Combining Eye Movements and EEG to Enhance Emotion Recognition
Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence. Main Track. Pages 1170-1175.
Abstract
In this paper, we adopt a multimodal emotion recognition framework by combining eye movements and electroencephalography (EEG) to enhance emotion recognition. The main contributions of this paper are twofold. a) We investigate sixteen eye movements related to emotions and identify the intrinsic patterns of these eye movements for three emotional states: positive, neutral and negative. b) We examine various modality fusion strategies for integrating users external subconscious behaviors and internal cognitive states and reveal that the characteristics of eye movements and EEG are complementary to emotion recognition. Experiment results demonstrate that modality fusion could significantly improve emotion recognition accuracy in comparison with single modality. The best accuracy achieved by fuzzy integral fusion strategy is 87.59%, whereas the accuracies of solely using eye movements and EEG data are 77.80% and 78.51%, respectively.
@inproceedings{ijcai2015p169,
title = {Combining Eye Movements and EEG to Enhance Emotion Recognition},
author = {Lu, Yifei and Zheng, Wei-Long and Li, Binbin and Lu, Bao-Liang},
booktitle = {Proceedings of the Twenty-Fourth International Joint Conference on
Artificial Intelligence, {IJCAI-15}},
publisher = {International Joint Conferences on Artificial Intelligence},
editor = {Qiang Yang and Michael Wooldridge},
pages = {1170--1175},
year = {2015},
month = {7},
note = {Main Track},
url = {https://ijcai.org/proceedings/2015/169},
}
TY - CPAPER TI - Combining Eye Movements and EEG to Enhance Emotion Recognition AU - Lu, Yifei AU - Zheng, Wei-Long AU - Li, Binbin AU - Lu, Bao-Liang T2 - Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-15 PB - International Joint Conferences on Artificial Intelligence PY - 2015 SP - 1170 EP - 1175 UR - https://ijcai.org/proceedings/2015/169 ER -Copied
Machine-readable versions of this paper, for tools and AI agents: