GSR Analysis for Stress: Development and Validation of an Open Source Tool for Noisy Naturalistic GSR Data

Author(s): Aqajari, Seyed Amir Hossein; Naeini, Emad Kasaeyan; Mehrabadi, Milad Asgari; Labbaf, Sina; Rahmani, Amir M; Dutt, Nikil | Abstract: The stress detection problem is receiving great attention in related research communities. This is due to its essential part in behavioral studies for many serious health problems and physical illnesses. There are different methods and algorithms for stress detection using different physiological signals. Previous studies have already shown that Galvanic Skin Response (GSR), also known as Electrodermal Activity (EDA), is one of the leading indicators for stress. However, the GSR signal itself is not trivial to analyze. Different features are extracted from GSR signals to detect stress in people like the number of peaks, max peak amplitude, etc. In this paper, we are proposing an open-source tool for GSR analysis, which uses deep learning algorithms alongside statistical algorithms to extract GSR features for stress detection. Then we use different machine learning algorithms and Wearable Stress and Affect Detection (WESAD) dataset to evaluate our results. The results show that we are capable of detecting stress with the accuracy of 92 percent using 10-fold cross-validation and using the features extracted from our tool.

[1]  Giulio Gabrieli,et al.  PySiology: A Python Package for Physiological Feature Extraction , 2020, Neural Approaches to Dynamics of Signal Exchanges.

[2]  Thierry Pun,et al.  Toolbox for Emotional feAture extraction from Physiological signals (TEAP) , 2017, Front. ICT.

[3]  Luca Citi,et al.  cvxEDA: A Convex Optimization Approach to Electrodermal Activity Processing , 2016, IEEE Transactions on Biomedical Engineering.

[4]  N. Altman.  An Introduction to Kernel and Nearest-Neighbor Nonparametric Regression , 1992 .

[5]  Yuan Yu,et al.  TensorFlow: A system for large-scale machine learning , 2016, OSDI.

[6]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[7]  Yoshua Bengio,et al.  Convolutional networks for images, speech, and time series , 1998 .

[8]  Fernando Seoane,et al.  Wearable Biomedical Measurement Systems for Assessment of Mental Stress of Combatants in Real Time , 2014, Sensors.

[9]  Kristof Van Laerhoven,et al.  Introducing WESAD, a Multimodal Dataset for Wearable Stress and Affect Detection , 2018, ICMI.

[10]  D. Hand,et al.  Idiot's Bayes—Not So Stupid After All? , 2001 .

[11]  Sergi Bermúdez i Badia,et al.  PhysioLab - a multivariate physiological computing toolbox for ECG, EMG and EDA signals: a case of study of cardiorespiratory fitness assessment in the elderly population , 2017, Multimedia Tools and Applications.

[12]  Andrea Kleinsmith,et al.  Public Speaking Anxiety in a Real Classroom: Towards Developing a Reflection System , 2019, CHI Extended Abstracts.

[13]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[14]  Boreom Lee,et al.  Detection of Stress Levels from Biosignals Measured in Virtual Reality Environments Using a Kernel-Based Extreme Learning Machine , 2017, Sensors.

[15]  Sazali Yaacob,et al.  Multiple Physiological Signal-Based Human Stress Identification Using Non-Linear Classifiers , 2013 .

[16]  Frank H Wilhelm,et al.  ANSLAB: Integrated multichannel peripheral biosignal processing in psychophysiological science , 2016, Behavior research methods.

[17]  Ron Kohavi,et al.  A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection , 1995, IJCAI.

[18]  F. Braceland.  THE STRESS OF LIFE , 1976 .