Title | ||
---|---|---|
Eeg-Based Emotion Estimation Using Adaptive Tracking Of Discriminative Frequency Components |
Abstract | ||
---|---|---|
EEG-based emotion recognition has received increasing attention in the past few decades. The frequency components that give effective discrimination between different emotion states are subject specific. Identification of these subject-specific discriminative frequency components (DFCs) is important for the accurate classification of emotional activities. This paper investigated the potential of adaptive tracking of DFCs as an effective method for choosing the discriminative bands of EEG patterns and improving emotion recognition performance. 13 healthy volunteers were emotionally elicited by pictures selected from the International Affective Picture System (LAPS). Discriminative frequency components were tracked and analyzed for each subject and classification of three emotions (pleasant/high arousal, neutral, unpleasant/high arousal) was performed by employing a Hidden Markov Model (HMM) and a Support Vector Machine (SVM). Our results showed that adaptive tracking of DFCs improved classification accuracies significantly and the highest average accuracy of 82.85% was achieved by SVM. |
Year | DOI | Venue |
---|---|---|
2017 | 10.1109/EMBC.2017.8037298 | 2017 39TH ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY (EMBC) |
Keywords | Field | DocType |
Emotion recognition, Electroencephalographic (EEG), Discriminative band, Hidden Markov Model, Support vector machine (SVM) | Arousal,Pattern recognition,Emotion recognition,Computer science,Support vector machine,Speech recognition,Artificial intelligence,Hidden Markov model,International Affective Picture System,Discriminative model,Electroencephalography | Conference |
Volume | ISSN | Citations |
2017 | 1094-687X | 0 |
PageRank | References | Authors |
0.34 | 10 | 7 |
Name | Order | Citations | PageRank |
---|---|---|---|
Shuang Liu | 1 | 36 | 22.95 |
Di Zhang | 2 | 0 | 0.34 |
Jingjing Tong | 3 | 4 | 1.08 |
Feng He | 4 | 16 | 9.45 |
Hongzhi Qi | 5 | 49 | 20.61 |
Lixin Zhang | 6 | 0 | 0.34 |
Dong Ming | 7 | 105 | 51.47 |