Transfer Learning in Brain-Computer Interfaces

@article{Jayaram2016TransferLI,
  title={Transfer Learning in Brain-Computer Interfaces},
  author={V. Jayaram and Morteza Alamgir and Y. Altun and B. Sch{\"o}lkopf and M. Grosse-Wentrup},
  journal={IEEE Computational Intelligence Magazine},
  year={2016},
  volume={11},
  pages={20-31}
}
The performance of brain-computer interfaces (BCIs) improves with the amount of available training data; the statistical distribution of this data, however, varies across subjects as well as across sessions within individual subjects, limiting the transferability of training data or trained models between them. In this article, we review current transfer learning techniques in BCIs that exploit shared structure between training data of multiple subjects and/or sessions to increase performance… Expand
Weighted Transfer Learning for Improving Motor Imagery-Based Brain–Computer Interface
TLDR
A new similarity measure based on the Kullback–Leibler divergence (KL) is used to measure the similarity between two feature spaces obtained using subject-specific common spatial patterns (CSP) and the results showed that the proposed weighted transfer learning classifier performed significantly better than the considered comparable baseline algorithms. Expand
Multi-task logistic regression in brain-computer interfaces
TLDR
The ability of the model to identify relevant topographies along with signal band-power features that agree with neurophysiological properties of a common sensorimotor rhythm paradigm is demonstrated, making it further applicable for identification, analysis and evaluation of paradigm characteristics without relying on expert knowledge. Expand
Tangent Space Features-Based Transfer Learning Classification Model for Two-Class Motor Imagery Brain-Computer Interface
TLDR
The aim of this work is to reduce the long calibration time in BCI systems by proposing a transfer learning model which can be used for evaluating unseen single trials for a subject without the need for training session data. Expand
Multi-Task Learning for Commercial Brain Computer Interfaces
  • G. Panagopoulos
  • Computer Science
  • 2017 IEEE 17th International Conference on Bioinformatics and Bioengineering (BIBE)
  • 2017
TLDR
This work visualizes the so-called inter subject variability problem and applies machine learning methods commonly used in BCI literature, and employs multi-task learning algorithms, setting each subject specific classification as a separate task. Expand
Cross-Paradigm Pretraining of Convolutional Networks Improves Intracranial EEG Decoding
TLDR
This paper applies transfer learning to a framework based on deep convolutional neural networks (deep ConvNets) to prove the transferability of learned patterns in error-related brain signals across different tasks, and extracts similar patterns in time-frequency analyses in identical channels, leading to selective high signal correlations between the two different paradigms. Expand
Spectral Transfer Learning Using Information Geometry for a User-Independent Brain-Computer Interface
TLDR
This method demonstrates that unsupervised transfer learning for single-trial detection in ERP-based BCIs can be achieved without the requirement of costly training data, representing a step-forward in the overall goal of achieving a practical user-independent BCI system. Expand
EEG classification across sessions and across subjects through transfer learning in motor imagery-based brain-machine interface system
TLDR
Preliminary results suggested that the proposed algorithm can be effectively applied to the classification of motor imagery EEG signals across sessions and across subjects and the performance is better than that of the traditional machine learning algorithms. Expand
Transfer Learning for Brain–Computer Interfaces: A Euclidean Space Data Alignment Approach
  • He He, Dongrui Wu
  • Computer Science, Mathematics
  • IEEE Transactions on Biomedical Engineering
  • 2020
TLDR
This work proposes a novel approach to align EEG trials from different subjects in the Euclidean space to make them more similar, and hence improve the learning performance for a new subject, and can greatly facilitate transfer learning in BCIs. Expand
A Novel Transfer Support Matrix Machine for Motor Imagery-Based Brain Computer Interface
TLDR
A novel knowledge-leverage-based support matrix machine (KL-SMM) was developed to improve the classification performance when only a few labeled EEG data in the target domain (target subject) were available and outperformed the comparable methods when the EEG data were insufficient. Expand
A Subject-to-subject Transfer Learning Framework Based on Jensen-Shannon Divergence for Improving Brain-computer Interface
TLDR
A novel subject-to-subject transfer learning framework that improves the classification accuracy using limited training data and outperforms the subject-specific BCI model by 3%. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 47 REFERENCES
Multitask Learning for Brain-Computer Interfaces
TLDR
This paper utilizes the framework of multitask learning to construct a BCI that can be used without any subject-specific calibration process, and shows that satisfactory classification results can be achieved with zero training data. Expand
Towards Zero Training for Brain-Computer Interfacing
TLDR
By a novel technique, prototypical spatial filters are determined which have better generalization properties compared to single-session filters and can be used in follow-up sessions without the need to recalibrate the system. Expand
Learning a common dictionary for subject-transfer decoding with resting calibration
TLDR
The results suggest that analyzing multisubject brain activities on common bases by the proposed method enables information sharing across subjects with low-burden resting calibration, and is effective for practical use of BMI in variable environments. Expand
Subject-to-subject adaptation to reduce calibration time in motor imagery-based brain-computer interface
  • M. Arvaneh, I. Robertson, T. Ward
  • Computer Science, Medicine
  • 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society
  • 2014
TLDR
A new subject-to-subject adaptation algorithm to reliably reduce the calibration time of a new subject to only 3-4 minutes and the previously trained model based on the selected historic session is entirely used for the classification of the new subject's data after adaptation. Expand
Subject-independent mental state classification in single trials
TLDR
This work uses a large database of EEG recordings from 45 subjects, who took part in movement imagination task experiments, to construct an ensemble of classifiers derived from subject-specific temporal and spatial filters. Expand
The non-invasive Berlin Brain–Computer Interface: Fast acquisition of effective performance in untrained subjects
TLDR
It is proposed that the key to quick efficiency in the BBCI system is its flexibility due to complex but physiologically meaningful features and its adaptivity which respects the enormous inter-subject variability. Expand
Application of Covariate Shift Adaptation Techniques in Brain–Computer Interfaces
TLDR
It can be summarized that covariate shift adaptation is helpful to realize adaptive BCI systems. Expand
Multisubject Learning for Common Spatial Patterns in Motor-Imagery BCI
TLDR
The details of the multitask CSP algorithm are outlined, results on two data sets are shown and a clear improvement can be seen, especially when the number of training trials is relatively low. Expand
A brain-computer interface based on self-regulation of gamma-oscillations in the superior parietal cortex.
TLDR
Self-regulation of gamma-power in the SPC is a feasible paradigm for brain-computer interfacing and may be preserved in late stages of ALS, providing a novel approach to testing whether completely locked-in ALS patients retain the capacity for goal-directed thinking. Expand
Adaptive Spatial Filters with predefined Region of Interest for EEG based Brain-Computer-Interfaces
TLDR
An adaptive spatial filter is proposed that replaces the training data in the CSP approach by a-priori information and maximizes the ratio of the variance of the electric field originating in a predefined region of interest (ROI) and the overall variance ofthe measured EEG. Expand
...
1
2
3
4
5
...