Related Experiment Video
Updated: Sep 16, 2025

12:51
Evaluation of Commercial-Off-The-Shelf Wrist Wearables to Estimate Stress on Students
Published on: June 16, 2018
7.6K
Visualizing Relaxation in Wearables: Multi-Domain Feature Fusion of HRV Using Fuzzy Recurrence Plots
Puneet Arya1, Mandeep Singh1, Mandeep Singh1
1Department of Electrical and Instrumentation Engineering, Thapar Institute of Engineering and Technology, Patiala 147004, India.
Sensors (Basel, Switzerland)
|July 12, 2025
Summary
This study introduces fuzzy recurrence plots (FRPs) to visualize heart rate variability (HRV) for objective relaxation monitoring. This visual method, combined with machine learning, accurately detects autonomic changes, aiding biofeedback systems.
Area of Science:
- Physiological monitoring
- Biomedical signal processing
- Wearable technology
Background:
- Traditional relaxation monitoring relies on subjective self-assessment.
- Electrocardiograms (ECG) offer limited one-dimensional insights into cardiovascular activity.
- Objective physiological monitoring is crucial for effective biofeedback and stress management.
Purpose of the Study:
- To introduce a novel visual interpretation framework for heart rate variability (HRV) time series using fuzzy recurrence plots (FRPs).
- To develop a multi-domain feature fusion framework for automated detection of autonomic changes from HRV data, suitable for wearable systems.
- To evaluate the performance of the proposed framework in distinguishing between different relaxation states.
Main Methods:
- Transformed HRV time series data into two-dimensional fuzzy recurrence plots (FRPs).
- Extracted features from five domains: time, frequency, non-linear, geometric, and image-based.
- Employed feature selection techniques (Fisher discriminant ratio, correlation filtering, greedy search) and evaluated six classifiers, with Support Vector Machine (SVM) showing the highest performance.
Main Results:
- Fuzzy recurrence plots (FRPs) provide visually distinct patterns corresponding to autonomic changes, aiding non-expert interpretation.
- The multi-domain feature fusion framework achieved 96.6% accuracy and 100% specificity using only three selected features with an SVM classifier.
- The proposed approach demonstrates high efficacy in objectively monitoring real-time stress levels.
Conclusions:
- Fuzzy recurrence plots (FRPs) offer a promising, human-interpretable method for visualizing physiological changes related to relaxation.
- The automated detection framework using feature fusion and SVM provides accurate and efficient objective monitoring of autonomic status.
- This approach holds significant potential for developing advanced biofeedback systems integrated into wearable devices for real-time stress management.
Related Concept Videos
Relaxation of Skeletal Muscles
3.8K
The period of muscle contraction primarily influences the duration of stimulation at the neuromuscular junction (NMJ), the presence of free calcium ions in the sarcoplasm, and the availability of energy or ATP to support contractions.
When an action potential reaches the axon terminal, it depolarizes the membrane and opens voltage-gated sodium channels. Sodium ions enter the cell, further depolarizing the presynaptic membrane. This depolarization causes voltage-gated calcium channels to open....
When an action potential reaches the axon terminal, it depolarizes the membrane and opens voltage-gated sodium channels. Sodium ions enter the cell, further depolarizing the presynaptic membrane. This depolarization causes voltage-gated calcium channels to open....
3.8K
Residual Plots
5.1K
A residual plot is a statistical representation of data used to analyze correlation and regression results. It helps verify the requirements for drawing specific conclusions about correlation and regression. To obtain the residual plot, first, the residual for each data value is calculated, which is simply the vertical distance between the observed and the predicted value obtained from the regression equation.
When the residual values are plotted against the variable x, it is called a residual...
When the residual values are plotted against the variable x, it is called a residual...
5.1K

