Multi-Source Decentralized Transfer for Privacy-Preserving BCIs

Zhang, Wen; Wang, Ziwei; Wu, Dongrui

doi:10.1109/tnsre.2022.3207494

Cited by 11 publications

(6 citation statements)

References 63 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Zuo et al [29] proposed attentionbased multi-source domain adaptation to cope with negative transfer. Zhang et al [30] proposed source transferability estimation to estimate the contribution of each source domain.…”

Section: Negative Transfer Mitigationmentioning

confidence: 99%

“…We compared the proposed SDS-GDA-TASA with five categories of baselines, including Traditional classifiers, Neural networks, Traditional TL, Meta-Learning, and Deep TL: The network architecture of MLP as proposed in [30] is shown in table 4, and it used the manually extracted features in table 3. (c) Traditional TL, i.e.…”

Section: Algorithmsmentioning

confidence: 99%

“…All MLP-based shallow models were trained for 10 epochs, same as [30], with learning rate 0.001 and momentum 0.9. 10% random samples of the source domains were combined and used to identify the optimal λ 1 and λ 2 in (7).…”

Section: Algorithmsmentioning

confidence: 99%

See 2 more Smart Citations

Unsupervised domain adaptation for cross-patient seizure classification

Wang,

Zhang,

et al. 2023

J. Neural Eng.

Self Cite

View full text Add to dashboard Cite

Objective. Epileptic seizure is a chronic neurological disease affecting millions of patients. Electroencephalogram (EEG) is the gold standard in epileptic seizure classification. However, its low signal-to-noise ratio, strong non-stationarity, and large individual difference nature make it difficult to directly extend the seizure classification model from one patient to another. This paper considers multi-source unsupervised domain adaptation for cross-patient EEG-based seizure classification, i.e. there are multiple source patients with labeled EEG data, which are used to label the EEG trials of a new patient. Approach. We propose an source domain selection (SDS)-global domain adaptation (GDA)-target agent subdomain adaptation (TASA) approach, which includes SDS to filter out dissimilar source domains, GDA to align the overall distributions of the selected source domains and the target domain, and TASA to identify the most similar source domain to the target domain so that its labels can be utilized. Main results. Experiments on two public seizure datasets demonstrated that SDS-GDA-TASA outperformed 13 existing approaches in unsupervised cross-patient seizure classification. Significance. Our approach could save clinicians plenty of time in labeling EEG data for epilepsy patients, greatly increasing the efficiency of seizure diagnostics.

show abstract

Section: Negative Transfer Mitigationmentioning

confidence: 99%

Section: Algorithmsmentioning

confidence: 99%

See 1 more Smart Citation

Unsupervised domain adaptation for cross-patient seizure classification

Wang,

Zhang,

et al. 2023

J. Neural Eng.

Self Cite

View full text Add to dashboard Cite

show abstract

“…In recent years, deep learning has emerged as a promising approach for analyzing EEG signals. Deep learning models have demonstrated significant success in various EEG-based applications, such as sleep staging [12], [13], seizure detection [14], [15], motor imagery (MI) [16], [17], or emotion classification [18], [19]. However, the limited availability of diverse and high-quality data for training the models presents a major challenge when applying deep learning to EEG signal analysis [20].…”

Section: Introductionmentioning

confidence: 99%

Toward Domain-Free Transformer for Generalized EEG Pre-Training

Kim,

Lee,

Kwak

et al. 2024

IEEE Trans. Neural Syst. Rehabil. Eng.

View full text Add to dashboard Cite

Electroencephalography (EEG) signals are the brain signals acquired using the non-invasive approach. Owing to the high portability and practicality, EEG signals have found extensive application in monitoring human physiological states across various domains. In recent years, deep learning methodologies have been explored to decode the intricate information embedded in EEG signals. However, since EEG signals are acquired from humans, it has issues with acquiring enormous amounts of data for training the deep learning models. Therefore, previous research has attempted to develop pre-trained models that could show significant performance improvement through fine-tuning when data are scarce. Nonetheless, existing pre-trained models often struggle with constraints, such as the necessity to operate within datasets of identical configurations or the need to distort the original data to apply the pre-trained model. In this paper, we proposed the domainfree transformer, called DFformer, for generalizing the EEG pre-trained model. In addition, we presented the pre-trained model based on DFformer, which is capable of seamless integration across diverse datasets without necessitating architectural modification or data distortion. The proposed model achieved competitive performance across motor imagery and sleep stage classification datasets. Notably, even when fine-tuned on datasets distinct from the pre-training phase, DFformer demonstrated marked performance enhancements. Hence, we demonstrate the potential of DFformer to overcome the conventional limitations in pretrained model development, offering robust applicability across a spectrum of domains.

show abstract

“…Zhang and Wu [20] solved the same problem using lightweight source-free transfer. Zhang et al [21] further proposed unsupervised privacy-preserving multi-source decentralized transfer and demonstrated its effectiveness in MI classification and EEG-based emotion classification. Li et al [22] proposed multi-domain modelagnostic meta-learning for privacy-preserving crosssubject and few-shot MI/ERP classification.…”

mentioning

confidence: 99%

User Identity Protection in EEG-Based Brain–Computer Interfaces

Meng,

Jiang,

Huang

et al. 2023

IEEE Trans. Neural Syst. Rehabil. Eng.

Self Cite

View full text Add to dashboard Cite

A brain-computer interface (BCI) establishes a direct communication pathway between the brain and an external device. Electroencephalogram (EEG) is the most popular input signal in BCIs, due to its convenience and low cost. Most research on EEG-based BCIs focuses on the accurate decoding of EEG signals; however, EEG signals also contain rich private information, e.g., user identity, emotion, and so on, which should be protected. This paper first exposes a serious privacy problem in EEG-based BCIs, i.e., the user identity in EEG data can be easily learned so that different sessions of EEG data from the same user can be associated together to more reliably mine private information. To address this issue, we further propose two approaches to convert the original EEG data into identity-unlearnable EEG data, i.e., removing the user identity information while maintaining the good performance on the primary BCI task. Experiments on seven EEG datasets from five different BCI paradigms showed that on average the generated identity-unlearnable EEG data can reduce the user identification accuracy from 70.01% to at most 21.36%, greatly facilitating user privacy protection in EEG-based BCIs.

show abstract

Multi-Source Decentralized Transfer for Privacy-Preserving BCIs

Cited by 11 publications

References 63 publications

Unsupervised domain adaptation for cross-patient seizure classification

Unsupervised domain adaptation for cross-patient seizure classification

Toward Domain-Free Transformer for Generalized EEG Pre-Training

User Identity Protection in EEG-Based Brain–Computer Interfaces

Contact Info

Product

Resources

About