Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
May 19, 2020Applied SciencesOpen Access

Emotion Recognition Using Convolutional Neural Network with Selected Statistical Photoplethysmogram Features

View Full Paper
Ask AI
Bookmark
Share

Why the study?

PPG signals are easier to obtain than other physiological signals, motivating an efficient method to recognize emotion using fused deep CNN features and selected statistical PPG features.

Population

Database for Emotion Analysis using Physiological signals (DEAP)

Authors

MLMin Seop LeeKorea UniversityYLYun Kyu LeeDaegu Haany UniversityMLMyo Taeg LimKorea University

Discussion

Loading...

Member takes

Overview

May enable wearable emotion monitoring via PPG; leaves open validation in cardiovascular populations.

Structured PICO

P
Population
Database for Emotion Analysis using Physiological signals (DEAP)
I
Intervention
Method fusing deep features extracted by two deep convolutional neural networks and statistical features selected by Pearson's correlation technique from photoplethysmogram (PPG) signals
O
Outcome
Classification of valence and arousal (basic parameters of emotion)

A proposed CNN-based method using PPG features achieved noticeable performance for emotion recognition.

Cite This Study

Lee et al. (2020) studied this question.

synapsesocial.com/papers/6a71837ee5469ee92be20290https://doi.org/10.3390/app10103501
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. 1Estimating vital signs remotely using adaptive facial regions for photoplethysmography2023
  2. 2Remote PPG vital sign Estimation with adaptive facial regions2023
  3. 3Optimized Deep Learning Framework for Emotion Recognition Using Multimodal Physiological Signals and Temporal Convolutional Networks2026
  4. 4An emotion recognition method based on frequency-domain features of PPG2025 · 7 citations
  5. 5Emotion Recognition from Electroencephalogram Signals based on Deep Neural Networks2023