Identifying music-induced emotions from EEG for use in brain-computer music interfacing

Daly, I; Malik, A; Weaver, J; Hwang, F; Nasuto, SJ; Williams, DAH; Kirke, A; Miranda, E

Abstract

Brain-computer music interfaces (BCMI) provide a method to modulate an individuals affective state via the selection or generation of music according to their current affective state. Potential applications of such systems may include entertainment of therapeutic applications. We outline a proposed design for such a BCMI and seek a method for automatically differentiating different music induced affective states. Band-power features are explored for use in automatically identifying music-induced affective states. Additionally, a linear discriminant analysis classifier and a support vector machine are evaluated with respect to their ability to classify music induced affective states from the electroencephalogram recorded during a BCMI calibration task. Accuracies of up to 79.5% (p <; 0.001) are achieved with the support vector machine.

• Presentation Conference Type: Other
• Conference Name: 2015 International Conference on Affective Computing and Intelligent Interaction (ACII)
• End Date: Sep 24, 2015
• Publication Date: Dec 7, 2015
• Deposit Date: Dec 12, 2019
• Book Title: 2015 International Conference on Affective Computing and Intelligent Interaction (ACII)
• ISBN: 9781479999538
• DOI: https://doi.org/10.1109/acii.2015.7344685
• Publisher URL: https://doi.org/10.1109/acii.2015.7344685
• Additional Information: Event Type : Conference; Funders : Engineering and Physical Sciences Research Council (EPSRC); Grant Number: EP/J003077/1; Grant Number: EP/J002135/1