CROSS-CORPUS EEG-BASED EMOTION RECOGNITION (bibtex)
by Rayatdoost, Soheil and Soleymani, Mohammad
Abstract:
Lack of generalization is a common problem in automatic emotion recognition. The present study aims to explore the suitability of the existing EEG features for emotion recognition and investigate the performance of emotion recognition methods across different corpora. We introduce a novel dataset which includes spontaneous emotions and was analyzed in addition to the existing datasets for cross-corpus evaluation. We demonstrate that the performance of the existing methods significantly decreases when evaluated across different corpora. The best results are obtained by a convolutional neural network fed by spectral topography maps from different bands. We provide some evidence that stimuli-related sensory information is learned by machine learning models for emotion recognition using EEG signals.
Reference:
CROSS-CORPUS EEG-BASED EMOTION RECOGNITION (Rayatdoost, Soheil and Soleymani, Mohammad), In 2018 IEEE 28th International Workshop on Machine Learning for Signal Processing (MLSP), IEEE, 2018.
Bibtex Entry:
@inproceedings{rayatdoost_cross-corpus_2018,
	address = {Aalborg, Denmark},
	title = {{CROSS}-{CORPUS} {EEG}-{BASED} {EMOTION} {RECOGNITION}},
	isbn = {978-1-5386-5477-4},
	url = {https://ieeexplore.ieee.org/document/8517037/},
	doi = {10.1109/MLSP.2018.8517037},
	abstract = {Lack of generalization is a common problem in automatic emotion recognition. The present study aims to explore the suitability of the existing EEG features for emotion recognition and investigate the performance of emotion recognition methods across different corpora. We introduce a novel dataset which includes spontaneous emotions and was analyzed in addition to the existing datasets for cross-corpus evaluation. We demonstrate that the performance of the existing methods significantly decreases when evaluated across different corpora. The best results are obtained by a convolutional neural network fed by spectral topography maps from different bands. We provide some evidence that stimuli-related sensory information is learned by machine learning models for emotion recognition using EEG signals.},
	booktitle = {2018 {IEEE} 28th {International} {Workshop} on {Machine} {Learning} for {Signal} {Processing} ({MLSP})},
	publisher = {IEEE},
	author = {Rayatdoost, Soheil and Soleymani, Mohammad},
	month = sep,
	year = {2018},
	keywords = {Virtual Humans},
	pages = {1--6}
}
Powered by bibtexbrowser