Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
January 1, 2024IEEE AccessOpen Access

Optimization of Wearable Biosensor Data for Stress Classification Using Machine Learning and Explainable AI

View Full Paper
Ask AI
Bookmark
Share

Population

Subjects undergoing the Montreal Imaging Stress Task (MIST) in an academic environment

Design

Other

Authors

SSShikha ShikhaDSDivyashikha SethiaSIS. Indu

Discussion

Loading...

Member takes

Overview

Wearable biosignal classification may flag academic stress in real time but should not yet change practice; leaves open meditation audio's real-world benefit.

Structured PICO

P
Population
Subjects undergoing the Montreal Imaging Stress Task (MIST) in an academic environment
I
Intervention
Wearable biosensor data collection (HRV, BVP, EDA) combined with machine learning (Gradient Boosting) and meditation audio
O
Outcome
Stress classification accuracy (2-level and 3-level)

Wearable biosensor data combined with machine learning can accurately classify stress levels, with HRV and EDA being the most significant features.

Cite This Study

Shikha et al. (2024) studied this question.

synapsesocial.com/papers/6a800a88fcb29c286731bb9fhttps://doi.org/10.1109/access.2024.3463742
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 4 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1AIPs-SnTCN: Predicting Anti-Inflammatory Peptides Using fastText and Transformer Encoder-Based Hybrid Word Embedding with Self-Normalized Temporal Convolutional Networks2023 · 114 citations
  2. 2Wearable electroencephalography and multi-modal mental state classification: A systematic literature review2022 · 28 citations
  3. 3Using mutual information for selecting features in supervised neural net learning1994 · 2,630 citations
  4. 4Dimensionality reduction using genetic algorithms2000 · 842 citations