A review on transfer learning approaches in brain–computer interface

A review on transfer learning approaches in brain–computer interface

For access to this article, please select a purchase option:

Buy chapter PDF
(plus tax if applicable)

IET members benefit from discounts to all IET publications and free access to E&T Magazine. If you are an IET member, log in to your account and the discounts will automatically be applied.

Learn more about IET membership 

Recommend Title Publication to library

You must fill out fields marked with: *

Librarian details
Your details
Why are you recommending this title?
Select reason:
Signal Processing and Machine Learning for Brain-Machine Interfaces — Recommend this title to your library

Thank you

Your recommendation has been sent to your librarian.

One of the major limitations of brain-computer interface (BCI) is its long calibration time. Typically, a big amount of training data needs to be collected at the beginning of each session in order to tune the parameters of the system for the target user due to between sessions/subjects non-stationarity. To mitigate this limitation, transfer learning can be potentially one useful solution. Transfer learning extracts information from different domains (raw data, features, or classification domain) to compensate the lack of labelled data from the test subject. Within this chapter transfer learning definitions and techniques are fully explained.After that, some of the available transfer learning applications in BCI are explored. Then, a brief discussion about applying transfer learning in the different domains is included. The discussion shows that despite some advances, a successful transfer learning framework for BCI still needs to be developed. Finally, future research directions in this topic are suggested in order to successfully and reliably reduce the calibration time for new subjects and increase the accuracy of the system.

Chapter Contents:

  • Abstract
  • 5.1 Introduction
  • 5.2 Transfer learning
  • 5.2.1 History of transfer learning
  • 5.2.2 Transfer learning definition
  • 5.2.3 Transfer learning categories
  • Inductive transfer learning
  • Transductive transfer learning
  • Unsupervised transfer learning
  • 5.3 Transfer learning approaches
  • 5.3.1 Instance-based transfer learning
  • 5.3.2 Feature-representation transfer learning
  • 5.3.3 Classifier-based transfer learning
  • 5.3.4 Relational-based transfer learning
  • 5.4 Transfer learning methods used in BCI
  • 5.4.1 Instance-based transfer learning in BCI
  • Importance sampling instance-based transfer learning
  • Re-weighting instance-based transfer learning
  • 5.4.2 Feature-representation transfer learning in BCI
  • CSP-based feature-representation transfer learning
  • Non CSP-based feature-representation transfer learning
  • 5.4.3 Classifier-based transfer learning in BCI
  • Domain adaptation in classifiers
  • Ensemble learning of classifier
  • 5.4.4 Unsupervised transfer learning
  • 5.5 Challenges and discussion
  • 5.5.1 Instance-based transfer learning in BCI
  • 5.5.2 Feature-representation transfer learning in BCI
  • 5.5.3 Classifier-based transfer learning in BCI
  • 5.6 Summary
  • References

Inspec keywords: reviews; brain-computer interfaces; pattern classification; medical computing; learning (artificial intelligence)

Other keywords: labelled data; chapter transfer; target user; potentially one useful solution; available transfer; transfer learning approaches; BCI; training data needs; sessions-subjects nonstationarity; test subject; session; long calibration time; successful transfer learning framework; classification domain; brain-computer interface

Subjects: User interfaces; Biology and medical computing; Learning in AI; Data handling techniques; Knowledge engineering techniques

Preview this chapter:
Zoom in

A review on transfer learning approaches in brain–computer interface, Page 1 of 2

| /docserver/preview/fulltext/books/ce/pbce114e/PBCE114E_ch5-1.gif /docserver/preview/fulltext/books/ce/pbce114e/PBCE114E_ch5-2.gif

Related content

This is a required field
Please enter a valid email address