Online Calibration of Intracortical Neural Interface Based on Transfer Learning

In the application of neural interface, the neural activity of neurons and neuronal groups is not fixed even under the same task conditions. Meanwhile, the recording conditions of neural signals are also very unstable, with a high degree of within-and across-day variability. This results in a very unstable firing pattern for the recorded neural spike signals. In order to get better performance, the decoder often requires a lot of online calibration samples. This brings a heavy training burden to neural interface users. To solve this problem, this paper proposes to apply transfer learning (TL) to online calibration of intracortical neural interface to reduce the dependence of decoder on a large number of online calibration samples. Experimental results show that through transferring from a large amount of historical data, decoder can achieve satisfactory classification accuracy with only a small amount of online data.

[1]  Jun Lu,et al.  A review on transfer learning for brain-computer interface classification , 2015, 2015 5th International Conference on Information Science and Technology (ICIST).

[2]  Guy M McKhann,et al.  Cortical control of a prosthetic arm for self-feeding. , 2008, Neurosurgery.

[3]  Jiping He,et al.  Cell categories and k-nearest neighbor algorithm based decoding of primary motor cortical activity during reach-to-grasp task , 2014, 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[4]  R. Andersen,et al.  Decoding motor imagery from the posterior parietal cortex of a tetraplegic human , 2015, Science.

[5]  Motoaki Kawanabe,et al.  Toward Unsupervised Adaptation of LDA for Brain–Computer Interfaces , 2011, IEEE Transactions on Biomedical Engineering.

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

[7]  Jon A. Mukand,et al.  Neuronal ensemble control of prosthetic devices by a human with tetraplegia , 2006, Nature.

[8]  Wei Wu,et al.  Neural Decoding of Hand Motion Using a Linear State-Space Model With Hidden States , 2009, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[9]  Cuntai Guan,et al.  Improving session-to-session transfer performance of motor imagery-based BCI using adaptive extreme learning machine , 2013, 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[10]  Wojciech Samek,et al.  Transferring Subspaces Between Subjects in Brain--Computer Interfacing , 2012, IEEE Transactions on Biomedical Engineering.

[11]  Moritz Grosse-Wentrup,et al.  Multisubject Learning for Common Spatial Patterns in Motor-Imagery BCI , 2011, Comput. Intell. Neurosci..

[12]  Yasuharu Koike,et al.  Application of Covariate Shift Adaptation Techniques in Brain–Computer Interfaces , 2010, IEEE Transactions on Biomedical Engineering.

[13]  Brent Lance,et al.  Reducing Offline BCI Calibration Effort Using Weighted Adaptation Regularization with Source Domain Selection , 2015, 2015 IEEE International Conference on Systems, Man, and Cybernetics.

[14]  Brent Lance,et al.  Transfer learning and active transfer learning for reducing calibration data in single-trial classification of visually-evoked potentials , 2014, 2014 IEEE International Conference on Systems, Man, and Cybernetics (SMC).

[15]  Shiliang Sun,et al.  A subject transfer framework for EEG classification , 2012, Neurocomputing.

[16]  Nicolas Y. Masse,et al.  Reach and grasp by people with tetraplegia using a neurally controlled robotic arm , 2012, Nature.

[17]  A. Schwartz,et al.  High-performance neuroprosthetic control by an individual with tetraplegia , 2013, The Lancet.