Home > Research > Publications & Outputs > Application Level Performance Evaluation of Wea...

Electronic data

Links

Text available via DOI:

View graph of relations

Application Level Performance Evaluation of Wearable Devices for Stress Classification with Explainable AI

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Published

Standard

Application Level Performance Evaluation of Wearable Devices for Stress Classification with Explainable AI. / Chalabianloo, Niaz; Can, Yekta Said ; Umair, Muhammad et al.
In: Pervasive and Mobile Computing, Vol. 87, 101703, 31.12.2022.

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Harvard

APA

Vancouver

Chalabianloo N, Can YS, Umair M, Sas C, Ersoy C. Application Level Performance Evaluation of Wearable Devices for Stress Classification with Explainable AI. Pervasive and Mobile Computing. 2022 Dec 31;87:101703. Epub 2022 Oct 31. doi: 10.1016/j.pmcj.2022.101703

Author

Bibtex

@article{fc77d8cbd9a047f98cd2bc2d2e82fab3,
title = "Application Level Performance Evaluation of Wearable Devices for Stress Classification with Explainable AI",
abstract = "Stress has become one of the most prominent problems of modern societies and a key contributor to major health issues. Dealing with stress effectively requires detecting it in real-time, informing the user, and giving instructions on how to manage it. Over the past few years, wearable devices equipped with biosensors that can be utilized for stress detection have become increasingly popular. Since they come with various designs and technologies and acquire biosignals from different body locations, choosing a suitable device for a particular application has become a challenge for researchers and end-users. This study compares seven common wearable biosensors for stress detection applications. This was accomplished by collecting physiological sensor data during Baseline, Stress, Recovery, and Cycling sessions from 32 participants. Machine learning algorithms were used to classify four stress classes, and the results obtained from all wearables were compared. Following this, a state-of-the-art explainable artificial intelligence method was employed to clarify our models{\textquoteright} predictions and investigate the influence different features have on the models{\textquoteright} outputs. Despite the results showing that ECG wearables perform slightly better than the rest of the devices, adding a second biosignal (EDA) improved the results significantly, tipping the balance toward multisensor wearables. Finally, we concluded that although the output results of each model can be affected by various factors, in most cases, there is no significant difference in the accuracy of stress detection by different wearables. However, the decision to select a particular wearable for stress detection applications must be made carefully considering the trade-off between the users{\textquoteright} expectations and preferences and the pros and cons of each device.",
keywords = "HRV, EDA, XAI, Stress, Detection, Wearable Sensors, Affective Computing",
author = "Niaz Chalabianloo and Can, {Yekta Said} and Muhammad Umair and Corina Sas and Cem Ersoy",
year = "2022",
month = dec,
day = "31",
doi = "10.1016/j.pmcj.2022.101703",
language = "English",
volume = "87",
journal = "Pervasive and Mobile Computing",
issn = "1574-1192",
publisher = "Elsevier Science B.V.",

}

RIS

TY - JOUR

T1 - Application Level Performance Evaluation of Wearable Devices for Stress Classification with Explainable AI

AU - Chalabianloo, Niaz

AU - Can, Yekta Said

AU - Umair, Muhammad

AU - Sas, Corina

AU - Ersoy, Cem

PY - 2022/12/31

Y1 - 2022/12/31

N2 - Stress has become one of the most prominent problems of modern societies and a key contributor to major health issues. Dealing with stress effectively requires detecting it in real-time, informing the user, and giving instructions on how to manage it. Over the past few years, wearable devices equipped with biosensors that can be utilized for stress detection have become increasingly popular. Since they come with various designs and technologies and acquire biosignals from different body locations, choosing a suitable device for a particular application has become a challenge for researchers and end-users. This study compares seven common wearable biosensors for stress detection applications. This was accomplished by collecting physiological sensor data during Baseline, Stress, Recovery, and Cycling sessions from 32 participants. Machine learning algorithms were used to classify four stress classes, and the results obtained from all wearables were compared. Following this, a state-of-the-art explainable artificial intelligence method was employed to clarify our models’ predictions and investigate the influence different features have on the models’ outputs. Despite the results showing that ECG wearables perform slightly better than the rest of the devices, adding a second biosignal (EDA) improved the results significantly, tipping the balance toward multisensor wearables. Finally, we concluded that although the output results of each model can be affected by various factors, in most cases, there is no significant difference in the accuracy of stress detection by different wearables. However, the decision to select a particular wearable for stress detection applications must be made carefully considering the trade-off between the users’ expectations and preferences and the pros and cons of each device.

AB - Stress has become one of the most prominent problems of modern societies and a key contributor to major health issues. Dealing with stress effectively requires detecting it in real-time, informing the user, and giving instructions on how to manage it. Over the past few years, wearable devices equipped with biosensors that can be utilized for stress detection have become increasingly popular. Since they come with various designs and technologies and acquire biosignals from different body locations, choosing a suitable device for a particular application has become a challenge for researchers and end-users. This study compares seven common wearable biosensors for stress detection applications. This was accomplished by collecting physiological sensor data during Baseline, Stress, Recovery, and Cycling sessions from 32 participants. Machine learning algorithms were used to classify four stress classes, and the results obtained from all wearables were compared. Following this, a state-of-the-art explainable artificial intelligence method was employed to clarify our models’ predictions and investigate the influence different features have on the models’ outputs. Despite the results showing that ECG wearables perform slightly better than the rest of the devices, adding a second biosignal (EDA) improved the results significantly, tipping the balance toward multisensor wearables. Finally, we concluded that although the output results of each model can be affected by various factors, in most cases, there is no significant difference in the accuracy of stress detection by different wearables. However, the decision to select a particular wearable for stress detection applications must be made carefully considering the trade-off between the users’ expectations and preferences and the pros and cons of each device.

KW - HRV

KW - EDA

KW - XAI

KW - Stress

KW - Detection

KW - Wearable Sensors

KW - Affective Computing

U2 - 10.1016/j.pmcj.2022.101703

DO - 10.1016/j.pmcj.2022.101703

M3 - Journal article

VL - 87

JO - Pervasive and Mobile Computing

JF - Pervasive and Mobile Computing

SN - 1574-1192

M1 - 101703

ER -