Improving quality of life through brain-computer interfaces - an integrated stress prediction method using machine learning

Aug 5, 2026

People face stress driven by modern living demands, making it a global risk that undermines well-being. Effective support depends on understanding individual differences in stress resilience and enabling timely, personalized intervention. This study develops an integrated stress prediction framework using machine learning and combined physiological signals (EEG, blood pressure, heart rate) with psychological measures (perceived stress scale). Experiments classify stressed versus non-stressed individuals using KNN, random forest, and k-SVM, achieving 98.27% accuracy with random forest.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages13

Reading Time33 min

AccessFree to download

Introduction

Stress as a global health concern

Stress prediction using physiological and psychological parameters

Role of brain-computer interfaces and machine learning

Indonesian Journal of Electrical Engineering and Computer Science Vol. 36, No. 2, November 2024, pp. 1030~ 1042 ISSN: 2502-4752, DOI: 10. 11591/ijeecs.v36 . i2 .pp1030-1042 􀂈 1030 | Improving quality of life through brain-computer interfaces: an integrated stress prediction method using machine learning
Shrivatsa D. Perur, Harish H. Kenchannavar
Department of Information Science and Engineering, KLS Gogte Institute of Technology, Visvesvaraya Technological University,
Belagavi, India | | | --- | --- | | Article Info
Article history:
Received May 7, 2024 Revised Jul 3, 2024 Accepted Jul 14, 2024
Keywords:
Intelligent computing Machine learning algorithms Personalized intervention Prediction of stress level Psychological and physiological parameters
Corresponding Author: | ABSTRACT
In recent days, people must deal with stress brought on by the demands of modern living, which constantly presents new obstacles. Stress, a state of mental tension triggered by challenging circumstances, has become a global risk factor impacting individual well-being. Understanding variations in stress resilience is crucial for tailoring treatment strategies. Previous studies have explored stress prediction using measures like electroencephalography (EEG), blood pressure (BP), heart rate (HR), and interventions such as Kriya Yoga and mindfulness meditation. The experimentation is done on the data collected from people who practice heartfulness meditation regularly. The research employs machine learning (ML) algorithms alongside physiological parameters such as EEG, BP, HR, and psychological parameters, perceived stress scale (PSS), to precisely classify, measure, and predict stress levels. The investigations are done using K-nearest neighbor (KNN), random forest (RF), and kernel-support vector machine (k-SVM) . An accuracy of 98.27% accuracy was achieved with the RF algorithm in classifying stressed and non-stressed individuals.
This is an open access article under the CC BY-SA license.
| | Harish H. Kenchannavar
Department of Information Science and Engineering, KLS Gogte Institute of Technology Visvesvaraya Technological University
Belagavi-590018, Karnataka, India
[Email: perur35@gmail.com](Email: perur35@gmail.com) | | 1. INTRODUCTION In recent days, human beings have suffered from stress for many reasons such as financial stability, and work pressure, family responsibility. The growing prevalence of mental health disorders and the need for advanced technologies to assist in early detection and management. Mental health issues related to stress disorders have become a significant global concern affecting millions of individuals worldwide. As depicted in Figure 1, 34% of people across the world feel that they are stressed, and 31% of people feel stressed as they cannot deal with things [1] . Like the global scenario, in India also the fast-paced modern lifestyle, high work demands, academic pressures, and competitive environments often contribute to elevated stress levels among individuals. Additionally, factors such as socioeconomic challenges, urbanization, and digitalization have added complexity to the stress landscape in India. Stress is characterized as a condition of anxiety or mental tension brought on by a challenging circumstance. Stress is a normal human reaction that motivates us to deal with problems and dangers in our lives. Everyone goes through periods of stress [2] . As a complex relationship of physiological, cognitive, and emotional responses to external pressures, stress poses significant challenges to both individual well-being and public health systems [3] . Predicting stress levels in individuals is crucial for early intervention and prevention of stress-related health issues like anxiety, depression, and cardiovascular diseases. Identifying stress using various parameters involves assessing physiological, behavioral, and psychological indicators. Physiological paramete

FAQs

Why is stress prediction important in this research?

Predicting stress enables early intervention to prevent stress-related problems such as anxiety, depression, and cardiovascular diseases, improving well-being and resilience.

What inputs are used to predict stress levels?

The method uses physiological parameters (EEG, blood pressure, heart rate) and psychological parameters including the perceived stress scale (PSS).

Which machine learning model achieved the best performance and what was the accuracy?

Random forest achieved the highest reported accuracy, reaching 98.27% for classifying stressed and non-stressed individuals.

Aug 5, 2026

Upload by Theodore