Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
February 25, 2025Frontiers in PhysiologyOpen Access

An emotion recognition method based on frequency-domain features of PPG

View Full Paper
Ask AI
Bookmark
Share

Key result

Novel PPG frequency-domain method achieves ~88% accuracy for arousal emotion recognition.

  • n=157

Why the study?

This study aimed to use physiological model simulation to analyze frequency-domain components of PPG signals, extract key features, and evaluate their efficacy in distinguishing emotional states.

Comparison

PPG frequency-domain features vs PRV and morphological features

Design

Physiological modeling and validation study

Authors

ZZZhibin ZhuZhejiang UniversityXWXuanyi WangZhejiang University of TechnologyYXYifei XuHarbin Institute of Technology

Discussion

Loading...

Member takes

Overview

May enable wearable emotion monitoring in cardiac patients; hypothesis-generating pending clinical validation.

Study Design

Type

Observational (n=157)

Multicenter

No

Structured PICO

P
Population
157 university students (96 females, 61 males) with normal vision, hearing, and perception abilities, free from any physical or psychological conditions that could potentially influence emotional responses.
I
Intervention
Emotion recognition method using frequency-domain features of photoplethysmography (PPG) signals, analyzed via a dual windkessel model and classified using Support Vector Machines (SVM).
C
Comparator
Emotion recognition using pulse rate variability (PRV) features and PPG morphological features.
O
Outcome
Classification accuracy of emotional states (arousal and valence).

Frequency-domain features of PPG signals analyzed via physiological modeling can effectively distinguish emotional states, achieving high classification accuracy.

Limitations

  • The study primarily demonstrates strong associations rather than establishing precise quantitative correlations.
  • The selection of emotional elicitation materials presents inherent challenges, as material-specific characteristics can influence extracted features.
  • The duration of stimulus materials significantly impacts feature selection and interpretation.
  • The research primarily focused on feature analysis and interpretation, with relatively less emphasis on optimization for classification accuracy.

Cite This Study

Zhu et al. (2025) conducted an observational in Healthy (Emotion Recognition) (n=157). PPG frequency-domain features vs. PRV and morphological features was evaluated on Emotion classification accuracy for arousal. A novel emotion recognition method based on PPG frequency-domain features achieved classification accuracies of 87.5% for arousal and 81.4% for valence.

synapsesocial.com/papers/6a16fd84c23c548e2a7bad1ahttps://doi.org/10.3389/fphys.2025.1486763
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1A Comprehensive Evaluation of Features and Simple Machine Learning Algorithms for Electroencephalographic-Based Emotion Recognition2024 · 12 citations
  2. 2PPG-BASED AUTOMATED ESTIMATION OF BLOOD PRESSURE USING PATIENT-SPECIFIC NEURAL NETWORK MODELING2020 · 12 citations
  3. 3Interactions Between Autonomic Nervous System Activity and Endothelial Function: A Model for the Development of Cardiovascular Disease2004 · 181 citations
  4. 4Autonomic and endocrine control of cardiovascular function2015 · 727 citations
  5. 5Fast Emotion Recognition Based on Single Pulse PPG Signal with Convolutional Neural Network2019 · 110 citations