• Home
  • Search
  • Extended Tied-Mixture HMMs for Both Labeled and Unlabeled Time Series Data
  • Cite Icon2
  • https://doi.org/10.1023/b:vlsi.0000027484.54541.bdCopy DOI Icon

Extended Tied-Mixture HMMs for Both Labeled and Unlabeled Time Series Data

  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Classifier design often faces a lack of sufficient labeled data because the class labels are identified by experienced analysts and therefore collecting labeled data often costs much. To mitigate this problem, several learning methods have been proposed to effectively use unlabeled data that can be inexpensively collected. In these methods, however, only static data have been considered; time series unlabeled data cannot be dealt with by these methods. Focusing on Hidden Markov Models (HMMs), in this paper we first present an extension of HMMs, named Extended Tied-Mixture HMMs (ETM-HMMs), in which both labeled and unlabeled time series data can be utilized simultaneously. We also formally derive a learning algorithm for the ETM-HMMs based on the maximum likelihood framework. Experimental results using synthetic and real time series data show that we can obtain a certainly better classification accuracy when unlabeled time series data are added to labeled training data than the case only labeled data are used.

Similar Papers
  • Conference Article
  • Citations4

HMMs for both labeled and unlabeled time series data

  • Sep 10, 2001
  • M Inoue +1
  • Research Article
  • Citations127

Time series feature learning with labeled and unlabeled data

  • Dec 19, 2018
  • Pattern Recognition
  • Haishuai Wang +4
  • Research Article

FORECASTING LABELLED AND UNLABELLED TIME SERIES DATA THROUGH HISTOGRAM BASED KNN PREDICTION

  • Jan 01, 2018
  • PONTE International Scientific Researchs Journal
  • Kumar V +1
  • Research Article
  • Citations53

Semi-supervised Time Series Classification Model with Self-supervised Learning

  • Sep 01, 2022
  • Engineering Applications of Artificial Intelligence
  • Liang Xi +5
  • Research Article

Use of unlabeled time series data in hidden Markov models

  • Oct 14, 2003
  • Systems and Computers in Japan
  • Masashi Inoue +1
  • Research Article
  • Citations20

SEMI-SUPERVISED SEQUENCE CLASSIFICATION WITH HMMs

  • Mar 01, 2005
  • International Journal of Pattern Recognition and Artificial Intelligence
  • Shi Zhong
  • PDF
  • Conference Article
  • Citations583

Time-Series Representation Learning via Temporal and Contextual Contrasting

  • Aug 01, 2021
  • Emadeldeen Eldele +6
  • Conference Article
  • Citations2

The use of formal measures for the training of hierarchical Kohonen maps

  • Jun 27, 1994
  • P Weierich +1
  • Conference Article

Extended Tied-Mixture HMMs for Both Labeled and Unlabeled Time Series Data

  • Jun 01, 2004
  • Uedanaonori +1
  • PDF
  • Research Article
  • Citations7

Synthetic Time Series Data in Groundwater Analytics: Challenges, Insights, and Applications

  • Mar 25, 2024
  • Water
  • Sarva T Pulla +2
  • Research Article
  • Citations37

Exploitation of unlabeled sequences in hidden Markov models

  • Dec 01, 2003
  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • M Inoue +1
  • Research Article
  • Citations40

Validation of synthetic daily Landsat NDVI time series data generated by the improved spatial and temporal data fusion approach

  • Jun 13, 2017
  • Information Fusion
  • Mingquan Wu +5
  • Conference Article
  • Citations1

Estimating Classification Error to Identify Biomarkers in Time Series Expression Data

  • Oct 01, 2007
  • John H Phan +1
  • Research Article
  • Citations15

Large Scale Time-Series Representation Learning via Simultaneous Low- and High-Frequency Feature Bootstrapping.

  • Jan 01, 2025
  • IEEE transactions on neural networks and learning systems
  • Vandan Gorade +2
  • Book Chapter
  • Citations12

Semi-Supervised Learning

  • Jan 01, 2009
  • Tobias Scheffer
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.