Year: 2021
Type: article
Abstract: As a subjectively psychological and physiological response to external stimuli, emotion is ubiquitous in our daily life. With the continuous development of the artificial intelligence and brain science, emotion recognition rapidly becomes a multiple discipline research field through EEG signals. This paper investigates the relevantly scientific literature in the past five years and reviews the emotional feature extraction methods and the classification methods using EEG signals. Commonly used feature extraction analysis methods include time domain analysis, frequency domain analysis, and time-frequency domain analysis. The widely used classification methods include machine learning algorithms based on Support Vector Machine (SVM), k-Nearest Neighbor (KNN), Naive Bayes (NB), etc., and their classification accuracy ranges from 57.50% to 95.70%. The classification accuracy of the deep learning algorithms based on Neural Network (NN), Long and Short-Term Memory (LSTM), and Deep Belief Network (DBN) ranges from 63.38% to 97.56%.
Source: Cognitive Robotics
Authors: Jiang Wang, Mei Wang
Institution: Xi'an University of Science and Technology
Language: English
Topic: Emotion and Mood Recognition
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Keywords: emotion recognition, EEG signals, emotional feature extraction, emotion classification, time-frequency analysis, frequency domain analysis, time-domain analysis, support vector machine, k-nearest neighbors, naive Bayes, artificial neural networks, long short-term memory, deep belief network
Open Access status: gold
Estimated APC paid: $700
OpenAlex ID: W3153380589
