AVEMODB

Abstract,

Throughout various disciplines, emotion recognition continues to be an essential subject of study. With the advancement of machine learning methods, accurate emotion recognition from different data modalities (facial images, brain EEG signals) has become possible. Success of EEG-based emotion recognition systems depends on efficient feature extraction and pre/postprocessing of signals. Main objective of this study is to analyze the efficacy of multiple-instance learning (MIL) on postprocessing features of EEG signals using three different domains (time, frequency, time-frequency) for human emotion classification. Methods and results are presented for single-trial classification of valence (V), arousal (A), and dominance (D) ratings from EEG signals obtained with audio (A), video (V), and audio-video (AV) stimulus using alpha, beta and gamma bands. High accuracy was observed with both binary and multiclass classification of the AV stimulus. Findings in this study suggest that MIL applied on frequency features yields efficient results on EEG emotion recognition.

References

The dataset is made publicly available. We encourage other researchers to use this dataset, which presents Audio, Visual, Audio-Visual supported stimuli with their machine-learning methods. The dataset was first introduced in the following paper. If you feel that the dataset is helpful for your study, please add the following references to your publications.

AVEMODB Dataset paper:
DAŞDEMİR, YAŞAR and ÖZAKAR, RÜSTEM (2022) "Affective states classification performance of audio-visual stimuli from EEG signals with multiple-instance learning," Turkish Journal of Electrical Engineering and Computer Sciences: Vol. 30: No. 7, Article 15.

how to use

If you are interested in using this dataset, you will have to print, sign and scan an EULA (End User License Agreement) and upload it via the dataset request form. We will then supply you with a username and password to download the data. Please head on over to the downloads page for more details. Also, please consult the dataset description page for a complete explanation of the dataset.

credits

First and foremost we'd like to thank the 22 participants in this study for having the patience and goodwill to let us record their data. This dataset was collected by a team of engineer candidate students who are committed to learning:

Serdar Yıldırım
Yaşar Daşdemir
Rüstem Özakar

All this would not have been possible without their valuable contribution and expert guidance, the project advisor:

Serdar Yıldırım

Finally, we would like to thank our funding institutions:

Mustafa Kemal University Scientific Research and Publication Ethics Committee

Page updated

Report abuse