WGAN Domain Adaptation for EEG-Based Emotion Recognition
| Autor: | Bao-Liang Lu, Wei-Long Zheng, Si-Yang Zhang, Yun Luo |
|---|---|
| Rok vydání: | 2018 |
| Předmět: |
Domain adaptation
medicine.diagnostic_test Computer science business.industry Feature vector Stability (learning theory) Pattern recognition 02 engineering and technology Electroencephalography Domain (software engineering) 03 medical and health sciences 0302 clinical medicine 0202 electrical engineering electronic engineering information engineering medicine 020201 artificial intelligence & image processing Emotion recognition Artificial intelligence business 030217 neurology & neurosurgery |
| Zdroj: | Neural Information Processing ISBN: 9783030042202 ICONIP (5) |
| DOI: | 10.1007/978-3-030-04221-9_25 |
| Popis: | In this paper, we propose a novel Wasserstein generative adversarial network domain adaptation (WGANDA) framework for building cross-subject electroencephalography (EEG)-based emotion recognition models. The proposed framework consists of GANs-like components and a two-step training procedure with pre-training and adversarial training. Pre-training is to map source domain and target domain to a common feature space, and adversarial-training is to narrow down the gap between the mappings of the source and target domains on the common feature space. A Wasserstein GAN gradient penalty loss is applied to adversarial-training to guarantee the stability and convergence of the framework. We evaluate the framework on two public EEG datasets for emotion recognition, SEED and DEAP. The experimental results demonstrate that our WGANDA framework successfully handles the domain shift problem in cross-subject EEG-based emotion recognition and significantly outperforms the state-of-the-art domain adaptation methods. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|