2020
DOI: 10.1109/access.2020.2966144
|View full text |Cite
|
Sign up to set email alerts
|

Emotion Feature Analysis and Recognition Based on Reconstructed EEG Sources

Abstract: Emotion plays a significant role in perceiving external events or situations in daily life. Due to ease of use and relative accuracy, Electroencephalography (EEG)-based emotion recognition has become a hot topic in the affective computing field. However, scalp EEG is a mixed-signal and cannot directly indicate the exact information about active cortex sources of different emotions. In this paper, we analyze the significant differences of active source regions and frequency bands for pairs of emotions-based rec… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
2

Citation Types

0
28
0

Year Published

2020
2020
2024
2024

Publication Types

Select...
8

Relationship

0
8

Authors

Journals

citations
Cited by 45 publications
(28 citation statements)
references
References 38 publications
0
28
0
Order By: Relevance
“…For each trial, ( , , , ) and ( , , , ) are synchronously collected with the given sampling frequency ( 1 = 512 for EEG, 2 = 32 for facial expression) under the coordination of the dedicated server. According to the method and the implementation of building up EEG ground truth data set presented in Section Ⅲ , computer software tool SVSF is performed on ( , , , ) to segment the facial expression images into 60 × 32 = 1920 separated sequence frames ( , , , ), ∈ [1,1920]. And then the computer software tool BEEGLDS is performed on the ( , , , ), ∈ [1,1920] to recognize the special frame frame-s m th and special frame frame-e ℎ of the k th emotion.…”
Section: E Build Up Eeg Ground Truth Data Set Eeg-lmentioning
confidence: 99%
See 2 more Smart Citations
“…For each trial, ( , , , ) and ( , , , ) are synchronously collected with the given sampling frequency ( 1 = 512 for EEG, 2 = 32 for facial expression) under the coordination of the dedicated server. According to the method and the implementation of building up EEG ground truth data set presented in Section Ⅲ , computer software tool SVSF is performed on ( , , , ) to segment the facial expression images into 60 × 32 = 1920 separated sequence frames ( , , , ), ∈ [1,1920]. And then the computer software tool BEEGLDS is performed on the ( , , , ), ∈ [1,1920] to recognize the special frame frame-s m th and special frame frame-e ℎ of the k th emotion.…”
Section: E Build Up Eeg Ground Truth Data Set Eeg-lmentioning
confidence: 99%
“…According to the method and the implementation of building up EEG ground truth data set presented in Section Ⅲ , computer software tool SVSF is performed on ( , , , ) to segment the facial expression images into 60 × 32 = 1920 separated sequence frames ( , , , ), ∈ [1,1920]. And then the computer software tool BEEGLDS is performed on the ( , , , ), ∈ [1,1920] to recognize the special frame frame-s m th and special frame frame-e ℎ of the k th emotion. The frames ( , , , ), ∈ [ , + 1, … , ] are taken as the facial expression ground truth data, and store them into the facial expression ground truth data set FE-L.…”
Section: E Build Up Eeg Ground Truth Data Set Eeg-lmentioning
confidence: 99%
See 1 more Smart Citation
“…EEG estimates voltage variations because of ionic current within the neurons of the cerebrum. The state-of-the-art emotion recognition methods [ 6 , 7 ] can be broadly divided into three types namely, knowledge-based methods, statistical approaches, and hybrid techniques [ 8 ]. In knowledge-based, emotion detection is carried out by utilizing domain understanding and the semantic and syntactic features of language [ 9 ] using WordNet, SenticNet [ 10 ], ConceptNet, and EmotiNet [ 11 ].…”
Section: Introductionmentioning
confidence: 99%
“…Russell’s valence–arousal model is a widely-recognized model of emotion, and in this model, emotions are represented in the space of two axes: valence (ranging from pleasant to unpleasant state) and arousal (ranging from excited to calm state), as illustrated in Figure 1 a [ 5 ]. Among many emotion classification studies based on EEG, some studies estimated source activities in the brain and performed classification using only emotion-related source signals [ 6 , 7 , 8 , 9 ]. Padilla-Buritica and colleagues reconstructed source-level signals from scalp EEG and classified emotions using signals extracted from the selected brain regions [ 6 ].…”
Section: Introductionmentioning
confidence: 99%