Authors:
C. Godin
1
;
F. Prost-Boucle
1
;
A. Campagne
2
;
S. Charbonnier
3
;
S. Bonnet
1
and
A. Vidal
1
Affiliations:
1
Univ. Grenoble Alpes, CEA and LETI, France
;
2
Université Pierre Mendes, France
;
3
Univ. Grenoble Alpes & CNRS, France
Keyword(s):
Emotion Recognition, Physiological Signals, Classification, Feature Selection, Heart Rate Variability, Galvanic Skin Response, Eye Blinking, Arousal, Valence, DEAP, MAHNOB-HCI.
Related
Ontology
Subjects/Areas/Topics:
Artificial Intelligence
;
Biomedical Engineering
;
Biomedical Signal Processing
;
Biosignal Acquisition, Analysis and Processing
;
Data Manipulation
;
Devices
;
Health Engineering and Technology Applications
;
Health Information Systems
;
Human-Computer Interaction
;
Methodologies and Methods
;
Neurocomputing
;
Neurotechnology, Electronics and Informatics
;
Pattern Recognition
;
Physiological Computing Systems
;
Processing of Multimodal Input
;
Sensor Networks
;
Soft Computing
;
Wearable Sensors and Systems
Abstract:
With the development of wearable physiological sensors, emotion estimation becomes a hot topic in the
literature. Databases of physiological signals recorded during emotional stimulation are acquired and
machine learning algorithms are used. Yet, which are the most relevant signals to detect emotions is still a
question to be answered. In order to better understand the contribution of each signal, and thus sensor, to the
emotion estimation problem, several feature selection algorithms were implemented on two databases freely
available to the research community (DEAP and MANHOB-HCI). Both databases manipulate emotions by
showing participants short videos (video clips or part of movies respectively). Features extracted from
Galvanic Skin response were found to be relevant for arousal estimation in both databases. Other relevant
features were eye closing rate for arousal, variance of zygomatic EMG for valence (those features being
only available for DEAP). The hearth rate variability po
wer in three frequency bands also appeared to be
very relevant, but only for MANHOB-HCI database where heat rate was measured using ECG (whereas
DEAP used PPG). This suggests that PPG is not accurate enough to estimate HRV precisely. Finally we
showed on DEAP database that emotion classifiers need just a few well selected features to obtain similar
performances to literature classifiers using more features.
(More)