Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
Review
. 2020 Sep 7;20(18):5083.
doi: 10.3390/s20185083.

EEG-Based BCI Emotion Recognition: A Survey

Edgar P Torres P  1 , Edgar A Torres  2 , Myriam Hernández-Álvarez  1 , Sang Guun Yoo  1
Affiliations
Review

EEG-Based BCI Emotion Recognition: A Survey

Edgar P Torres P et al. Sensors (Basel). .

Abstract

Affecting computing is an artificial intelligence area of study that recognizes, interprets, processes, and simulates human affects. The user's emotional states can be sensed through electroencephalography (EEG)-based Brain Computer Interfaces (BCI) devices. Research in emotion recognition using these tools is a rapidly growing field with multiple inter-disciplinary applications. This article performs a survey of the pertinent scientific literature from 2015 to 2020. It presents trends and a comparative analysis of algorithm applications in new implementations from a computer science perspective. Our survey gives an overview of datasets, emotion elicitation methods, feature extraction and selection, classification algorithms, and performance evaluation. Lastly, we provide insights for future developments.

Keywords: BCI; classification; emotion; extraction; feature; preprocessing; recognition; selection; survey; trends.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflict of interest.

Figures

Figure 1
Figure 1
Emotional states in the Valence-Arousal space [11].
Figure 2
Figure 2
Emotional states in the Valence-Arousal-Dominance space [12].
Figure 3
Figure 3
Components of an EEG-based BCI for emotion recognition.
Figure 4
Figure 4
Frequency domain, time domain, and spatial information [63].
Figure 5
Figure 5
Emotion elicitation methods.
Figure 6
Figure 6
Number of participants in EEG datasets.
Figure 7
Figure 7
EEG datasets for emotion recognition.
Figure 8
Figure 8
Domain of used features.
Figure 9
Figure 9
Percentage of the use of algorithms for feature extraction from Table 8.
Figure 10
Figure 10
Classifiers’ usage.
Figure 11
Figure 11
Percentage of systems with different numbers of classified emotions.
Figure 12
Figure 12
Accuracy vs. types and number of classified emotions.
See this image and copyright information in PMC

References

    1. Picard R.W. Affective Computing for HCI; Proceedings of the HCI International 1999-Proceedings of the 8th International Conference on Human-Computer Interaction; Munich, Germany. 22–26 August 1999.
    1. Elfenbein H.A., Ambady N. Predicting workplace outcomes from the ability to eavesdrop on feelings. J. Appl. Psychol. 2002;87:963–971. doi: 10.1037/0021-9010.87.5.963. - DOI - PubMed
    1. Goenaga S., Navarro L., Quintero C.G.M., Pardo M. Imitating human emotions with a nao robot as interviewer playing the role of vocational tutor. Electronics. 2020;9:971. doi: 10.3390/electronics9060971. - DOI
    1. Kitcheman B. Procedures for performing systematic reviews. [(accessed on 26 May 2020)];Comput. Sci. 2004 :1–28. Available online: http://www.inf.ufsc.br/~aldo.vw/kitchenham.pdf.
    1. Salzman C.D., Fusi S. Emotion, cognition, and mental state representation in Amygdala and prefrontal Cortex. Annu. Rev. Neurosci. 2010;33:173–202. doi: 10.1146/annurev.neuro.051508.135256. - DOI - PMC - PubMed

LinkOut - more resources