Subject-Invariant Eeg Representation Learning For Emotion Recognition

Rayatdoost, Soheil; Yin, Yufeng; Rudrauf, David; Soleymani, Mohammad

doi:10.1109/icassp39728.2021.9414496

Cited by 10 publications

(6 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thus we have to employ DA methods from other fields. The maximum independence domain adaptation (MIDA) (Yan et al, 2017 ), model-agnostic learning of semantic features (MASF), conditional deep convolutional generative adversarial networks (C-DCGANs) (Zhang et al, 2021 ) and subject-invariant domain adaption (SIDA) (Rayatdoost et al, 2021 ) are introduced to verify the advantage of our model. The sensitivity and FPR are provided in Tables 5 , 6 .…”

Section: Resultsmentioning

confidence: 99%

Seizure Prediction in EEG Signals Using STFT and Domain Adaptation

Peng

Song²,

Lü

et al. 2022

Front. Neurosci.

View full text Add to dashboard Cite

Epileptic seizure prediction is one of the most used therapeutic adjuvant strategies for drug-resistant epilepsy. Conventional approaches commonly collect training and testing samples from the same patient due to inter-individual variability. However, the challenging problem of domain shift between various subjects remains unsolved, resulting in a low conversion rate to the clinic. In this work, a domain adaptation (DA)-based model is proposed to circumvent this issue. The short-time Fourier transform (STFT) is employed to extract the time-frequency features from raw EEG data, and an autoencoder is developed to map these features into high-dimensional space. By minimizing the inter-domain distance in the embedding space, this model learns the domain-invariant information, such that the generalization ability is improved by distribution alignment. Besides, to increase the feasibility of its application, this work mimics the data distribution under the clinical sampling situation and tests the model under this condition, which is the first study that adopts the assessment strategy. Experimental results on both intracranial and scalp EEG databases demonstrate that this method can minimize the domain gap effectively compared with previous approaches.

show abstract

Section: Resultsmentioning

confidence: 99%

Seizure Prediction in EEG Signals Using STFT and Domain Adaptation

Peng

Song²,

Lü

et al. 2022

Front. Neurosci.

View full text Add to dashboard Cite

show abstract

“…HIVE-CODAs include seven constituent modules: subjectinvariant domain adaption (SIDA) [37], conditional deep convolutional generative adversarial networks (C-DCGANs) [38], plug-and-play domain adaptation (PPDA) [39], maximum independence domain adaptation (MIDA) [40], maximum mean discrepancy-adversarial autoencoders (MMD-AAEs) [41], model-agnostic learning of semantic features (MASF) [42], and cone manifold domain adaptation (CMDA) [43]. The modular hierarchical structure is depicted in Figure 4.…”

Section: Modular Hierarchical Structurementioning

confidence: 99%

“…2) SIDA: We also estimated the performance of SIDA on epileptic EEG, which combines power spectral density (PSD) features and adversarial learning [37]. SIDA focuses on the extraction of the invariant representations among different domains.…”

Section: ) Mmd-aaementioning

confidence: 99%

See 1 more Smart Citation

Seizure Prediction With HIVE-CODAs: The Hierarchical Vote Collective of Domain Adaptation Methods

Peng

2022

Front. Phys.

View full text Add to dashboard Cite

Epileptic seizure prediction is one of the most used therapeutic adjuvant strategies for drug-resistant epilepsy. Conventional methods are usually trained and tested on the same patient due to the interindividual variability. However, the challenging problem of the domain shift between different subjects remains unsolved, resulting in low prevalence of clinical application. In this study, a generic model based on the domain adaptation (DA) technique is proposed to alleviate such problems. Ensemble learning is employed by developing a hierarchical vote collective of seven DA modules over multi-modality data, such that the predictive performance is improved by training multiple models. Moreover, to increase the feasibility of its implementation, this study mimics the data distribution of clinical sampling and tests the model under this simulated realistic condition. Based on the performance of seven subnetworks, the applicability of each DA algorithm for seizure prediction is evaluated, which is the first study that provides the assessment. Experimental results on both intracranial and scalp EEG databases demonstrate that this method can reduce the domain gap effectively compared with previous studies.

show abstract

“…In the related fields of EEG emotion recognition and EEG motor imagery, it has been shown that explicitly modeling subject-invariant features, by using an adversarial layer to remove all subject information from the latent features, improves generalization of models and benefits classification accuracy across subjects [9,10,11]. In [12,13], the authors have proposed to include Variational Autoencoders (VAE) [14] and have found that VAE's may improve subjectindependent performance, as the latent space is conditioned to follow a Gaussian distribution, and are advantageous in the unsupervised modeling of EEG brain neural signals.…”

Section: Introductionmentioning

confidence: 99%

Learning Subject-Invariant Representations from Speech-Evoked EEG Using Variational Autoencoders

Bollens,

Francart,

Van Hamme

2022

Preprint

View full text Add to dashboard Cite

The electroencephalogram (EEG) is a powerful method to understand how the brain processes speech. Linear models have recently been replaced for this purpose with deep neural networks and yield promising results. In related EEG classification fields, it is shown that explicitly modeling subject-invariant features improves generalization of models across subjects and benefits classification accuracy. In this work, we adapt factorized hierarchical variational autoencoders to exploit parallel EEG recordings of the same stimuli. We model EEG into two disentangled latent spaces. Subject accuracy reaches 98.96% and 1.60% on respectively the subject and content latent space, whereas binary content classification experiments reach an accuracy of 51.51% and 62.91% on respectively the subject and content latent space.

show abstract

Subject-Invariant Eeg Representation Learning For Emotion Recognition

Cited by 10 publications

References 16 publications

Seizure Prediction in EEG Signals Using STFT and Domain Adaptation

Seizure Prediction in EEG Signals Using STFT and Domain Adaptation

Seizure Prediction With HIVE-CODAs: The Hierarchical Vote Collective of Domain Adaptation Methods

Learning Subject-Invariant Representations from Speech-Evoked EEG Using Variational Autoencoders

Contact Info

Product

Resources

About