DEAP statistics

Tool stats & trends

Looking to identify usage trends or leading experts?

DEAP specifications


Unique identifier OMICS_34045
Alternative name Database for Emotion Analysis using Physiological Signals
Restrictions to use None
Community driven No
Data access File download, Browse
User data submission Not allowed
Maintained Yes


  • person_outline Sander Koelstra

Publication for Database for Emotion Analysis using Physiological Signals

DEAP citations


Electroencephalography Amplitude Modulation Analysis for Automated Affective Tagging of Music Video Clips

Front Comput Neurosci
PMCID: 5767842
PMID: 29367844
DOI: 10.3389/fncom.2017.00115

[…] r more details. Here, SVM classifiers are trained on four different binary classification problems, i.e., detecting low/high valence, low/high arousal, low/high dominance and low/high liking.With the DEAP database, subjective ratings followed a 9-point scale. Typically, values greater or equal to 5 are assumed to correspond to high activation levels or low, otherwise. However, it is not guaranteed […]


A Fast, Efficient Domain Adaptation Technique for Cross Domain Electroencephalography(EEG) Based Emotion Recognition

PMCID: 5469537
PMID: 28467371
DOI: 10.3390/s17051014

[…] ct emotion classification. The effectiveness of the T-RFE algorithm for such cross-subject emotion classification paradigm is validated by a database for emotion analysis using physiological signals (DEAP) [], and outperforms several recent reported works on the same database. The authors of [] proposed a semi-supervised strategy by utilizing a validating set with the emotion class labels rom the […]


ReliefF Based EEG Sensor Selection Methods for Emotion Recognition

PMCID: 5087347
PMID: 27669247
DOI: 10.3390/s16101558

[…] estigated and compared.The rest of this paper is structured as follows. presents the material and methods, including the description of the database for emotion analysis using physiological signals (DEAP), feature extraction, channel selection based on an ReliefF algorithm, and the an SVM classifier. is dedicated to the obtained results. The proposed methods are assessed in the task of classifyi […]


Familiarity effects in EEG based emotion recognition

Brain Inform
PMCID: 5319949
PMID: 27747819
DOI: 10.1007/s40708-016-0051-5

[…] ation by separating arousal into high and low classes and valence into positive and negative classes. Each class in our dataset was determined by the positivity of arousal and valence ratings. In the DEAP dataset, the instances were classified into the high arousal class when arousal rating was higher than 4.5; otherwise, they were placed in the low arousal class. Similarly, the data with a valenc […]


Looking to check out a full list of citations?

DEAP institution(s)
School of Electronic Engineering and Computer Science, Queen Mary University of London, London; Human Media Interaction Group, University of Twente, Enschede, The Netherlands; Computer Science Department, University of Geneva, Geneva, Switzerland; School of Integrated Technology, Yonsei University, Seoul, Korea; Multimedia Signal Processing Group, Institute of Electrical Engineering (IEL), Ecole Polytechnique Federale de Lausanne (EPFL), Lausanne, Switzerland
DEAP funding source(s)
Supported by the European Community’s 17th Framework Program (FP7/2007-2011) under grant agreement no. 216444 (PetaMedia).

DEAP reviews

star_border star_border star_border star_border star_border
star star star star star

Be the first to review DEAP