EEGANet: Removal of Ocular Artifacts From the EEG Signal Using Generative Adversarial Networks

Sawangjai, Phattarapong; Trakulruangroj, Manatsanan; Boonnag, Chiraphat; Piriyajitakonkij, Maytus; Tripathy, Rajesh Kumar; Sudhawiyangkul, Thapanun; Wilaiprasitporn, Theerawit

doi:10.1109/jbhi.2021.3131104

Cited by 39 publications

(14 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This system still has few limitations due to time duration of EEG recording which is 2s-long and also the size of dataset to be increased in deep learning applications for better training. Another deep learning method called generative adversarial network (GAN) is also used to remove the ocular artifact as shown in [87]. GAN gave good performance compared to traditional state-of-the-art methods.…”

Section: Ica-cca 11%mentioning

confidence: 99%

EEG artifacts detection and removal techniques for brain computer interface applications: a systematic review

2022

IJATEE

View full text Add to dashboard Cite

The artifacts may affect the signal in spectral, temporal and in few cases it affects spatial domain as well which makes it difficult to process. In this case, simple filtering is not sufficient to completely remove the artifacts during pre-processing. Hence, many hybrid methods were developed but still there is no single method to detect and remove all types of artifacts [2].In this context, this paper provides a systematic literature review on types of artifacts, existing methods and comparative analysis on available methods. Further, performance evaluation metrics and available open-source tools for artifact removal are also discussed. The preferred reporting items for

show abstract

Section: Ica-cca 11%mentioning

confidence: 99%

EEG artifacts detection and removal techniques for brain computer interface applications: a systematic review

2022

IJATEE

View full text Add to dashboard Cite

show abstract

“…The effect of model learning is equivalent to that of experts separating, and it can automatically process long-term collected EEG signals. Sawangjai et al [27] put forward the generation countermeasure network model EEGANET for EEG de-noising in 2021. Based on the discriminator, they can judge whether it is the mutual confrontation between artifacts and artifact signals generated by the generator, and constantly learn to improve the recognition ability of EEG artifacts.…”

Section: Deep Learning Artifact Eliminationmentioning

confidence: 99%

Artifact Elimination of Eeg Signals Based on Deep Learning: Survey

Yan¹,

Chen²

2022

Int.J.Res.Publ.Rev.

View full text Add to dashboard Cite

Electroencephalogram (EEG) plays an important role in measuring human status and activities. EEG signals come from weak currents and are very vulnerable to artifact pollution, which affects the performance of many EEG tasks. It is crucial to develop methods that can effectively identify and remove artifacts. In the past, researchers have proposed a variety of methods to eliminate artifacts, but there is still no method to achieve the best effect. With the rapid development of deep learning, the new method has made excellent progress in eliminating artifacts. Compared with traditional methods, it is fast and can be automatically processed. This paper explores a new method to eliminate artifacts using deep learning technology. First, it discusses the characteristics and types of artifacts of EEG data, reviews the traditional elimination methods, then introduces the application of new and new methods of deep learning, and introduces the relevant data sets. In the future research, the method of artifact elimination relying on data automation has great potential.

show abstract

“…Sun et al [42] reported a residual-connection-based DCNN for reducing ocular, muscular, and cardiac abnormalities from noisy EEG data. Recently, authors of [43] proposed EEGANet, a framework based on generative adversarial networks (GANs) for the removal of ocular artifacts from EEG data whereas in [44], the k-means algorithm in combination with the SSA technique was proposed for the reduction of eye blink artifacts. Although a fair share of studies is existent for the removal of ocular, muscle, and cardiac artifacts from EEG recordings to the best of our knowledge, the removal of motion artifacts using deep learning models has not been investigated to date.…”

Section: Introductionmentioning

confidence: 99%

MLMRS-Net: Electroencephalography (EEG) motion artifacts removal using a multi-layer multi-resolution spatially pooled 1D signal reconstruction network

Mahmud

Hossain

Chowdhury

et al. 2022

Neural Comput & Applic

View full text Add to dashboard Cite

Electroencephalogram (EEG) signals suffer substantially from motion artifacts when recorded in ambulatory settings utilizing wearable sensors. Because the diagnosis of many neurological diseases is heavily reliant on clean EEG data, it is critical to eliminate motion artifacts from motion-corrupted EEG signals using reliable and robust algorithms. Although a few deep learning-based models have been proposed for the removal of ocular, muscle, and cardiac artifacts from EEG data to the best of our knowledge, there is no attempt has been made in removing motion artifacts from motion-corrupted EEG signals: In this paper, a novel 1D convolutional neural network (CNN) called multi-layer multi-resolution spatially pooled (MLMRS) network for signal reconstruction is proposed for EEG motion artifact removal. The performance of the proposed model was compared with ten other 1D CNN models: FPN, LinkNet, UNet, UNet+, UNetPP, UNet3+, AttentionUNet, MultiResUNet, DenseInceptionUNet, and AttentionUNet++ in removing motion artifacts from motion-contaminated single-channel EEG signal. All the eleven deep CNN models are trained and tested using a single-channel benchmark EEG dataset containing 23 sets of motion-corrupted and reference ground truth EEG signals from PhysioNet. Leave-one-out cross-validation method was used in this work. The performance of the deep learning models is measured using three well-known performance matrices viz. mean absolute error (MAE)-based construction error, the difference in the signal-to-noise ratio (ΔSNR), and percentage reduction in motion artifacts (η). The proposed MLMRS-Net model has shown the best denoising performance, producing an average ΔSNR, η, and MAE values of 26.64 dB, 90.52%, and 0.056, respectively, for all 23 sets of EEG recordings. The results reported using the proposed model outperformed all the existing state-of-the-art techniques in terms of average η improvement.

show abstract

EEGANet: Removal of Ocular Artifacts From the EEG Signal Using Generative Adversarial Networks

Cited by 39 publications

References 37 publications

EEG artifacts detection and removal techniques for brain computer interface applications: a systematic review

EEG artifacts detection and removal techniques for brain computer interface applications: a systematic review

Artifact Elimination of Eeg Signals Based on Deep Learning: Survey

MLMRS-Net: Electroencephalography (EEG) motion artifacts removal using a multi-layer multi-resolution spatially pooled 1D signal reconstruction network

Contact Info

Product

Resources

About