with time series accounting for an increasingly large fraction of world's supply of data, there has been an explosion of interest in mining time series data. This paper proposes an approach of creating a new data structure automatically, for multivariate time series classifi cation. For more accurate and comprehensive classifi cation, induction of valuable rules named soft discretisation decision forest is illustrated comparing with other machine learning methods such as traditional neural network, SVM and nearest neighbour algorithms. Moreover, some real time series instances from the training dataset will be selected as class dedicated patterns. And a splitting stage using fuzzy theory is prepared for comparing attributes of time series. The ideas of authors are confi rmed by simulation results with a set of Japanese vowel time series capably.

AB - Nowadays with time series accounting for an increasingly large fraction of world's supply of data, there has been an explosion of interest in mining time series data. This paper proposes an approach of creating a new data structure automatically, for multivariate time series classifi cation. For more accurate and comprehensive classifi cation, induction of valuable rules named soft discretisation decision forest is illustrated comparing with other machine learning methods such as traditional neural network, SVM and nearest neighbour algorithms. Moreover, some real time series instances from the training dataset will be selected as class dedicated patterns. And a splitting stage using fuzzy theory is prepared for comparing attributes of time series. The ideas of authors are confi rmed by simulation results with a set of Japanese vowel time series capably.

KW - Classification

KW - Decision forest

KW - Fuzzy partitioning

KW - Multivariate time series

KW - Soft discretisation

KW - Supervised clustering

UR - http://www.scopus.com/inward/record.url?scp=84867302391&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84867302391&partnerID=8YFLogxK

U2 - 10.1504/IJBIDM.2012.049555

DO - 10.1504/IJBIDM.2012.049555

M3 - Article

AN - SCOPUS:84867302391

VL - 7

SP - 203

EP - 216

JO - International Journal of Business Intelligence and Data Mining

JF - International Journal of Business Intelligence and Data Mining

SN - 1743-8187

IS - 3

ER -