Comparative Analysis of Electrodermal Activity Decomposition Methods in Emotion Detection Using Machine Learning

Ganapathy, Nagarajan (2023) Comparative Analysis of Electrodermal Activity Decomposition Methods in Emotion Detection Using Machine Learning. In: 33rd Medical Informatics Europe Conference: Caring is Sharing - Exploiting the Value in Data for Health and Innovation, MIE2023, 22 May 2023 to 25 May 2023, Gothenburg.

Text
SHTI-302-SHTI230067.pdf - Published Version
Download (594kB)

Abstract

Electrodermal activity (EDA) reflects sympathetic nervous system activity through sweating-related changes in skin conductance. Decomposition analysis is used to deconvolve the EDA into slow and fast varying tonic and phasic activity, respectively. In this study, we used machine learning models to compare the performance of two EDA decomposition algorithms to detect emotions such as amusing, boring, relaxing, and scary. The EDA data considered in this study were obtained from the publicly available Continuously Annotated Signals of Emotion (CASE) dataset. Initially, we pre-processed and deconvolved the EDA data into tonic and phasic components using decomposition methods such as cvxEDA and BayesianEDA. Further, 12 time-domain features were extracted from the phasic component of EDA data. Finally, we applied machine learning algorithms such as logistic regression (LR) and support vector machine (SVM), to evaluate the performance of the decomposition method. Our results imply that the BayesianEDA decomposition method outperforms the cvxEDA.

[error in script]

IITH Creators:

IITH Creators	ORCiD
Ganapathy, Nagarajan	http://www.orcid.org/0000-0002-3743-5388

Item Type:

Conference or Workshop Item (Paper)

Uncontrolled Keywords:

Deconvolution; Electrodermal activity; Emotion detection; Machine learning; Time-domain features; Algorithms; Emotions; Fear; Galvanic Skin Response; Machine Learning; Support Vector Machine; Diagnosis; Electrodes; Emotion Recognition; Learning algorithms; Learning systems; Medical informatics; Time domain analysis; Comparative analyzes; Decomposition methods; Deconvolutions; Electrodermal activity; Emotion detection; Machine-learning; Performance; Support vectors machine; Sympathetic nervous systems; Time domain features; classifier; conference paper; controlled study; decomposition; deconvolution; diagnostic test accuracy study; early diagnosis; emotion; human; human experiment; machine learning; sensitivity and specificity; statistical significance; support vector machine; algorithm; electrodermal response; fear; machine learning; support vector machine;

Subjects:

Biomedical Engineering
Biomedical Engineering > Biosensors

Divisions:

Department of Biomedical Engineering

Depositing User:

Mr Nigam Prasad Bisoyi

Date Deposited:

26 Sep 2023 05:17

Last Modified:

26 Sep 2023 05:17

URI:

http://raiithold.iith.ac.in/id/eprint/11693