Background: Human emotions greatly affect the actions of a person. The automated emotion recognition has applications in multiple domains such as health care, e-learning, surveillance, etc. The development of computer-aided diagnosis (CAD) tools has led to the automated recognition of human emotions.
Objective: This review paper provides an insight into various methods employed using electroencephalogram (EEG), facial, and speech signals coupled with multi-modal emotion recognition techniques. In this work, we have reviewed most of the state-of-the-art papers published on this topic.
Method: This study was carried out by considering the various emotion recognition (ER) models proposed between 2016 and 2021. The papers were analysed based on methods employed, classifier used and performance obtained.
Results: There is a significant rise in the application of deep learning techniques for ER. They have been widely applied for EEG, speech, facial expression, and multimodal features to develop an accurate ER model.
Conclusion: Our study reveals that most of the proposed machine and deep learning-based systems have yielded good performances for automated ER in a controlled environment. However, there is a need to obtain high performance for ER even in an uncontrolled environment.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1016/j.cmpb.2022.106646 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Emotion recognition using multi-scale EEG features through graph convolutional attention network.
Neural Netw
December 2024
The school of Electrical and Information Engineering, Tianjin University, Tianjin 300072, China. Electronic address:
Emotion recognition via electroencephalogram (EEG) signals holds significant promise across various domains, including the detection of emotions in patients with consciousness disorders, assisting in the diagnosis of depression, and assessing cognitive load. This process is critically important in the development and research of brain-computer interfaces, where precise and efficient recognition of emotions is paramount. In this work, we introduce a novel approach for emotion recognition employing multi-scale EEG features, denominated as the Dynamic Spatial-Spectral-Temporal Network (DSSTNet).
View Article and Find Full Text PDFDomain adaptation spatial feature perception neural network for cross-subject EEG emotion recognition.
Front Hum Neurosci
December 2024
School of Computer Sciences, Universiti Sains Malaysia, Penang, Malaysia.
Emotion recognition is a critical research topic within affective computing, with potential applications across various domains. Currently, EEG-based emotion recognition, utilizing deep learning frameworks, has been effectively applied and achieved commendable performance. However, existing deep learning-based models face challenges in capturing both the spatial activity features and spatial topology features of EEG signals simultaneously.
View Article and Find Full Text PDFExploring neural mechanisms of gender differences in bodily emotion recognition: a time-frequency analysis and network analysis study.
Front Neurosci
December 2024
Department of Military Medical Psychology, Fourth Military Medical University, Xi'an, China.
Background: This study aimed to explore the neural mechanisms underlying gender differences in recognizing emotional expressions conveyed through body language. Utilizing electroencephalogram (EEG) recordings, we examined the impact of gender on neural responses through time-frequency analysis and network analysis to uncover gender disparities in bodily emotion recognition.
Methods: The study included 34 participants, consisting of 18 males and 16 females.
Perceptions of Resilience Among Nurses: A Qualitative Study Based on the Society-To-Cells Framework.
J Adv Nurs
December 2024
Department of Community Health Nursing, College of Nursing, Jouf University, Sakaka, Saudi Arabia.
Aim(s): To explore the perceptions of resilience among nurses using the Society-to-Cells Resilience Theory and examine how multilevel factors influence their ability to maintain resilience in high-stress environments.
Design: A qualitative study using semi-structured interviews.
Methods: Sixteen registered nurses from various healthcare settings in the Asir region, Saudi Arabia, participated in face-to-face interviews conducted from February to April 2024.
Neuropsychological profile of POLR3A-related spastic ataxia.
Neurol Sci
December 2024
Memory Clinic, Department of Neurology, Onze-Lieve-Vrouwziekenhuis, Aalst, Belgium.
Background And Objectives: POLR3-related disorders are a group of autosomal recessive neurodegenerative diseases that usually cause leukodystrophy and can lead to cognitive dysfunction. Literature reporting comprehensive neuropsychological assessment in POLR3A-related diseases is sparse. Here we describe the neuropsychological profile of a case of childhood-onset POLR3A-related spastic ataxia without leukodystrophy.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!