Fast emotion recognition based on single pulse PPG signal with convolutional neural network

Min Seop Lee, Yun Kyu Lee, Dong Sung Pae, Myo Taeg Lim, Dong Won Kim, Tae Koo Kang

Research output: Contribution to journalArticle

Abstract

Physiological signals contain considerable information regarding emotions. This paper investigated the ability of photoplethysmogram (PPG) signals to recognize emotion, adopting a two-dimensional emotion model based on valence and arousal to represent human feelings. The main purpose was to recognize short term emotion using a single PPG signal pulse. We used a one-dimensional convolutional neural network (1D CNN) to extract PPG signal features to classify the valence and arousal. We split the PPG signal into a single 1.1 s pulse and normalized it for input to the neural network based on the personal maximum and minimum values. We chose the dataset for emotion analysis using physiological (DEAP) signals for the experiment and tested the 1D CNN as a binary classification (high or low valence and arousal), achieving the short-term emotion recognition of 1.1 s with 75.3% and 76.2% valence and arousal accuracies, respectively, on the DEAP data.

Original languageEnglish
Article number3355
JournalApplied Sciences (Switzerland)
Volume9
Issue number16
DOIs
Publication statusPublished - 2019 Aug 1

Fingerprint

emotions
arousal
Neural networks
pulses
valence
Experiments
sensory feedback

Keywords

  • One-dimensional convolutional neural network
  • Personal normalization
  • PPG
  • Short term emotion recognition

ASJC Scopus subject areas

  • Materials Science(all)
  • Instrumentation
  • Engineering(all)
  • Process Chemistry and Technology
  • Computer Science Applications
  • Fluid Flow and Transfer Processes

Cite this

Fast emotion recognition based on single pulse PPG signal with convolutional neural network. / Lee, Min Seop; Lee, Yun Kyu; Pae, Dong Sung; Lim, Myo Taeg; Kim, Dong Won; Kang, Tae Koo.

In: Applied Sciences (Switzerland), Vol. 9, No. 16, 3355, 01.08.2019.

Research output: Contribution to journalArticle

Lee, Min Seop ; Lee, Yun Kyu ; Pae, Dong Sung ; Lim, Myo Taeg ; Kim, Dong Won ; Kang, Tae Koo. / Fast emotion recognition based on single pulse PPG signal with convolutional neural network. In: Applied Sciences (Switzerland). 2019 ; Vol. 9, No. 16.
@article{fd18db24e54e403993a4bb2e88edf85c,
title = "Fast emotion recognition based on single pulse PPG signal with convolutional neural network",
abstract = "Physiological signals contain considerable information regarding emotions. This paper investigated the ability of photoplethysmogram (PPG) signals to recognize emotion, adopting a two-dimensional emotion model based on valence and arousal to represent human feelings. The main purpose was to recognize short term emotion using a single PPG signal pulse. We used a one-dimensional convolutional neural network (1D CNN) to extract PPG signal features to classify the valence and arousal. We split the PPG signal into a single 1.1 s pulse and normalized it for input to the neural network based on the personal maximum and minimum values. We chose the dataset for emotion analysis using physiological (DEAP) signals for the experiment and tested the 1D CNN as a binary classification (high or low valence and arousal), achieving the short-term emotion recognition of 1.1 s with 75.3{\%} and 76.2{\%} valence and arousal accuracies, respectively, on the DEAP data.",
keywords = "One-dimensional convolutional neural network, Personal normalization, PPG, Short term emotion recognition",
author = "Lee, {Min Seop} and Lee, {Yun Kyu} and Pae, {Dong Sung} and Lim, {Myo Taeg} and Kim, {Dong Won} and Kang, {Tae Koo}",
year = "2019",
month = "8",
day = "1",
doi = "10.3390/app9163355",
language = "English",
volume = "9",
journal = "Applied Sciences (Switzerland)",
issn = "2076-3417",
publisher = "Multidisciplinary Digital Publishing Institute",
number = "16",

}

TY - JOUR

T1 - Fast emotion recognition based on single pulse PPG signal with convolutional neural network

AU - Lee, Min Seop

AU - Lee, Yun Kyu

AU - Pae, Dong Sung

AU - Lim, Myo Taeg

AU - Kim, Dong Won

AU - Kang, Tae Koo

PY - 2019/8/1

Y1 - 2019/8/1

N2 - Physiological signals contain considerable information regarding emotions. This paper investigated the ability of photoplethysmogram (PPG) signals to recognize emotion, adopting a two-dimensional emotion model based on valence and arousal to represent human feelings. The main purpose was to recognize short term emotion using a single PPG signal pulse. We used a one-dimensional convolutional neural network (1D CNN) to extract PPG signal features to classify the valence and arousal. We split the PPG signal into a single 1.1 s pulse and normalized it for input to the neural network based on the personal maximum and minimum values. We chose the dataset for emotion analysis using physiological (DEAP) signals for the experiment and tested the 1D CNN as a binary classification (high or low valence and arousal), achieving the short-term emotion recognition of 1.1 s with 75.3% and 76.2% valence and arousal accuracies, respectively, on the DEAP data.

AB - Physiological signals contain considerable information regarding emotions. This paper investigated the ability of photoplethysmogram (PPG) signals to recognize emotion, adopting a two-dimensional emotion model based on valence and arousal to represent human feelings. The main purpose was to recognize short term emotion using a single PPG signal pulse. We used a one-dimensional convolutional neural network (1D CNN) to extract PPG signal features to classify the valence and arousal. We split the PPG signal into a single 1.1 s pulse and normalized it for input to the neural network based on the personal maximum and minimum values. We chose the dataset for emotion analysis using physiological (DEAP) signals for the experiment and tested the 1D CNN as a binary classification (high or low valence and arousal), achieving the short-term emotion recognition of 1.1 s with 75.3% and 76.2% valence and arousal accuracies, respectively, on the DEAP data.

KW - One-dimensional convolutional neural network

KW - Personal normalization

KW - PPG

KW - Short term emotion recognition

UR - http://www.scopus.com/inward/record.url?scp=85070859847&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85070859847&partnerID=8YFLogxK

U2 - 10.3390/app9163355

DO - 10.3390/app9163355

M3 - Article

VL - 9

JO - Applied Sciences (Switzerland)

JF - Applied Sciences (Switzerland)

SN - 2076-3417

IS - 16

M1 - 3355

ER -