Skip to main navigation Skip to search Skip to main content

A feature segment based time series classification algorithm

  • Liqiang Pan
  • , Qi Meng*
  • , Wei Pan
  • , Yi Zhao
  • , Huijun Gao
  • *Corresponding author for this work
  • Harbin Institute of Technology
  • Harbin Huade University

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

Abstract

Traditional works on time series classification usually use all of data in time series without distinction. However, that will swamp the discriminative information and decrease the correctness of classification. In this paper, a feature segment based time series classification algorithm was proposed, which only selects some highly discriminative time series data for classification. Firstly, an adaptive time series segmentation method was proposed. Then, a large margin based feature segment selection method was given. Based on these two methods, a time series classification framework was established after representing the time series with the optimal segments. By exploring the discriminative temporal patterns hidden in subsequences of time series and giving them more emphasize, the algorithm proposed in this paper can improve the time series classification performance greatly. Extensive experimental results showed that the proposed algorithm can achieve a good classification performance.

Original languageEnglish
Title of host publicationProceedings - 5th International Conference on Instrumentation and Measurement, Computer, Communication, and Control, IMCCC 2015
EditorsJun-Bao Li
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1333-1338
Number of pages6
ISBN (Electronic)9781467377232
DOIs
StatePublished - 11 Feb 2016
Event5th International Conference on Instrumentation and Measurement, Computer, Communication, and Control, IMCCC 2015 - Qinhuangdao, China
Duration: 18 Sep 201520 Sep 2015

Publication series

NameProceedings - 5th International Conference on Instrumentation and Measurement, Computer, Communication, and Control, IMCCC 2015

Conference

Conference5th International Conference on Instrumentation and Measurement, Computer, Communication, and Control, IMCCC 2015
Country/TerritoryChina
CityQinhuangdao
Period18/09/1520/09/15

Keywords

  • Dynamic time warping
  • Feature segment
  • Large margin
  • Nearest neighbor
  • Time series classification

Fingerprint

Dive into the research topics of 'A feature segment based time series classification algorithm'. Together they form a unique fingerprint.

Cite this