Emotion Assessment by Variability-Based Ranking of Coherence Features from EEG
The automatic assessment of emotional states has important applications in human-computer interfaces and marketing. Several approaches use a dimensional characterization of emotional states along with features extracted from physiological signals to classify emotions elicited from complex audiovisual stimuli; however, the classification accuracy remains low. Here, we develop an emotion assessment approach using a variability-based ranking scheme to reveal relevant coherence features from electroencephalography (EEG) signals. Our method achieves higher classification accuracies than comparable state-of-the-art methods and almost matches the performance of multimodal strategies that require information from several physiological signals.
KeywordsEmotion assessment Electroencephalography Coherence features Relevance analysis
This work was supported by the project “Desarrollo de un sistema de apoyo al diagnóstico no invasivo de pacientes con epilepsia fármaco-resistente asociada a displasias corticales cerebrales: método costo-efectivo basado en procesamiento de imágenes de resonancia magnética” with code 1110-744-55778, and author I. De La Pava was supported by the program “Doctorado Nacional en Empresa - Convoctoria 758 de 2016”, both funded by Colciencias. The authors would also like to thank Cristian Alejandro Torres Valencia for his valuable contribution to this work.
- 3.Gonuguntla, V., et al.: Identification of emotion associated brain functional network with phase locking value. In: 2016 IEEE 38th Annual International Conference of the EMBC, pp. 4515–4518. IEEE (2016)Google Scholar