Classification of emotions from EEG signals using time-order representation based on the S-transform and convolutional neural network

Emotions are the most powerful information source to study the cognition, behaviour, and medical conditions of a person. Accurate identification of emotions helps in the development of affective computing, brain–computer interface, medical diagnosis system, etc. Electroencephalogram (EEG) signals ar...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Electronics letters Jg. 56; H. 25; S. 1359 - 1361
Hauptverfasser: Khare, S.K, Nishad, A, Upadhyay, A, Bajaj, V
Format: Journal Article
Sprache:Englisch
Veröffentlicht: The Institution of Engineering and Technology 10.12.2020
Schlagworte:
affective computing
behaviour conditions
brain‐computer interfaces
brain–computer interface
CNN
cognition conditions
convolutional neural nets
convolutional neural network
deep features
EEG signals
electroencephalogram signals
electroencephalography
emotion recognition
human emotions
information source
medical conditions
medical diagnosis system
medical signal processing
Special Issue: Current Trends in Cognitive Science and Brain Computing Research and Applications
time‐order representation
TOR
transforms
electroencephalography
CNN
brain-computer interfaces
affective computing
convolutional neural network
time-order representation
electroencephalogram signals
transforms
brain–computer interface
deep features
emotion recognition
behaviour conditions
medical signal processing
cognition conditions
human emotions
medical conditions
TOR
information source
medical diagnosis system
EEG signals
convolutional neural nets
ISSN:0013-5194, 1350-911X, 1350-911X
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Emotions are the most powerful information source to study the cognition, behaviour, and medical conditions of a person. Accurate identification of emotions helps in the development of affective computing, brain–computer interface, medical diagnosis system, etc. Electroencephalogram (EEG) signals are one such source to capture and study human emotions. In this Letter, a novel time-order representation based on the S-transform and convolutional neural network (CNN) is proposed for the identification of human emotions. EEG signals are transformed into time-order representation (TOR) based on the S-transform. This TOR is given as an input to CNN to automatically extract and classify the deep features. Emotional states of happiness, fear, sadness, and relax are classified with an accuracy of 94.58%. The superiority of the method is judged by evaluating four performance parameters and comparing it with existing state-of-the-art on the same dataset.
ISSN:0013-5194
1350-911X
1350-911X
DOI:10.1049/el.2020.2380