Machine learning-based stress classification system using wearable sensor devices - IAES International Journal of Artificial Intelligence

Aug 5, 2026

Upload by Levi

University students often face persistently high stress in competitive academic environments, and unmonitored stress can lead to serious physiological health risks. The presented work builds a stress classification framework using wearable sensor devices to predict mental stress levels for undergraduate engineering students. Data from 23 students are collected using EEG, EDA, skin temperature, and heart rate during the Montreal Imaging Stress Task. Machine learning models classify stress into rest, moderate, and high, reaching 99.98% accuracy with EEG time-frequency features and 99.51% with EDA, HR, and SKT.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages11

Reading Time28 min

AccessFree to download

Introduction

Stress, risk, and limitations of questionnaires

Physiological signals and wearable sensors

Data collection and experimental setup

IAES International Journal of Artificial Intelligence (IJ-AI) Vol. 13, No. 1, March 2024, pp. 337∼347 ISSN: 2252-8938, DOI: 10.11591/ijai.v13.i1.pp337-347 ❒ 337 | Machine learning-based stress classification system using
wearable sensor devices
Varun Chandra, Divyashikha Sethia
Department of Software Engineering, Delhi Technological University, New Delhi, India | | | | --- | --- | --- | | Article Info
Article history:
Received Aug 6, 2022 Revised Feb 13, 2023 Accepted Mar 10, 2023
Keywords:
Electrodermal activity Electroencephalogram Heart rate
K-nearest neighbors Montreal imaging stress task Random forest
Skin temperature Stress | | ABSTRACT
University students often become victims of high-stress levels due to the highly competitive work environment. Unmonitored stress levels in students can inflict severe physiological health problems. This work aims to build a stress classification framework using wearable sensor devices to predict mental stress levels for undergraduate engineering students. It comprises a study to collect a data set of 23 university students using wearable devices for four physiological signals, i.e., electroencephalogram (EEG), electrodermal activity (EDA), skin temperature (SKT), and heart rate (HR), when the students perform the montreal imaging stress task (MIST) for the mental workload. The machine learning models proposed in this work help classify stress into three levels: rest, moderate, and high. The models achieve a classification accuracy of 99.98% using the EEG signals’time-frequency domain features and an accuracy of 99.51% using the EDA, HR, and SKT signals. The proposed models achieve better scores than all the previous studies on stress classification, using EEG signals and EDA, HR, and SKT signals. This study is novel since it also demonstrates the applicability and proficiency of wearable sensor devices in developing accurate stress classification models to help build real-time stress monitoring systems.
This is an open access article under the CC BY-SA license. | | Corresponding Author: | | | | Divyashikha Sethia
Department of Software Engineering, Delhi Technological University Bawana Rd, Rohini, New Delhi, Delhi 110042, India
Email: [sethiadivya@gmail.com](sethiadivya@gmail.com) | | | 1. INTRODUCTION Stress occurs due to a person’s inability to handle his mental and emotional states during a challenging situation. It is described by Hans Selye as ”an unspecific response of a human body to the demand of task” [1] . There are two categorizations of stress, namely short-term and long-term stress. Cohen et al. [2] concluded that there is a direct association between long-term psychological stress and diseases like depression, human immunodeficiency virus (HIV) / acquired immune deficiency syndrome (AIDS), and cardiovascular diseases. High stress can also cause chronic illnesses such as stroke and diabetes. Tasks involving a high mental workload can induce stress, especially for academic and placement assessments of students. People in academia are constantly engaged in such tasks. Students in universities and schools face many mentally demanding and challenging situations, like examinations, peer pressure, teachers, and job interviews. In such a socially competitive and mentally exhausting environment, it is often the case that students become the victims of stress and its associated health risks. Nandi et al. [3] surveyed university medical students and found 53% of the students who participated in the study were stressed, and there were significant effects on the mental and social well-being of these participants. Behere et al. [4] proposed a study that involved a questionnaire-based survey of 100 random students. The study found that medical and engineering students had high-stress levels requiring immediate medical attention. It also concluded that students not attending to their high-stress levels could cause severe mental and

FAQs

Why is stress monitoring important for university students in this study?

The study explains that competitive environments can cause high stress, and unmonitored stress may result in severe physiological health problems.

Which wearable physiological signals are used for stress classification?

The framework uses EEG, electrodermal activity (EDA), skin temperature (SKT), and heart rate (HR) collected from wearable devices.

How many stress levels does the system classify, and what accuracy is reported?

The models classify stress into three levels: rest, moderate, and high, achieving 99.98% accuracy with EEG features and 99.51% accuracy using EDA, HR, and SKT.

Aug 5, 2026

Upload by Levi