Related Experiment Video
Updated: Aug 11, 2026
09:58
Recording Brain Activity with Ear-Electroencephalography
Published on: March 31, 2023
Music emotion recognition with cEEGrid
Chris Winnard1, Kaare Mikkelsen2, Preben Kidmose3
1School of Electronic Engineering and Computer Science (EECS), Queen Mary University of London, Mile End Road, London, E1 4NS, United Kingdom of Great Britain and Northern Ireland.
Journal of Neural Engineering
|August 4, 2026
Summary
Mobile electroencephalography (EEG) shows promise for emotion decoding, especially with music. Careful data splitting is crucial to avoid inflated performance and ensure reliable results in future mobile EEG studies.
Area of Science:
- Neuroscience
- Affective Computing
- Signal Processing
Background:
- Emotion decoding using electroencephalography (EEG) is a rapidly advancing field with significant healthcare applications.
- Mobile EEG systems offer potential for real-world emotion recognition, but research on music-elicited emotions and data handling is limited.
Purpose of the Study:
- To investigate music-based emotion decoding using mobile (around-the-ear) EEG.
- To evaluate the impact of different data splitting techniques on the performance of emotion decoding models.
Main Methods:
- Collected the Decoding Auditory Attention and Musical Emotions with Ear-EEG (DAAMEE) dataset, including scalp (DAAMEE-s) and around-the-ear cEEGrid (DAAMEE-c) data.
- Utilized music listening tasks from DAAMEE and DEAP datasets for performance testing with deep learning models and various data splitting strategies.
- Focused on binary valence decoding, extending to arousal, dominance, and VAD classification for top models.
Main Results:
- Around-the-ear cEEGrid data demonstrated comparable performance to traditional scalp EEG for emotion decoding.
- Certain data splitting techniques were found to inflate performance by exploiting temporal correlations, highlighting potential overfitting issues.
Conclusions:
- Mobile EEG, particularly using cEEGrid, is a viable approach for emotion decoding.
- Future EEG studies must employ data splitting methods that prevent overfitting to ensure robust and generalizable findings.
Related Concept Videos
01:20Labeling Emotion
Emotional labeling is a cognitive process that involves identifying and naming one's emotions, such as anger, fear, happiness, or sadness. It allows individuals to recognize and express their internal emotional states, a critical aspect of emotional regulation and communication. Labeling emotions requires more than mere recognition; it also involves drawing upon memory and contextual cues to understand the current situation and apply a corresponding emotional label. For instance, feeling...
01:22Motional Emf
Magnetic flux depends on three factors: the strength of the magnetic field, the area through which the field lines pass, and the field's orientation with respect to the surface area. If any of these quantities vary, a corresponding variation in magnetic flux occurs. If the area through which the magnetic field lines are passing changes, then the magnetic flux also changes. This change in the area can be of two types: the flux through the rectangular loop increases as it moves into the magnetic...