Extracting emotional features from ECG by using wavelet transform

Zhengji Long*, Guangyuan Liu, Xuewu Dai

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

21 Citations (Scopus)

Abstract

One key element of emotion recognition is to extract emotional features effectively from physiological signals. In this paper, a wavelet transform based feature extraction is proposed to recognize emotions through ECG (Electrocardiogram) signals. Four emotional data sets collected on the same day from one subject are decomposed by DWT (Discrete Wavelet Transform) and 84 statistic values of wavelet coefficients are selected as the emotional features according to their amplitude relations. Furthermore, in order to eliminate the negative impacts of material, time and environment, these selected features are normalized with respect to the emotional mode 'Pleasure'. The initial results show that, with the normalized features, the best correct-classification ratio of joy and sadness reaches 92%.

Original languageEnglish
Title of host publication2010 International Conference on Biomedical Engineering and Computer Science, ICBECS 2010
Place of PublicationPiscataway, NJ
PublisherInstitute of Electrical and Electronics Engineers Inc.
Number of pages4
ISBN (Print)9781424453153
DOIs
Publication statusPublished - 23 Apr 2010
Externally publishedYes
Event2010 International Conference on Biomedical Engineering and Computer Science, ICBECS 2010 - Wuhan, China
Duration: 23 Apr 201025 Apr 2010

Publication series

Name2010 International Conference on Biomedical Engineering and Computer Science, ICBECS 2010

Conference

Conference2010 International Conference on Biomedical Engineering and Computer Science, ICBECS 2010
Country/TerritoryChina
CityWuhan
Period23/04/1025/04/10

Keywords

  • ECG
  • Emotion recognition
  • Feature extraction
  • Wavelet transform

Fingerprint

Dive into the research topics of 'Extracting emotional features from ECG by using wavelet transform'. Together they form a unique fingerprint.

Cite this