University of Oulu

Ferdinando H., Seppänen T., Alasaarela E. (2018) Emotion Recognition Using Neighborhood Components Analysis and ECG/HRV-Based Features. In: De Marsico M., di Baja G., Fred A. (eds) Pattern Recognition Applications and Methods. ICPRAM 2017. Lecture Notes in Computer Science, vol 10857. Springer, Cham

Emotion recognition using neighborhood components analysis and ECG/HRV-based features

Saved in:
Author: Ferdinando, Hany1,2; Seppänen, Tapio3; Alasaarela, Esko1
Organizations: 1Health and Wellness Measurement Research Unit, Opto-electronic and Measurement Technique (OPEM) unit, University of Oulu, Finland
2Department of Electrical Engineering, Petra Christian University, Indonesia
3Physiological Signal Team Analysis, University of Oulu, Finland
Format: article
Version: accepted version
Access: open
Online Access: PDF Full Text (PDF, 0.4 MB)
Persistent link: http://urn.fi/urn:nbn:fi-fe202003097634
Language: English
Published: Springer Nature, 2018
Publish Date: 2020-03-09
Description:

Abstract

Previous research showed that supervised dimensionality reduction using Neighborhood Components Analysis (NCA) enhanced the performance of 3-class problem emotion recognition using ECG only where features were the statistical distribution of dominant frequencies and the first differences after applying bivariate empirical mode decomposition (BEMD). This paper explores how much NCA enhances emotion recognition using ECG-derived features, esp. standard HRV features with two difference normalization methods and statistical distribution of instantaneous frequencies and the first differences calculated using Hilbert-Huang Transform (HHT) after empirical mode decomposition (EMD) and BEMD. Results with the MAHNOB-HCI database were validated using subject-dependent and subject-independent scenarios with kNN as classifier for 3-class problem in valence and arousal. A t-test was used to assess the results with significance level 0.05. Results show that NCA enhances the performance up to 74% from the implementation without NCA with p-values close to zero in most cases. Different feature extraction methods offered different performance levels in the baseline but the NCA enhanced them such that the performances were close to each other. In most experiments use of combined standardized and normalized HRV-based features improved performance. Using NCA on this database improved the standard deviation significantly for HRV-based features under subject-independent scenario.

see all

Series: Lecture notes in computer science
ISSN: 0302-9743
ISSN-E: 1611-3349
ISSN-L: 0302-9743
ISBN: 978-3-319-93647-5
ISBN Print: 978-3-319-93646-8
Pages: 99 - 113
DOI: 10.1007/978-3-319-93647-5_6
OADOI: https://oadoi.org/10.1007/978-3-319-93647-5_6
Host publication: Pattern Recognition Applications and Methods. ICPRAM 2017
Host publication editor: Fred, Ana
De Marsico, Maria
di Baja, Gabriella Sanniti
Conference: International Conference on Pattern Recognition Applications and Methods
Type of Publication: A1 Journal article – refereed
Field of Science: 113 Computer and information sciences
217 Medical engineering
Subjects:
Copyright information: © Springer International Publishing AG, part of Springer Nature 2018. This is a post-peer-review, pre-copyedit version of an article published in Pattern Recognition Applications and Methods. ICPRAM 2017. The final authenticated version is available online at: https://doi.org/10.1007/978-3-319-93647-5_6.