Different Set Domain Adaptation for Brain-Computer Interfaces: A Label Alignment Approach

He, He; Wu, Dongrui

doi:10.1109/tnsre.2020.2980299

Cited by 67 publications

(34 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We are currently exploring extensions of HTNet for a variety of applications such as cross-frequency coupling [94, 95], long-term state decoding [6], cross-task decoding [96], and data-driven regression [97, 98]. In addition, other decoding measures could be substituted for the Hilbert transform, including non-Fourier methods [99, 100], and more complex interpolation schemes could be used to generate the projection matrix by incorporating participant-specific cortical anatomy [101, 102].…”

Section: Discussionmentioning

confidence: 99%

Generalized neural decoders for transfer learning across participants and recording modalities

Peterson

Steine-Hanson

Davis

et al. 2020

Preprint

View full text Add to dashboard Cite

Advances in neural decoding have enabled brain-computer interfaces to perform increasingly complex and clinically-relevant tasks. However, such decoders are often tailored to specific participants, days, and recording sites, limiting their practical long-term usage. Therefore, a fundamental challenge is to develop neural decoders that can robustly train on pooled, multi-participant data and generalize to new participants. We introduce a new decoder, HTNet, which uses a convolutional neural network with two innovations: (1) a Hilbert transform that computes spectral power at data-driven frequencies and (2) a layer that projects electrode-level data onto predefined brain regions. The projection layer critically enables applications with intracranial electrocorticography (ECoG), where electrode locations are not standardized and vary widely across participants. We trained HTNet to decode arm movements using pooled ECoG data from 11 of 12 participants and tested performance on unseen ECoG or electroencephalography (EEG) participants; these pretrained models were also subsequently fine-tuned to each test participant. HTNet outperformed state-of-the-art decoders when tested on unseen participants, even when a different recording modality was used. By fine-tuning these generalized HTNet decoders, we achieved performance approaching the best tailored decoders with as few as 50 ECoG or 20 EEG events. We were also able to interpret HTNet's trained weights and demonstrate its ability to extract physiologically-relevant features. By generalizing to new participants and recording modalities, robustly handling variations in electrode placement, and allowing participant-specific fine-tuning with minimal data, HTNet is applicable across a broader range of neural decoding applications compared to current state-of-the-art decoders.

show abstract

Section: Discussionmentioning

confidence: 99%

Generalized neural decoders for transfer learning across participants and recording modalities

Peterson

Steine-Hanson

Davis

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…The choice of a reference matrix is crucial because it defines the center of all single-trial EEG signals from the same subject. Data alignment can be conducted in Riemannian space (RA) [23] or Euclidean space (EA) [24]. In the study, we propose a hybrid Riemannian and Euclidean space data alignment (REA) method.…”

Section: B Data Alignmentmentioning

confidence: 99%

“…2) Data alignment in Euclidean space: EA employs Euclidean mean of covariance matrices from all EEG signals in task periods as a reference matrix, in which the subject conducts mental tasks of motor imagery. The reference matrix of a subject is strictly equivalent to an identity matrix [24]. Different from RA, EA aligns EEG trials instead of covariance matrices because in Euclidean space, classification is based on spatially filtered EEG trials.…”

Section: B Data Alignmentmentioning

confidence: 99%

“…To alleviate the problem, Lotte et al used a subset of automatically selected subjects to formulate a weighted sum of covariance matrices [20]. Another method for improving the TL in BCIs is to align EEG data from different subjects [22][23][24]. Rodrigues et al [22] proposed a method based on Procrustes analysis for matching the statistical distributions of two data sets using geometrical transformations (translation, scaling and rotation) over the data points.…”

Section: Introductionmentioning

confidence: 99%

“…The RA can improve the performance of the MDM classifier by making use of subsidiary data from other subjects. Subsequently, He et al [24] proposed a Euclidean space data alignment (EA) approach that aligns the EEG trials of a subject with the reference matrix estimated by the EEG data in task states without using the label information. The aligned trials are then transferred to the target subject for creating a classification model with CSP and LDA in Euclidean space.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Transfer Learning Based on Hybrid Riemannian and Euclidean Space Data Alignment and Subject Selection in Brain-Computer Interfaces

Wei

Chen

et al. 2021

IEEE Access

View full text Add to dashboard Cite

Transfer learning is a promising approach for reducing training time in a brain-computer interface (BCI). However, how to effectively transfer data from previous users to a new user poses a huge challenge. This paper presents a novel transfer learning approach that combines data alignment and source subject selection for motor imagery (MI) based BCIs. The former is achieved by a reference matrix from the regularization of the two reference matrices estimated in Riemannian and Euclidean space respectively, whereas the latter is implemented by a modified sequential forward floating-point search algorithm. The aligned training data from chosen source subjects are used for creating a classification model based on either spatial covariance matrices in Riemannian space or common spatial pattern algorithm in Euclidean space. The proposed algorithms were evaluated on two MI based BCI data sets with different subjects and compared with existing transfer learning algorithms with sole data alignment or subject selection. The experimental results show that the hybrid-space data alignment methods for reducing the differences among subjects significantly outperform two single-space alignment methods, and the source subject selection method can substantially enhance the similarity between source subjects and the target subject. The combination of the two methods achieves superior classification performance compared to either one. The proposed algorithms will greatly facilitate the real-world applications of MI based BCIs.

show abstract

Sle-CNN: a novel convolutional neural network for sleep stage classification

Zhang

Xue

Słowik

et al. 2023

Neural Comput & Applic

View full text Add to dashboard Cite

Many classical methods have been used in automatic sleep stage classification but few methods explore deep learning. Meanwhile, most deep learning methods require extensive expertise and suffer from a mass of handcrafted steps which are time-consuming. In this paper, we propose an efficient convolutional neural network, Sle-CNN, for five-sleep-stage classification. We attach each kernel in the first layers with a trainable coefficient to enhance the learning ability and flexibility of the kernel. Then, we make full use of the genetic algorithm’s heuristic search and the advantage of no need for the gradient to search for the sleep stage classification architecture. We verify the convergence of Sle-CNN and compare the performance of traditional convolutional neural networks before and after using the trainable coefficient. Meanwhile, we compare the performance between the Sle-CNN generated through genetic algorithm and the traditional convolutional neural networks. The experiments demonstrate that the convergence of Sle-CNN is faster than the normal convolutional neural networks and the Sle-CNN generated by genetic algorithm outperforms the traditional handcrafted counterparts too. Our research suggests that deep learning has a great potential on electroencephalogram signal processing, especially with the intensification of neural architecture search. Meanwhile, neural architecture search can exert greater power in practical engineering applications. We conduct the Sle-CNN with the Python library, Pytorch, and the code and models will be publicly available.

show abstract

Different Set Domain Adaptation for Brain-Computer Interfaces: A Label Alignment Approach

Cited by 67 publications

References 40 publications

Generalized neural decoders for transfer learning across participants and recording modalities

Generalized neural decoders for transfer learning across participants and recording modalities

Transfer Learning Based on Hybrid Riemannian and Euclidean Space Data Alignment and Subject Selection in Brain-Computer Interfaces

Sle-CNN: a novel convolutional neural network for sleep stage classification

Contact Info

Product

Resources

About