ABSTRACT
There have been many transfer learning models to solve the problem of individual differences in cross-subject emotion recognition using electroencephalogram (EEG) signals. However, the existing work consider little of the complexity of the class structure in the source domain, and may break the class structure in the target domain. In this paper, we propose a novel transfer learning model (CL-PSR-TL) based on the traditional domain-adversarial training of neural networks (DANN) in three aspects: 1) an inter-subject contrastive loss is additionally introduced in the source domain to extract the subject-irrelevant information; 2) a pairwise similarity mechanism with the effective pair selection is developed in the target domain to achieve a stable explore for the class structure; 3) a stepwise optimization strategy is applied to train the model. Then we evaluate the proposed model on two datasets (SEED and SEED-IV). Experimental results show that our proposed model achieves good performances compared with the state-of-the-art models.
- Cowie R, Douglas-Cowie E, Tsapatsoulis N, Emotion recognition in human-computer interaction[J]. IEEE Signal processing magazine, 2001, 18(1): 32-80.Google ScholarCross Ref
- Shu L, Xie J, Yang M, A review of emotion recognition using physiological signals[J]. Sensors, 2018, 18(7): 2074.Google ScholarCross Ref
- Egger M, Ley M, Hanke S. Emotion recognition from physiological signal analysis: A review[J]. Electronic Notes in Theoretical Computer Science, 2019, 343: 35-55.Google ScholarDigital Library
- Lin Y P, Wang C H, Jung T P, EEG-based emotion recognition in music listening[J]. IEEE Transactions on Biomedical Engineering, 2010, 57(7): 1798-1806.Google ScholarCross Ref
- Murugappan M, Ramachandran N, Sazali Y. Classification of human emotion from EEG using discrete wavelet transform[J]. Journal of biomedical science and engineering, 2010, 3(04): 390.Google Scholar
- Bos D O. EEG-based emotion recognition[J]. The influence of visual and auditory stimuli, 2006, 56(3): 1-17.Google Scholar
- Liu Y, Sourina O, Nguyen M K. Real-time EEG-based emotion recognition and its applications[M]//Transactions on computational science XII. Springer, Berlin, Heidelberg, 2011: 256-277.Google Scholar
- Joormann J, Gotlib I H. Emotion regulation in depression: Relation to cognitive inhibition[J]. Cognition and Emotion, 2010, 24(2): 281-298.Google ScholarCross Ref
- Kuusikko S, Haapsamo H, Jansson-Verkasalo E, Emotion recognition in children and adolescents with autism spectrum disorders[J]. Journal of autism and developmental disorders, 2009, 39(6): 938-945.Google Scholar
- Zheng W L, Lu B L. Personalizing EEG-based affective models with transfer learning[C]//Proceedings of the twenty-fifth international joint conference on artificial intelligence. 2016: 2732-2738.Google Scholar
- Pan S J, Tsang I W, Kwok J T, Domain adaptation via transfer component analysis[J]. IEEE transactions on neural networks, 2010, 22(2): 199-210.Google Scholar
- Li H, Jin Y M, Zheng W L, Cross-subject emotion recognition using deep adaptation networks[C]//International conference on neural information processing. Springer, Cham, 2018: 403-413.Google Scholar
- Goodfellow I, Pouget-Abadie J, Mirza M, Generative adversarial networks[J]. Communications of the ACM, 2020, 63(11): 139-144.Google ScholarDigital Library
- Zhong P, Wang D, Miao C. EEG-based emotion recognition using regularized graph neural networks[J]. IEEE Transactions on Affective Computing, 2020.Google Scholar
- Li Y, Zheng W, Zong Y, A bi-hemisphere domain adversarial neural network model for EEG emotion recognition[J]. IEEE Transactions on Affective Computing, 2018, 12(2): 494-504.Google ScholarDigital Library
- Luo Y, Zhang S Y, Zheng W L, WGAN domain adaptation for EEG-based emotion recognition[C]//International Conference on Neural Information Processing. Springer, Cham, 2018: 275-286.Google Scholar
- Li J, Qiu S, Du C, Domain adaptation for EEG emotion recognition based on latent representation similarity[J]. IEEE Transactions on Cognitive and Developmental Systems, 2019, 12(2): 344-353.Google ScholarCross Ref
- Zhou R, Zhang Z, Yang X, A novel transfer learning framework with prototypical representation based pairwise learning for cross-subject cross-session EEG-based emotion recognition[J]. arXiv preprint arXiv:2202.06509, 2022.Google Scholar
- Yin Y, Yang Z, Hu H, Metric-learning-assisted domain adaptation[J]. Neurocomputing, 2021, 454: 268-279.Google ScholarCross Ref
- Chen X, Wang S, Long M, Transferability vs. discriminability: Batch spectral penalization for adversarial domain adaptation[C]//International conference on machine learning. PMLR, 2019: 1081-1090.Google Scholar
- Mingsheng Long, Zhangjie Cao, Jianmin Wang, and Michael I Jordan. 2018. Conditional adversarial domain adaptation. In Advances in Neural Information Processing Systems. 1640-1650.Google Scholar
- Zheng W L, Lu B L. Investigating critical frequency bands and channels for EEG-based emotion recognition with deep neural networks[J]. IEEE Transactions on autonomous mental development, 2015, 7(3): 162-175.Google ScholarDigital Library
- Duan R N, Zhu J Y, Lu B L. Differential entropy feature for EEG-based emotion classification[C]//2013 6th International IEEE/EMBS Conference on Neural Engineering (NER). IEEE, 2013: 81-84.Google Scholar
- Zheng W L, Liu W, Lu Y, Emotionmeter: A multimodal framework for recognizing human emotions[J]. IEEE transactions on cybernetics, 2018, 49(3): 1110-1122.Google Scholar
- Lee P, Hwang S, Lee J, Inter-subject contrastive learning for subject adaptive eeg-based visual recognition[C]//2022 10th International Winter Conference on Brain-Computer Interface (BCI). IEEE, 2022: 1-6.Google Scholar
- Khosla P, Teterwak P, Wang C, Supervised contrastive learning[J]. Advances in Neural Information Processing Systems, 2020, 33: 18661-18673.Google Scholar
- Chen H, Jin M, Li Z, MS-MDA: Multisource marginal distribution adaptation for cross-subject and cross-session EEG emotion recognition[J]. Frontiers in Neuroscience, 2021, 15.Google Scholar
Index Terms
- A Novel Transfer Learning Model for Cross-Subject Emotion Recognition using EEGs
Recommendations
Cross-Domain Color Facial Expression Recognition Using Transductive Transfer Subspace Learning
Facial expression recognition across domains, e.g., training and testing facial images come from different facial poses, is very challenging due to the different marginal distributions between training and testing facial feature vectors. To deal with ...
Cross-subject EEG emotion recognition combined with connectivity features and meta-transfer learning
AbstractIn recent years, with the rapid development of machine learning, automatic emotion recognition based on electroencephalogram (EEG) signals has received increasing attention. However, owing to the great variance of EEG signals sampled ...
Highlights- The work proposed a novel method for Cross-subject EEG emotion recognition. The highlights are as follows:
Human-Computer Interaction Using Emotion Recognition from Facial Expression
EMS '11: Proceedings of the 2011 UKSim 5th European Symposium on Computer Modeling and SimulationThis paper describes emotion recognition system based on facial expression. A fully automatic facial expression recognition system is based on three steps: face detection, facial characteristic extraction and facial expression classification. We have ...
Comments