Multi-Level Stress Detection using Ensemble Filter-based Feature Selection Method

Arham Reza; Pawan Kumar Singh; Mufti Mahmud; David J. Brown; Ram Sarkar

doi:10.1007/978-981-99-1916-1_13

Multi-Level Stress Detection using Ensemble Filter-based Feature Selection Method

Arham Reza
, Pawan Kumar Singh
, Mufti Mahmud^*
, David J. Brown
, Ram Sarkar

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

3 Scopus citations

Abstract

Stress has become one of the major concerns in modern human life, especially after the outbreak of the COVID-19 pandemic, and it has had a great impact on human daily life activities. Detecting stress from physiological signals at an early stage is crucial as it prevents it from outgrowing severe health issues. Most researchers interested in stress detection have focused on developing new feature extraction methods. In this paper, at first, we have extracted some common statistical features from raw data. Then to remove redundant features, we have proposed an ensemble of filter-based feature selection methods for stress detection. Two filter methods, namely, Mutual Information and Pearson Correlation Coefficient are used to obtain the rank of the features. Based on the selected features, three popular classification models, namely, Decision Tree, Random Forest, and K-nearest neighbors are used for the detection of four stress classes—baseline, stress, amusement, and meditation). The proposed method has been applied to the publicly available standard WESAD dataset which consists of various physiological signals taken from both chest and wrist. We have achieved classification accuracies of 99.9% and 96.8% for subject-dependent and subject-independent cases, respectively.

Original language	English
Title of host publication	Proceedings of Trends in Electronics and Health Informatics - TEHI 2022
Editors	Mufti Mahmud, Claudia Mendoza-Barrera, M. Shamim Kaiser, Anirban Bandyopadhyay, Kanad Ray, Eduardo Lugo
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	161-173
Number of pages	13
ISBN (Print)	9789819919154
DOIs	https://doi.org/10.1007/978-981-99-1916-1_13
State	Published - 2023
Externally published	Yes
Event	2nd International Conference on Trends in Electronics and Health Informatics, TEHI 2022 - Puebla, Mexico Duration: 7 Dec 2022 → 9 Dec 2022

Publication series

Name	Lecture Notes in Networks and Systems
Volume	675 LNNS
ISSN (Print)	2367-3370
ISSN (Electronic)	2367-3389

Conference

Conference	2nd International Conference on Trends in Electronics and Health Informatics, TEHI 2022
Country/Territory	Mexico
City	Puebla
Period	7/12/22 → 9/12/22

Bibliographical note

Publisher Copyright:
© 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Keywords

Ensemble learning
Feature selection
Filter method
Stress detection
WESAD dataset

ASJC Scopus subject areas

Control and Systems Engineering
Signal Processing
Computer Networks and Communications

Access to Document

10.1007/978-981-99-1916-1_13

Cite this

Reza, A., Singh, P. K., Mahmud, M., Brown, D. J., & Sarkar, R. (2023). Multi-Level Stress Detection using Ensemble Filter-based Feature Selection Method. In M. Mahmud, C. Mendoza-Barrera, M. S. Kaiser, A. Bandyopadhyay, K. Ray, & E. Lugo (Eds.), Proceedings of Trends in Electronics and Health Informatics - TEHI 2022 (pp. 161-173). (Lecture Notes in Networks and Systems; Vol. 675 LNNS). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-981-99-1916-1_13

Reza, Arham ; Singh, Pawan Kumar ; Mahmud, Mufti et al. / Multi-Level Stress Detection using Ensemble Filter-based Feature Selection Method. Proceedings of Trends in Electronics and Health Informatics - TEHI 2022. editor / Mufti Mahmud ; Claudia Mendoza-Barrera ; M. Shamim Kaiser ; Anirban Bandyopadhyay ; Kanad Ray ; Eduardo Lugo. Springer Science and Business Media Deutschland GmbH, 2023. pp. 161-173 (Lecture Notes in Networks and Systems).

@inproceedings{4e62add04d62488f824152ab59179e1c,

title = "Multi-Level Stress Detection using Ensemble Filter-based Feature Selection Method",

abstract = "Stress has become one of the major concerns in modern human life, especially after the outbreak of the COVID-19 pandemic, and it has had a great impact on human daily life activities. Detecting stress from physiological signals at an early stage is crucial as it prevents it from outgrowing severe health issues. Most researchers interested in stress detection have focused on developing new feature extraction methods. In this paper, at first, we have extracted some common statistical features from raw data. Then to remove redundant features, we have proposed an ensemble of filter-based feature selection methods for stress detection. Two filter methods, namely, Mutual Information and Pearson Correlation Coefficient are used to obtain the rank of the features. Based on the selected features, three popular classification models, namely, Decision Tree, Random Forest, and K-nearest neighbors are used for the detection of four stress classes—baseline, stress, amusement, and meditation). The proposed method has been applied to the publicly available standard WESAD dataset which consists of various physiological signals taken from both chest and wrist. We have achieved classification accuracies of 99.9\% and 96.8\% for subject-dependent and subject-independent cases, respectively.",

keywords = "Ensemble learning, Feature selection, Filter method, Stress detection, WESAD dataset",

author = "Arham Reza and Singh, \{Pawan Kumar\} and Mufti Mahmud and Brown, \{David J.\} and Ram Sarkar",

note = "Publisher Copyright: {\textcopyright} 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.; 2nd International Conference on Trends in Electronics and Health Informatics, TEHI 2022 ; Conference date: 07-12-2022 Through 09-12-2022",

year = "2023",

doi = "10.1007/978-981-99-1916-1\_13",

language = "English",

isbn = "9789819919154",

series = "Lecture Notes in Networks and Systems",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "161--173",

editor = "Mufti Mahmud and Claudia Mendoza-Barrera and Kaiser, \{M. Shamim\} and Anirban Bandyopadhyay and Kanad Ray and Eduardo Lugo",

booktitle = "Proceedings of Trends in Electronics and Health Informatics - TEHI 2022",

address = "Germany",

}

Reza, A, Singh, PK, Mahmud, M, Brown, DJ & Sarkar, R 2023, Multi-Level Stress Detection using Ensemble Filter-based Feature Selection Method. in M Mahmud, C Mendoza-Barrera, MS Kaiser, A Bandyopadhyay, K Ray & E Lugo (eds), Proceedings of Trends in Electronics and Health Informatics - TEHI 2022. Lecture Notes in Networks and Systems, vol. 675 LNNS, Springer Science and Business Media Deutschland GmbH, pp. 161-173, 2nd International Conference on Trends in Electronics and Health Informatics, TEHI 2022, Puebla, Mexico, 7/12/22. https://doi.org/10.1007/978-981-99-1916-1_13

Multi-Level Stress Detection using Ensemble Filter-based Feature Selection Method. / Reza, Arham; Singh, Pawan Kumar; Mahmud, Mufti et al.
Proceedings of Trends in Electronics and Health Informatics - TEHI 2022. ed. / Mufti Mahmud; Claudia Mendoza-Barrera; M. Shamim Kaiser; Anirban Bandyopadhyay; Kanad Ray; Eduardo Lugo. Springer Science and Business Media Deutschland GmbH, 2023. p. 161-173 (Lecture Notes in Networks and Systems; Vol. 675 LNNS).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Multi-Level Stress Detection using Ensemble Filter-based Feature Selection Method

AU - Reza, Arham

AU - Singh, Pawan Kumar

AU - Mahmud, Mufti

AU - Brown, David J.

AU - Sarkar, Ram

PY - 2023

Y1 - 2023

N2 - Stress has become one of the major concerns in modern human life, especially after the outbreak of the COVID-19 pandemic, and it has had a great impact on human daily life activities. Detecting stress from physiological signals at an early stage is crucial as it prevents it from outgrowing severe health issues. Most researchers interested in stress detection have focused on developing new feature extraction methods. In this paper, at first, we have extracted some common statistical features from raw data. Then to remove redundant features, we have proposed an ensemble of filter-based feature selection methods for stress detection. Two filter methods, namely, Mutual Information and Pearson Correlation Coefficient are used to obtain the rank of the features. Based on the selected features, three popular classification models, namely, Decision Tree, Random Forest, and K-nearest neighbors are used for the detection of four stress classes—baseline, stress, amusement, and meditation). The proposed method has been applied to the publicly available standard WESAD dataset which consists of various physiological signals taken from both chest and wrist. We have achieved classification accuracies of 99.9% and 96.8% for subject-dependent and subject-independent cases, respectively.

AB - Stress has become one of the major concerns in modern human life, especially after the outbreak of the COVID-19 pandemic, and it has had a great impact on human daily life activities. Detecting stress from physiological signals at an early stage is crucial as it prevents it from outgrowing severe health issues. Most researchers interested in stress detection have focused on developing new feature extraction methods. In this paper, at first, we have extracted some common statistical features from raw data. Then to remove redundant features, we have proposed an ensemble of filter-based feature selection methods for stress detection. Two filter methods, namely, Mutual Information and Pearson Correlation Coefficient are used to obtain the rank of the features. Based on the selected features, three popular classification models, namely, Decision Tree, Random Forest, and K-nearest neighbors are used for the detection of four stress classes—baseline, stress, amusement, and meditation). The proposed method has been applied to the publicly available standard WESAD dataset which consists of various physiological signals taken from both chest and wrist. We have achieved classification accuracies of 99.9% and 96.8% for subject-dependent and subject-independent cases, respectively.

KW - Ensemble learning

KW - Feature selection

KW - Filter method

KW - Stress detection

KW - WESAD dataset

UR - https://www.scopus.com/pages/publications/85164911207

U2 - 10.1007/978-981-99-1916-1_13

DO - 10.1007/978-981-99-1916-1_13

M3 - Conference contribution

AN - SCOPUS:85164911207

SN - 9789819919154

T3 - Lecture Notes in Networks and Systems

SP - 161

EP - 173

BT - Proceedings of Trends in Electronics and Health Informatics - TEHI 2022

A2 - Mahmud, Mufti

A2 - Mendoza-Barrera, Claudia

A2 - Kaiser, M. Shamim

A2 - Bandyopadhyay, Anirban

A2 - Ray, Kanad

A2 - Lugo, Eduardo

PB - Springer Science and Business Media Deutschland GmbH

T2 - 2nd International Conference on Trends in Electronics and Health Informatics, TEHI 2022

Y2 - 7 December 2022 through 9 December 2022

ER -

Reza A, Singh PK, Mahmud M, Brown DJ, Sarkar R. Multi-Level Stress Detection using Ensemble Filter-based Feature Selection Method. In Mahmud M, Mendoza-Barrera C, Kaiser MS, Bandyopadhyay A, Ray K, Lugo E, editors, Proceedings of Trends in Electronics and Health Informatics - TEHI 2022. Springer Science and Business Media Deutschland GmbH. 2023. p. 161-173. (Lecture Notes in Networks and Systems). doi: 10.1007/978-981-99-1916-1_13

Multi-Level Stress Detection using Ensemble Filter-based Feature Selection Method

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this