Fusing Acoustic and Electroencephalographic Modalities for User-Independent Emotion Prediction
Contributo in Atti di convegno
Data di Pubblicazione:
2019
Citazione:
Fusing Acoustic and Electroencephalographic Modalities for User-Independent Emotion Prediction / S. Ntalampiras, F. Avanzini, L.A. Ludovico - In: 2019 IEEE International Conference on Cognitive Computing (ICCC) / [a cura di] E. Bertino, C.K. Chang, P. Chen, E. Damiani, M. Goul, K. Oyama. - [s.l] : IEEE, 2019. - ISBN 9781728127118. - pp. 36-41 (( Intervento presentato al 4. convegno IEEE International Conference on Cognitive Computing (IEEE ICCC) Part of the IEEE World Congress on Services tenutosi a Milano nel 2019 [10.1109/ICCC.2019.00018].
Abstract:
Search and retrieval of multimedia content based on the evoked emotion comprises an interesting scientific field with numerous applications. This paper proposes a method that fuses two heterogeneous modalities, i.e. music and electroencephalographic signals, both for predicting emotional dimensions in the valence-arousal plane and for addressing four binary classification tasks, namely i.e. high/low arousal, positive/negative valence, high/low dominance, high/low liking. The proposed solution exploits Mel-scaled and EEG spectrograms feeding a k-medoids clustering scheme based on canonical correlation analysis. A thorough experimental campaign carried out on a publicly available dataset confirms the efficacy of such an approach. Despite its low computational cost, it was able to surpass state of the art results, and most importantly, in a user-independent manner.
Tipologia IRIS:
03 - Contributo in volume
Keywords:
music emotion prediction; EEG emotion prediction; music EEG fusion; canonical correlation analysis; k-medoids clustering algorithm
Elenco autori:
S. Ntalampiras, F. Avanzini, L.A. Ludovico
Link alla scheda completa:
Titolo del libro:
2019 IEEE International Conference on Cognitive Computing (ICCC)