EEG Data Augmentation for Emotion Recognition Using a Conditional Wasserstein GAN

  title={EEG Data Augmentation for Emotion Recognition Using a Conditional Wasserstein GAN},
  author={Yun Luo},
  journal={2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)},
  • Yun Luo
  • Published 1 July 2018
  • Medicine, Computer Science
  • 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)
Due to the lack of electroencephalography (EEG) data, it is hard to build an emotion recognition model with high accuracy from EEG signals using machine learning approach. [...] Key Method A Wasserstein GAN with gradient penalty is adopted to generate realistic-like EEG data in differential entropy (DE) form.Expand
EEG data augmentation for emotion recognition with a multiple generator conditional Wasserstein GAN
Experimental results demonstrate that the artificial data that are generated by the proposed model can effectively improve the performance of emotion classification models that are based on EEG. Expand
GANSER: A Self-supervised Data Augmentation Framework for EEG-based Emotion Recognition
  • Zhi Zhang, Sheng-hua Zhong, Yan Liu
  • Computer Science
  • ArXiv
  • 2021
As the first to combine adversarial training with self-supervised learning for EEG-based emotion recognition, the proposed framework can generate high-quality and high-diversity simulated EEG samples and help emotion recognition for performance gain and achieve state of theart results. Expand
A GAN-Based Data Augmentation Method for Multimodal Emotion Recognition
A GAN-based data augmentation method for enhancing the performance of multimodal emotion recognition models by adopting conditional Boundary Equilibrium GAN (cBEGAN) to generate artificial differential entropy features of electroencephalography signal, eye movement data and their direct concatenations. Expand
GAN-Based Data Augmentation For Improving The Classification Of EEG Signals
The experimental results demonstrate that the proposed Wasserstein Generative Adversarial Network with gradient penalty (WGAN-GP) based model gives a considerable enhancement of the classification task’s performance. Expand
Generating EEG signals of an RSVP Experiment by a Class Conditioned Wasserstein Generative Adversarial Network
This work proposes a novel Conditional Wasserstein Generative Adversarial Network with gradient penalty (cWGAN-GP) that can be trained to synthesize EEG data for different cognitive events and shows that the synthesized EEG data can augment the real EEG data to achieve improved event classification performance. Expand
EEG-based Emotion Detection Using Unsupervised Transfer Learning
A novel, integrated framework for semi-generic emotion detection using (1) independent component analysis for EEG preprocessing, (2) EEG subject clustering by unsupervised learning, and (3) a convolutional neural network (CNN) for EEG-based emotion recognition is presented. Expand
EZSL-GAN: EEG-based Zero-Shot Learning approach using a Generative Adversarial Network
A new scheme for Zero-Shot EEG signal classification using EZSL-GAN, a Generative Adversarial Network that can tackle the problem for recognizing unknown EEG labels with a knowledge base and demonstrates that unseen EEG labels can be recognized by the knowledge base. Expand
Conditional generative adversarial network for EEG-based emotion fine-grained estimation and visualization
A conditional generative adversarial network (cGAN) is proposed to establish the relationship between EEG data associated with emotions, a coarse label, and a facial expression image in this study to achieve a fine mapping of EEG data directly to facial images. Expand
A Cross-Culture Study on Multimodal Emotion Recognition Using Deep Learning
The experimental results show that French has higher classification accuracy on beta frequency band while Chinese performs better on gamma frequency band, and EEG signals and eye movement data of French participants have complementary characteristics in discriminating positive and negative emotions. Expand
Ground Truth Dataset for EEG-Based Emotion Recognition With Visual Indication
An approach to building up ground truth electroencephalogram dataset with visual indication, which covers 3 kinds of emotions of the subjects who are undergraduate and graduate students from Minzu University of China. Expand


Rotational data augmentation for electroencephalographic data
  • M. M. Krell, S. K. Kim
  • Computer Science, Medicine
  • 2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)
  • 2017
This work suggests and evaluates rotational distortions similar to affine/rotational distortions of images to generate augmented data that increases the performance of signal processing chains for EEG-based brain-computer interfaces when rotating only around y- and z-axis with an angle around ±18 degrees. Expand
Combining Eye Movements and EEG to Enhance Emotion Recognition
It is revealed that the characteristics of eye movements and EEG are complementary to emotion recognition and modality fusion could significantly improve emotion recognition accuracy in comparison with single modality. Expand
Investigating Critical Frequency Bands and Channels for EEG-Based Emotion Recognition with Deep Neural Networks
The experiment results show that neural signatures associated with different emotions do exist and they share commonality across sessions and individuals, and the performance of deep models with shallow models is compared. Expand
Fusion of electroencephalographic dynamics and musical contents for estimating emotional responses in music listening
The present study not only provided principles for constructing an EEG-based multimodal approach, but also revealed the fundamental insights into the interplay of the brain activity and musical contents in emotion modeling. Expand
DEAP: A Database for Emotion Analysis ;Using Physiological Signals
A multimodal data set for the analysis of human affective states was presented and a novel method for stimuli selection is proposed using retrieval by affective tags from the website, video highlight detection, and an online assessment tool. Expand
Improved Training of Wasserstein GANs
This work proposes an alternative to clipping weights: penalize the norm of gradient of the critic with respect to its input, which performs better than standard WGAN and enables stable training of a wide variety of GAN architectures with almost no hyperparameter tuning. Expand
Signal Processing Approaches to Minimize or Suppress Calibration Time in Oscillatory Activity-Based Brain–Computer Interfaces
  • F. Lotte
  • Computer Science
  • Proceedings of the IEEE
  • 2015
This paper proposes to generate artificial EEG trials from the few EEG trials initially available, in order to augment the training set size, and surveys existing approaches to reduce or suppress calibration time and proposes three different methods to do so. Expand
Data Augmentation Generative Adversarial Networks
It is shown that a Data Augmentation Generative Adversarial Network (DAGAN) augments standard vanilla classifiers well and can enhance few-shot learning systems such as Matching Networks. Expand
Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
This work introduces a class of CNNs called deep convolutional generative adversarial networks (DCGANs), that have certain architectural constraints, and demonstrates that they are a strong candidate for unsupervised learning. Expand
Generative Adversarial Nets
We propose a new framework for estimating generative models via an adversarial process, in which we simultaneously train two models: a generative model G that captures the data distribution, and aExpand