EEG Signal Reconstruction Using a Generative Adversarial Network With Wasserstein Distance and Temporal-Spatial-Frequency Loss

Luo, Tian-jian; Fan, Yue; Chen, Lifei; Guo, Ge; Zhou, Changle

doi:10.3389/fninf.2020.00015

Cited by 51 publications

(33 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…GANs are primarily used in the computer vision field which processes two-dimensional (2-D) data. In addition, there are some studies in different disciplines that attempted to use GANs for one-dimensional (1-D) data generation and reconstruction for different purposes (Truong and Yanushkevich, 2019;Kuo et al, 2020;Luo et al, 2020;Wulan et al, 2020;Sabir et al, 2021;Wang et al, 2021). In the SHM field of non-civil structures, some studies of GAN-based 1-D data generation, reconstruction, and then training an ML classifier are introduced (Gao et al, 2019;Shao et al, 2019;Guo et al, 2020;Zhang et al, 2021).…”

Section: Motivation and Objectivementioning

confidence: 99%

Generative Adversarial Networks for Data Generation in Structural Health Monitoring

Luleci

Çatbaş

Avcı

2022

Front. Built Environ.

View full text Add to dashboard Cite

Structural Health Monitoring (SHM) has been continuously benefiting from the advancements in the field of data science. Various types of Artificial Intelligence (AI) methods have been utilized to assess and evaluate civil structures. In AI, Machine Learning (ML) and Deep Learning (DL) algorithms require plenty of datasets to train; particularly, the more data DL models are trained with, the better output it yields. Yet, in SHM applications, collecting data from civil structures through sensors is expensive and obtaining useful data (damage associated data) is challenging. In this paper, one-dimensional (1-D) Wasserstein loss Deep Convolutional Generative Adversarial Networks using Gradient Penalty (1-D WDCGAN-GP) is utilized to generate damage-associated vibration datasets that are similar to the input. For the purpose of vibration-based damage diagnostics, a 1-D Deep Convolutional Neural Network (1-D DCNN) is built, trained, and tested on both real and generated datasets. The classification results from the 1-D DCNN on both datasets resulted in being very similar to each other. The presented work in this paper shows that, for the cases of insufficient data in DL or ML-based damage diagnostics, 1-D WDCGAN-GP can successfully generate data for the model to be trained on.

show abstract

Section: Motivation and Objectivementioning

confidence: 99%

Generative Adversarial Networks for Data Generation in Structural Health Monitoring

Luleci

Çatbaş

Avcı

2022

Front. Built Environ.

View full text Add to dashboard Cite

show abstract

“…By comparing the above EEG feature maps, after extracting the spectrum feature maps by the improved Morlet wavelet, the spatial-frequency feature maps extracted by multi-layers R3DCNNs model, which can obtain stable discriminant feature maps under the effect of error back-propagation algorithm (Luo et al, 2020). The stable discriminant feature maps corresponding to different brain's sensorimotor region activated tasks then used to extract spatial-frequency-sequential relationships by subsequent Bi-GRUs classification.…”

Section: Multidimensional Features Fusion Algorithmmentioning

confidence: 99%

A novel multi-dimensional features fusion algorithm for the EEG signal recognition of brain's sensorimotor region activated tasks

Wei

Lin

2020

IJICC

View full text Add to dashboard Cite

PurposeAiming at the shortcomings of EEG signals generated by brain's sensorimotor region activated tasks, such as poor performance, low efficiency and weak robustness, this paper proposes an EEG signals classification method based on multi-dimensional fusion features.Design/methodology/approachFirst, the improved Morlet wavelet is used to extract the spectrum feature maps from EEG signals. Then, the spatial-frequency features are extracted from the PSD maps by using the three-dimensional convolutional neural networks (3DCNNs) model. Finally, the spatial-frequency features are incorporated to the bidirectional gated recurrent units (Bi-GRUs) models to extract the spatial-frequency-sequential multi-dimensional fusion features for recognition of brain's sensorimotor region activated task.FindingsIn the comparative experiments, the data sets of motor imagery (MI)/action observation (AO)/action execution (AE) tasks are selected to test the classification performance and robustness of the proposed algorithm. In addition, the impact of extracted features on the sensorimotor region and the impact on the classification processing are also analyzed by visualization during experiments.Originality/valueThe experimental results show that the proposed algorithm extracts the corresponding brain activation features for different action related tasks, so as to achieve more stable classification performance in dealing with AO/MI/AE tasks, and has the best robustness on EEG signals of different subjects.

show abstract

“…The link between EEG data associated with emotions, a coarse label, and a facial expression image was established in the study [ 34 ] using a conditional generative adversarial network (cGAN). The authors of [ 35 ] recommend using a Generative Adversarial Network with Wasserstein Distance and Temporal-Spatial-Frequency Loss to reconstruct EEG signals. Luo et al developed a Conditional Wasserstein GAN (CWGAN) framework for EEG data augmentation to improve EEG-based emotion recognition in order to overcome the shortage of data when assessing emotions [ 36 ].…”

Section: Introductionmentioning

confidence: 99%

Deep Convolutional Neural Network-Based Visual Stimuli Classification Using Electroencephalography Signals of Healthy and Alzheimer’s Disease Subjects

Komolovaitė

Maskeliūnas

Damaševičius

2022

Life

View full text Add to dashboard Cite

Visual perception is an important part of human life. In the context of facial recognition, it allows us to distinguish between emotions and important facial features that distinguish one person from another. However, subjects suffering from memory loss face significant facial processing problems. If the perception of facial features is affected by memory impairment, then it is possible to classify visual stimuli using brain activity data from the visual processing regions of the brain. This study differentiates the aspects of familiarity and emotion by the inversion effect of the face and uses convolutional neural network (CNN) models (EEGNet, EEGNet SSVEP (steady-state visual evoked potentials), and DeepConvNet) to learn discriminative features from raw electroencephalography (EEG) signals. Due to the limited number of available EEG data samples, Generative Adversarial Networks (GAN) and Variational Autoencoders (VAE) are introduced to generate synthetic EEG signals. The generated data are used to pretrain the models, and the learned weights are initialized to train them on the real EEG data. We investigate minor facial characteristics in brain signals and the ability of deep CNN models to learn them. The effect of face inversion was studied, and it was observed that the N170 component has a considerable and sustained delay. As a result, emotional and familiarity stimuli were divided into two categories based on the posture of the face. The categories of upright and inverted stimuli have the smallest incidences of confusion. The model’s ability to learn the face-inversion effect is demonstrated once more.

show abstract

EEG Signal Reconstruction Using a Generative Adversarial Network With Wasserstein Distance and Temporal-Spatial-Frequency Loss

Cited by 51 publications

References 37 publications

Generative Adversarial Networks for Data Generation in Structural Health Monitoring

Generative Adversarial Networks for Data Generation in Structural Health Monitoring

A novel multi-dimensional features fusion algorithm for the EEG signal recognition of brain's sensorimotor region activated tasks

Deep Convolutional Neural Network-Based Visual Stimuli Classification Using Electroencephalography Signals of Healthy and Alzheimer’s Disease Subjects

Contact Info

Product

Resources

About