Filters








625 Hits in 3.8 sec

Exploiting Multiple EEG Data Domains with Adversarial Learning [article]

David Bethge, Philipp Hallgarten, Ozan Özdenizci, Ralf Mikut, Albrecht Schmidt, Tobias Grosse-Puppendahl
2022 arXiv   pre-print
We argue that multi-source learning via learning domain-invariant representations from multiple data-sources is a viable alternative, as the available data from different EEG data-source domains (e.g.,  ...  We propose an adversarial inference approach to learn data-source invariant representations in this context, enabling multi-source learning for EEG-based brain-computer interfaces.  ...  We present an adversarial learning framework to unify different EEG data-sources and labels for multi-source transfer learning by finding data-source-invariant shareable information for multiple EEG-related  ... 
arXiv:2204.07777v1 fatcat:c3prlcouofcghhzgiksb6rxt5y

A Survey on Deep Learning-Based Short/Zero-Calibration Approaches for EEG-Based Brain–Computer Interfaces

Wonjun Ko, Eunjin Jeon, Seungwoo Jeong, Jaeun Phyo, Heung-Il Suk
2021 Frontiers in Human Neuroscience  
However, EEG has complex patterns and EEG-based BCIs mostly involve a cost/time-consuming calibration phase; thus, acquiring sufficient EEG data is rarely possible.  ...  Recently, deep learning (DL) has had a theoretical/practical impact on BCI research because of its use in learning representations of complex patterns inherent in EEG.  ...  With regard to explicit TL-based methods, there exist two approaches, non-parametric and parametric (i.e., adversarial learning) alignment methods, for a feature space among multiple domains (subjects  ... 
doi:10.3389/fnhum.2021.643386 pmid:34140883 pmcid:PMC8204721 fatcat:3fw5s5xk4fhaxjz4lgby4n72hm

Toward Open-World Electroencephalogram Decoding Via Deep Learning: A Comprehensive Survey [article]

Xun Chen, Chang Li, Aiping Liu, Martin J. McKeown, Ruobing Qian, Z. Jane Wang
2021 arXiv   pre-print
Combining DL with domain-specific knowledge may allow for development of robust approaches to decode brain activity even with small-sample data.  ...  Traditional EEG decoding methods have achieved moderate success when applied to data acquired in static, well-controlled lab environments.  ...  Her research interests include statistical signal processing and machine learning, with applications in digital media and biomedical data analytics.  ... 
arXiv:2112.06654v2 fatcat:roxf5k7ypfcvtdzz3pbho3kdri

Mutual Information-driven Subject-invariant and Class-relevant Deep Representation Learning in BCI [article]

Eunjin Jeon, Wonjun Ko, Jee Seok Yoon, Heung-Il Suk
2020 arXiv   pre-print
In the meantime, it is known that adversarial learning-based domain adaptation methods are prone to negative transfer that disrupts learning generalized feature representations, applicable to diverse domains  ...  To this end, recent studies adopted a transfer learning strategy, especially domain adaptation techniques. Among those, to our knowledge, an adversarial learning has shown its potential in BCIs.  ...  In order to address the limitation, previous studies exploited multiple subjects and/or sessions data simultaneously to train their respective models through transfer learning [11] , [15] .  ... 
arXiv:1910.07747v4 fatcat:k235bsajnja5fkpougktarddbq

Domain-Invariant Representation Learning from EEG with Private Encoders [article]

David Bethge, Philipp Hallgarten, Tobias Grosse-Puppendahl, Mohamed Kari, Ralf Mikut, Albrecht Schmidt, Ozan Özdenizci
2022 arXiv   pre-print
Deep learning based electroencephalography (EEG) signal processing methods are known to suffer from poor test-time generalization due to the changes in data distribution.  ...  approaches with shared parameters.  ...  One approach to achieve this from a deep learning perspective is to extract and exploit domain-invariant representations from multi-channel EEG data.  ... 
arXiv:2201.11613v2 fatcat:e7cupdqw6vfhxgs2h3yzw5mstu

Dynamic Joint Domain Adaptation Network for Motor Imagery Classification

Xiaolin Hong, Qingqing Zheng, Luyan Liu, Peiyin Chen, Kai Ma, Zhongke Gao, Yefeng Zheng
2021 IEEE transactions on neural systems and rehabilitation engineering  
To address these issues, we propose a novel dynamic joint domain adaptation network based on adversarial learning strategy to learn domain-invariant feature representation, and thus improve EEG classification  ...  Index Terms-Deep neural network (DNN), domain adaptation, adversarial learning, electroencephalogram (EEG), motor imagery (MI), brain-computer interface (BCI).  ...  Recently, several deep learning architectures [19] , [33] - [35] have been exploited to learn deep representation and classifier for EEG signals in an end-to-end manner.  ... 
doi:10.1109/tnsre.2021.3059166 fatcat:vxp6txdhsjcopf4odgfe6ne67q

Deep Adversarial Domain Adaptation with Few-Shot Learning for Motor-Imagery Brain-Computer Interface

Chatrin Phunruangsakao, David Achanccaray, Mitsuhiro Hayashibe
2022 IEEE Access  
This study proposes the integration of deep domain adaptation with few-shot learning to address the challenge by leveraging the knowledge from multiple source subjects to enhance the performance of a single  ...  The domain discriminator was used to reduce domain drift, through adversarial training. The classifier predicted the user motor intention, based on EEG features.  ...  In this study, we refer D s to a domain consisting EEG samples with high signal-to-noise ratio (SNR), drawn from multiple subjects; and D t to a domain consisting low-SNR EEG samples, drawn from a single  ... 
doi:10.1109/access.2022.3178100 fatcat:qgvxw4f64rcjlhkieyf7znnb24

Enhancing the Security Privacy of Wearable Brain-Computer Interfaces [article]

Zahra Tarkhani, Lorena Qendro, Malachy O'Connor Brown, Oscar Hill, Cecilia Mascolo, Anil Madhavapeddy
2022 arXiv   pre-print
Wearable BCI setups typically involve a head-mounted sensor connected to a mobile device, combined with ML-based data processing.  ...  In this paper, we: (i) analyse the whole-system security and privacy threats to existing wearable BCI products from an operating system and adversarial machine learning perspective; and (ii) introduce  ...  To prevent this issue, our framework also targets adversarial attacks widely used against EEG-based deep learning models.  ... 
arXiv:2201.07711v1 fatcat:q4m4mzvnzzclnkggony534vz74

EEG-based Brain-Computer Interfaces (BCIs): A Survey of Recent Studies on Signal Sensing Technologies and Computational Intelligence Approaches and their Applications [article]

Xiaotong Gu, Zehong Cao, Alireza Jolfaei, Peng Xu, Dongrui Wu, Tzyy-Ping Jung, Chin-Teng Lin
2020 arXiv   pre-print
Recent technological advances such as wearable sensing devices, real-time data streaming, machine learning, and deep learning approaches have increased interest in electroencephalographic (EEG) based BCI  ...  Brain-Computer Interface (BCI) is a powerful communication tool between users and systems, which enhances the capability of the human brain in communicating and interacting with the environment directly  ...  Thus, transfer learning aims at coping with data that violate this hypothesis by exploiting knowledge acquired while learning a given task for solving a different but related task.  ... 
arXiv:2001.11337v1 fatcat:cmurfjykjja3rdifr7e7cqq3wy

Conditional Adversarial Domain Adaptation Neural Network for Motor Imagery EEG Decoding

Tang, Zhang
2020 Entropy  
Then, a novel conditional domain discriminator is introduced to work as an adversarial with the label classifier to learn commonly shared intra-subjects EEG features.  ...  Recently, deep learning techniques have had great success in EEG decoding because of their prominent ability to learn features from raw EEG signals automatically.  ...  stage, so that the feature extractor can adversarially learn common EEG features between X s and X t by minimizing the data distribution discrepancy.  ... 
doi:10.3390/e22010096 pmid:33285871 pmcid:PMC7516530 fatcat:eygilixplrbzfouxcwxktybjdm

EEG-Based Emotion Recognition Using Regularized Graph Neural Networks [article]

Peixiang Zhong, Di Wang, Chunyan Miao
2020 arXiv   pre-print
In addition, we propose two regularizers, namely node-wise domain adversarial training (NodeDAT) and emotion-aware distribution learning (EmotionDL), to better handle cross-subject EEG variations and noisy  ...  Many existing studies on EEG-based emotion recognition do not fully exploit the topology of EEG channels.  ...  [16] applied domain adversarial training to lower the influence of individual subject on EEG data and obtained improved performance as well.  ... 
arXiv:1907.07835v4 fatcat:qh5dy2y7uzbc3ep2ozvr4zjac4

Benchmarking Domain Generalization on EEG-based Emotion Recognition [article]

Yan Li, Hao Chen, Jake Zhao, Haolan Zhang, Jinpeng Li
2022 arXiv   pre-print
DG learns how to generalize to unseen target domains by leveraging knowledge from multiple source domains, which provides a new possibility to train general models.  ...  The DA methods assume that calibration data (although unlabeled) exists in the target domain (new user).  ...  DG helps extract domain-invariant features by exploiting domain differences across multiple source subjects without acquiring any extra target data.  ... 
arXiv:2204.09016v1 fatcat:ogppjbuerjglfd7ufxujkgo7iq

Federated Transfer Learning: concept and applications [article]

Sudipan Saha, Tahir Ahmad
2021 arXiv   pre-print
However, in most industries data exists in form of isolated islands, with limited scope of sharing between different organizations. This is an hindrance to the further development of AI.  ...  Among different variants of the federated learning, noteworthy is federated transfer learning (FTL) that allows knowledge to be transferred across domains that do not have many overlapping features and  ...  Privacy-preserving FTL typically involves multiple parties with emphasis on security guarantees to perform machine learning.  ... 
arXiv:2010.15561v3 fatcat:3udixrhta5btlb7w7r4fomwpzu

Guest Editorial: Special Issue on Deep Representation and Transfer Learning for Smart and Connected Health

Vasile Palade, Stefan Wermter, Ariel Ruiz-Garcia, Antonio De Padua Braga, Clive Cheong Took
2021 IEEE Transactions on Neural Networks and Learning Systems  
In the article "Deep representation-based domain adaptation for nonstationary EEG classification," Zhao et al. address this issue by treating multiple subjects as the source domain, and a single subject  ...  Gu et al. also look at exploiting data commonalities in RTL.  ... 
doi:10.1109/tnnls.2021.3049931 fatcat:g2kdub6kmnep5o3rx3sqiacexm

Deep Neural Network with Joint Distribution Matching for Cross-Subject Motor Imagery Brain-Computer Interfaces

Xianghong Zhao, Jieyu Zhao, Cong Liu, Weiming Cai
2020 BioMed Research International  
Experiments demonstrate that it can align source and target data according to the class they belong to. It has a direct relationship with classification accuracy and works well for transferring.  ...  In this paper, the source subject's data are explored to perform calibration for target subjects.  ...  Acknowledgments We are thankful to those who helped with the experiments and gave suggestions during the research. This work was supported in part by the National Natural Science  ... 
doi:10.1155/2020/7285057 pmid:32185216 pmcid:PMC7060420 fatcat:bfzgrhhjljcz7hf3c274bjm6ue
« Previous Showing results 1 — 15 out of 625 results