Self-labeling techniques for semi-supervised time series classification: an empirical study

An increasing amount of unlabeled time series data available render the semi-supervised paradigm a suitable approach to tackle classification problems with a reduced quantity of labeled data. Self-labeled techniques stand out from semi-supervised classification methods due to their simplicity and th...

Full description

Bibliographic Details
Main Authors: González, Mabel, Bergmeir, Christoph, Triguero, Isaac, Rodríguez, Yanet, Benítez, José M.
Format: Article
Published: Springer 2017
Subjects:
Online Access:https://eprints.nottingham.ac.uk/44845/
_version_ 1848797011483033600
author González, Mabel
Bergmeir, Christoph
Triguero, Isaac
Rodríguez, Yanet
Benítez, José M.
author_facet González, Mabel
Bergmeir, Christoph
Triguero, Isaac
Rodríguez, Yanet
Benítez, José M.
author_sort González, Mabel
building Nottingham Research Data Repository
collection Online Access
description An increasing amount of unlabeled time series data available render the semi-supervised paradigm a suitable approach to tackle classification problems with a reduced quantity of labeled data. Self-labeled techniques stand out from semi-supervised classification methods due to their simplicity and the lack of strong assumptions about the distribution of the labeled and unlabeled data. This paper addresses the relevance of these techniques in the time series classification context by means of an empirical study that compares successful self-labeled methods in conjunction with various learning schemes and dissimilarity measures. Our experiments involve 35 time series datasets with different ratios of labeled data, aiming to measure the transductive and inductive classification capabilities of the self-labeled methods studied. The results show that the nearest-neighbor rule is a robust choice for the base classifier. In addition, the amending and multi-classifier self-labeled-based approaches reveal a promising attempt to perform semi-supervised classification in the time series context.
first_indexed 2025-11-14T19:57:06Z
format Article
id nottingham-44845
institution University of Nottingham Malaysia Campus
institution_category Local University
last_indexed 2025-11-14T19:57:06Z
publishDate 2017
publisher Springer
recordtype eprints
repository_type Digital Repository
spelling nottingham-448452020-05-04T18:59:27Z https://eprints.nottingham.ac.uk/44845/ Self-labeling techniques for semi-supervised time series classification: an empirical study González, Mabel Bergmeir, Christoph Triguero, Isaac Rodríguez, Yanet Benítez, José M. An increasing amount of unlabeled time series data available render the semi-supervised paradigm a suitable approach to tackle classification problems with a reduced quantity of labeled data. Self-labeled techniques stand out from semi-supervised classification methods due to their simplicity and the lack of strong assumptions about the distribution of the labeled and unlabeled data. This paper addresses the relevance of these techniques in the time series classification context by means of an empirical study that compares successful self-labeled methods in conjunction with various learning schemes and dissimilarity measures. Our experiments involve 35 time series datasets with different ratios of labeled data, aiming to measure the transductive and inductive classification capabilities of the self-labeled methods studied. The results show that the nearest-neighbor rule is a robust choice for the base classifier. In addition, the amending and multi-classifier self-labeled-based approaches reveal a promising attempt to perform semi-supervised classification in the time series context. Springer 2017-08-08 Article PeerReviewed González, Mabel, Bergmeir, Christoph, Triguero, Isaac, Rodríguez, Yanet and Benítez, José M. (2017) Self-labeling techniques for semi-supervised time series classification: an empirical study. Knowledge and Information Systems . ISSN 0219-3116 Semi-supervised classification; Self-labeled; Time series classification; Semi-supervised learning; Self-training https://link.springer.com/article/10.1007%2Fs10115-017-1090-9 doi:10.1007/s10115-017-1090-9 doi:10.1007/s10115-017-1090-9
spellingShingle Semi-supervised classification; Self-labeled; Time series classification; Semi-supervised learning; Self-training
González, Mabel
Bergmeir, Christoph
Triguero, Isaac
Rodríguez, Yanet
Benítez, José M.
Self-labeling techniques for semi-supervised time series classification: an empirical study
title Self-labeling techniques for semi-supervised time series classification: an empirical study
title_full Self-labeling techniques for semi-supervised time series classification: an empirical study
title_fullStr Self-labeling techniques for semi-supervised time series classification: an empirical study
title_full_unstemmed Self-labeling techniques for semi-supervised time series classification: an empirical study
title_short Self-labeling techniques for semi-supervised time series classification: an empirical study
title_sort self-labeling techniques for semi-supervised time series classification: an empirical study
topic Semi-supervised classification; Self-labeled; Time series classification; Semi-supervised learning; Self-training
url https://eprints.nottingham.ac.uk/44845/
https://eprints.nottingham.ac.uk/44845/
https://eprints.nottingham.ac.uk/44845/