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

A brain-computer interface (BCI) system usually needs a long calibration session for each new subject/task to adjust its parameters, which impedes its transition from the laboratory to real-world applications. Domain adaptation, which leverages labeled data from auxiliary subjects/tasks (source domains), has demonstrated its effectiveness in reducing such calibration effort. Currently, most domain adaptation approaches require the source domains to have the same feature space and label space as the target domain, which limits their applications, as the auxiliary data may have different feature spaces and/or different label spaces. This paper considers different set domain adaptation for BCIs, i.e., the source and target domains have different label spaces. We introduce a practical setting of different label sets for BCIs, and propose a novel label alignment (LA) approach to align the source label space with the target label space. It has three desirable properties: 1) LA only needs as few as one labeled sample from each class of the target subject; 2) LA can be used as a preprocessing step before different feature extraction and classification algorithms; and, 3) LA can be integrated with other domain adaptation approaches to achieve even better performance. Experiments on two motor imagery datasets demonstrated the effectiveness of LA.

[1]  Michael I. Jordan,et al.  Universal Domain Adaptation , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  Feng Liu,et al.  Open Set Domain Adaptation: Theoretical Bound and Algorithm , 2019, IEEE Transactions on Neural Networks and Learning Systems.

[3]  Fabien Lotte,et al.  Brain-Computer Interfaces: Beyond Medical Applications , 2012, Computer.

[4]  Geoffrey E. Hinton,et al.  Visualizing Data using t-SNE , 2008 .

[5]  Kate Saenko,et al.  Return of Frustratingly Easy Domain Adaptation , 2015, AAAI.

[6]  Philip S. Yu,et al.  Visual Domain Adaptation with Manifold Embedded Distribution Alignment , 2018, ACM Multimedia.

[7]  Motoaki Kawanabe,et al.  Direct Importance Estimation with Model Selection and Its Application to Covariate Shift Adaptation , 2007, NIPS.

[8]  Brent Lance,et al.  Driver Drowsiness Estimation From EEG Signals Using Online Weighted Adaptation Regularization for Regression (OwARR) , 2017, IEEE Transactions on Fuzzy Systems.

[9]  Christian Jutten,et al.  Multiclass Brain–Computer Interface Classification by Riemannian Geometry , 2012, IEEE Transactions on Biomedical Engineering.

[10]  Dennis J. McFarland,et al.  Brain–computer interfaces for communication and control , 2002, Clinical Neurophysiology.

[11]  Taghi M. Khoshgoftaar,et al.  A survey on heterogeneous transfer learning , 2017, Journal of Big Data.

[12]  Dongrui Wu,et al.  Online and Offline Domain Adaptation for Reducing BCI Calibration Effort , 2017, IEEE Transactions on Human-Machine Systems.

[13]  K.-R. Muller,et al.  Optimizing Spatial filters for Robust EEG Single-Trial Analysis , 2008, IEEE Signal Processing Magazine.

[14]  Dongrui Wu,et al.  Channel and Trials Selection for Reducing Covariate Shift in EEG-based Brain-Computer Interfaces , 2019, 2019 IEEE International Conference on Systems, Man and Cybernetics (SMC).

[15]  Dongrui Wu,et al.  Active semi-supervised transfer learning (ASTL) for offline BCI calibration , 2017, 2017 IEEE International Conference on Systems, Man, and Cybernetics (SMC).

[16]  Scott E. Kerick,et al.  Brain–Computer Interface Technologies in the Coming Decades , 2012, Proceedings of the IEEE.

[17]  Klaus-Robert Müller,et al.  Boosting bit rates in noninvasive EEG single-trial classifications by feature combination and multiclass paradigms , 2004, IEEE Transactions on Biomedical Engineering.

[18]  Dongrui Wu,et al.  Transfer Learning for Brain–Computer Interfaces: A Euclidean Space Data Alignment Approach , 2018, IEEE Transactions on Biomedical Engineering.

[19]  Jing Zhang,et al.  Joint Geometrical and Statistical Alignment for Visual Domain Adaptation , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[20]  Qiang Yang,et al.  A Survey on Transfer Learning , 2010, IEEE Transactions on Knowledge and Data Engineering.

[21]  Dongrui Wu,et al.  Transfer Learning Enhanced Common Spatial Pattern Filtering for Brain Computer Interfaces (BCIs): Overview and a New Approach , 2017, ICONIP.

[22]  Philip S. Yu,et al.  Transfer Feature Learning with Joint Distribution Adaptation , 2013, 2013 IEEE International Conference on Computer Vision.

[23]  S. Coyle,et al.  Brain–computer interfaces: a review , 2003 .

[24]  Dongrui Wu,et al.  Spatial Filtering for Brain Computer Interfaces: A Comparison between the Common Spatial Pattern and Its Variant , 2018, 2018 IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC).

[25]  Michael S. Lazar,et al.  Spatial patterns underlying population differences in the background EEG , 2005, Brain Topography.

[26]  Klaus-Robert Müller,et al.  The non-invasive Berlin Brain–Computer Interface: Fast acquisition of effective performance in untrained subjects , 2007, NeuroImage.

[27]  Bernhard Schölkopf,et al.  Transfer Learning in Brain-Computer Interfaces , 2015, IEEE Computational Intelligence Magazine.

[28]  Paul E. Utgoff,et al.  Shift of bias for inductive concept learning , 1984 .

[29]  Cuntai Guan,et al.  Learning from other subjects helps reducing Brain-Computer Interface calibration time , 2010, 2010 IEEE International Conference on Acoustics, Speech and Signal Processing.

[30]  Brent Lance,et al.  Switching EEG Headsets Made Easy: Reducing Offline Calibration Effort Using Active Weighted Adaptation Regularization , 2016, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[31]  Tatsuya Harada,et al.  Open Set Domain Adaptation by Backpropagation , 2018, ECCV.

[32]  F. Yger,et al.  Riemannian Approaches in Brain-Computer Interfaces: A Review , 2017, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[33]  Nicholas Ayache,et al.  Geometric Means in a Novel Vector Space Structure on Symmetric Positive-Definite Matrices , 2007, SIAM J. Matrix Anal. Appl..

[34]  Christian Jutten,et al.  Transfer Learning: A Riemannian Geometry Framework With Applications to Brain–Computer Interfaces , 2018, IEEE Transactions on Biomedical Engineering.

[35]  Christa Neuper,et al.  Rehabilitation with Brain-Computer Interface Systems , 2008, Computer.

[36]  Bin He,et al.  Noninvasive Brain-Computer Interfaces Based on Sensorimotor Rhythms , 2015, Proceedings of the IEEE.

[37]  Peng Hao,et al.  Transfer learning using computational intelligence: A survey , 2015, Knowl. Based Syst..

[38]  Seungjin Choi,et al.  Composite Common Spatial Pattern for Subject-to-Subject Transfer , 2009, IEEE Signal Processing Letters.

[39]  Juergen Gall,et al.  Open Set Domain Adaptation , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[40]  H. Shimodaira,et al.  Improving predictive inference under covariate shift by weighting the log-likelihood function , 2000 .

[41]  G. Pfurtscheller,et al.  Optimal spatial filtering of single trial EEG during imagined hand movement. , 2000, IEEE transactions on rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society.

[42]  Feng Liu,et al.  Unsupervised Heterogeneous Domain Adaptation via Shared Fuzzy Equivalence Relations , 2018, IEEE Transactions on Fuzzy Systems.

[43]  John R. Anderson,et al.  MACHINE LEARNING An Artificial Intelligence Approach , 2009 .

[44]  G. Pfurtscheller,et al.  Designing optimal spatial filters for single-trial EEG classification in a movement task , 1999, Clinical Neurophysiology.

[45]  Bernhard Schölkopf,et al.  A Kernel Method for the Two-Sample-Problem , 2006, NIPS.

[46]  Arnaud Delorme,et al.  EEGLAB: an open source toolbox for analysis of single-trial EEG dynamics including independent component analysis , 2004, Journal of Neuroscience Methods.