Cargando…

A Transductive Model-based Stress Recognition Method Using Peripheral Physiological Signals

Existing research on stress recognition focuses on the extraction of physiological features and uses a classifier that is based on global optimization. There are still challenges relating to the differences in individual physiological signals for stress recognition, including dispersed distribution...

Descripción completa

Detalles Bibliográficos
Autores principales: Li, Minjia, Xie, Lun, Wang, Zhiliang
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2019
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6359102/
https://www.ncbi.nlm.nih.gov/pubmed/30669646
http://dx.doi.org/10.3390/s19020429
_version_ 1783392152036835328
author Li, Minjia
Xie, Lun
Wang, Zhiliang
author_facet Li, Minjia
Xie, Lun
Wang, Zhiliang
author_sort Li, Minjia
collection PubMed
description Existing research on stress recognition focuses on the extraction of physiological features and uses a classifier that is based on global optimization. There are still challenges relating to the differences in individual physiological signals for stress recognition, including dispersed distribution and sample imbalance. In this work, we proposed a framework for real-time stress recognition using peripheral physiological signals, which aimed to reduce the errors caused by individual differences and to improve the regressive performance of stress recognition. The proposed framework was presented as a transductive model based on transductive learning, which considered local learning as a virtue of the neighborhood knowledge of training examples. The degree of dispersion of the continuous labels in the y space was also one of the influencing factors of the transductive model. For prediction, we selected the epsilon-support vector regression (e-SVR) to construct the transductive model. The non-linear real-time features were extracted using a combination of wavelet packet decomposition and bi-spectrum analysis. The performance of the proposed approach was evaluated using the DEAP dataset and Stroop training. The results indicated the effectiveness of the transductive model, which had a better prediction performance compared to traditional methods. Furthermore, the real-time interactive experiment was conducted in field studies to explore the usability of the proposed framework.
format Online
Article
Text
id pubmed-6359102
institution National Center for Biotechnology Information
language English
publishDate 2019
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-63591022019-02-06 A Transductive Model-based Stress Recognition Method Using Peripheral Physiological Signals Li, Minjia Xie, Lun Wang, Zhiliang Sensors (Basel) Article Existing research on stress recognition focuses on the extraction of physiological features and uses a classifier that is based on global optimization. There are still challenges relating to the differences in individual physiological signals for stress recognition, including dispersed distribution and sample imbalance. In this work, we proposed a framework for real-time stress recognition using peripheral physiological signals, which aimed to reduce the errors caused by individual differences and to improve the regressive performance of stress recognition. The proposed framework was presented as a transductive model based on transductive learning, which considered local learning as a virtue of the neighborhood knowledge of training examples. The degree of dispersion of the continuous labels in the y space was also one of the influencing factors of the transductive model. For prediction, we selected the epsilon-support vector regression (e-SVR) to construct the transductive model. The non-linear real-time features were extracted using a combination of wavelet packet decomposition and bi-spectrum analysis. The performance of the proposed approach was evaluated using the DEAP dataset and Stroop training. The results indicated the effectiveness of the transductive model, which had a better prediction performance compared to traditional methods. Furthermore, the real-time interactive experiment was conducted in field studies to explore the usability of the proposed framework. MDPI 2019-01-21 /pmc/articles/PMC6359102/ /pubmed/30669646 http://dx.doi.org/10.3390/s19020429 Text en © 2019 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Li, Minjia
Xie, Lun
Wang, Zhiliang
A Transductive Model-based Stress Recognition Method Using Peripheral Physiological Signals
title A Transductive Model-based Stress Recognition Method Using Peripheral Physiological Signals
title_full A Transductive Model-based Stress Recognition Method Using Peripheral Physiological Signals
title_fullStr A Transductive Model-based Stress Recognition Method Using Peripheral Physiological Signals
title_full_unstemmed A Transductive Model-based Stress Recognition Method Using Peripheral Physiological Signals
title_short A Transductive Model-based Stress Recognition Method Using Peripheral Physiological Signals
title_sort transductive model-based stress recognition method using peripheral physiological signals
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6359102/
https://www.ncbi.nlm.nih.gov/pubmed/30669646
http://dx.doi.org/10.3390/s19020429
work_keys_str_mv AT liminjia atransductivemodelbasedstressrecognitionmethodusingperipheralphysiologicalsignals
AT xielun atransductivemodelbasedstressrecognitionmethodusingperipheralphysiologicalsignals
AT wangzhiliang atransductivemodelbasedstressrecognitionmethodusingperipheralphysiologicalsignals
AT liminjia transductivemodelbasedstressrecognitionmethodusingperipheralphysiologicalsignals
AT xielun transductivemodelbasedstressrecognitionmethodusingperipheralphysiologicalsignals
AT wangzhiliang transductivemodelbasedstressrecognitionmethodusingperipheralphysiologicalsignals