Augmenting The Size of EEG datasets Using Generative Adversarial Networks

Abdelfattah, Sherif; Abdelrahman, Ghodai; Wang, Min

doi:10.1109/ijcnn.2018.8489727

Cited by 89 publications

(56 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, some studies have demonstrated that generative adversarial networks (GANs) are well suited for EEG-DA [25,40,41]. However, few studies were conducted on the analysis of MI signals.…”

Section: Electroencephalogram (Eeg) Pattern Augmentation Methods Limimentioning

confidence: 99%

See 1 more Smart Citation

Data Augmentation for Motor Imagery Signal Classification Based on a Hybrid Neural Network

Zhang

Han

et al. 2020

Sensors

View full text Add to dashboard Cite

As an important paradigm of spontaneous brain-computer interfaces (BCIs), motor imagery (MI) has been widely used in the fields of neurological rehabilitation and robot control. Recently, researchers have proposed various methods for feature extraction and classification based on MI signals. The decoding model based on deep neural networks (DNNs) has attracted significant attention in the field of MI signal processing. Due to the strict requirements for subjects and experimental environments, it is difficult to collect large-scale and high-quality electroencephalogram (EEG) data. However, the performance of a deep learning model depends directly on the size of the datasets. Therefore, the decoding of MI-EEG signals based on a DNN has proven highly challenging in practice. Based on this, we investigated the performance of different data augmentation (DA) methods for the classification of MI data using a DNN. First, we transformed the time series signals into spectrogram images using a short-time Fourier transform (STFT). Then, we evaluated and compared the performance of different DA methods for this spectrogram data. Next, we developed a convolutional neural network (CNN) to classify the MI signals and compared the classification performance of after DA. The Fréchet inception distance (FID) was used to evaluate the quality of the generated data (GD) and the classification accuracy, and mean kappa values were used to explore the best CNN-DA method. In addition, analysis of variance (ANOVA) and paired t-tests were used to assess the significance of the results. The results showed that the deep convolutional generative adversarial network (DCGAN) provided better augmentation performance than traditional DA methods: geometric transformation (GT), autoencoder (AE), and variational autoencoder (VAE) (p < 0.01). Public datasets of the BCI competition IV (datasets 1 and 2b) were used to verify the classification performance. Improvements in the classification accuracies of 17% and 21% (p < 0.01) were observed after DA for the two datasets. In addition, the hybrid network CNN-DCGAN outperformed the other classification methods, with average kappa values of 0.564 and 0.677 for the two datasets.

show abstract

Section: Electroencephalogram (Eeg) Pattern Augmentation Methods Limimentioning

confidence: 99%

“…However, the training process of AE is unstable and prone to produce meaningless results [ 39 ]. Recently, some studies have demonstrated that generative adversarial networks (GANs) are well suited for EEG-DA [ 25 , 40 , 41 ]. However, few studies were conducted on the analysis of MI signals.…”

Section: Introductionmentioning

confidence: 99%

Data Augmentation for Motor Imagery Signal Classification Based on a Hybrid Neural Network

Zhang

Han

et al. 2020

Sensors

View full text Add to dashboard Cite

show abstract

“…For example, a novel GAN model [26] was recently proposed, which learned the statistical characteristics of the EEG and increased the size of datasets by generating synthesis samples to improve classification performance. Also, a new EEG‐based framework [27], named Conditional Wasserstein GAN, was proposed to enhance emotion recognition by generating high‐quality synthetic EEG data based using the SEED and DEAP datasets.…”

Section: Deep Learning For Eeg‐based Bcimentioning

confidence: 99%

A review of artificial intelligence for EEG‐based brain−computer interfaces and applications

Cao

2020

Brain Science Advances

View full text Add to dashboard Cite

The advancement in neuroscience and computer science promotes the ability of the human brain to communicate and interact with the environment, making brain–computer interface (BCI) top interdisciplinary research. Furthermore, with the modern technology advancement in artificial intelligence (AI), including machine learning (ML) and deep learning (DL) methods, there is vast growing interest in the electroencephalogram (EEG)‐based BCIs for AI‐related visual, literal, and motion applications. In this review study, the literature on mainstreams of AI for the EEG‐based BCI applications is investigated to fill gaps in the interdisciplinary BCI field. Specifically, the EEG signals and their main applications in BCI are first briefly introduced. Next, the latest AI technologies, including the ML and DL models, are presented to monitor and feedback human cognitive states. Finally, some BCI‐inspired AI applications, including computer vision, natural language processing, and robotic control applications, are presented. The future research directions of the EEG‐based BCI are highlighted in line with the AI technologies and applications.

show abstract

“…This strategy was also used by Zhang et al [30] to increase the dataset size and train a deep-learning network. Another approach to the problem is to use generative adversarial networks to generate artificial EEG signals [51], [52]. However, we tried to use this strategy to train a deep neural network for the workload dataset, but the achieved accuracy was still worst than the one obtained with classical CSP or FBCSP methods.…”

Section: Introductionmentioning

confidence: 99%

WLnet: Towards an Approach for Robust Workload Estimation Based on Shallow Neural Networks

Sun¹,

Duan

et al. 2021

IEEE Access

View full text Add to dashboard Cite

Augmenting The Size of EEG datasets Using Generative Adversarial Networks

Cited by 89 publications

References 16 publications

Data Augmentation for Motor Imagery Signal Classification Based on a Hybrid Neural Network

Data Augmentation for Motor Imagery Signal Classification Based on a Hybrid Neural Network

A review of artificial intelligence for EEG‐based brain−computer interfaces and applications

WLnet: Towards an Approach for Robust Workload Estimation Based on Shallow Neural Networks

Contact Info

Product

Resources

About