Your browser does not support JavaScript!

Error-aware BCIs

Error-aware BCIs

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

Buy chapter PDF
(plus tax if applicable)
Buy Knowledge Pack
10 chapters for $120.00
(plus taxes 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 to Drive Human-Computer Interaction: EEG and eye-controlled interfaces — Recommend this title to your library

Thank you

Your recommendation has been sent to your librarian.

The ability of recognizing and correcting the erroneous actions is an integral part of human nature. Plenty of neuroscientific studies have been investigating the ability of human brain to recognize errors. The distinct neuronal responses that are produced by the human brain during the perception of an erroneous action are referred to as error-related potentials (ErrPs). Although research in brain-computer interfaces (BCIs) has managed to achieve significant improvement in terms of detecting the users'intentions over the last years, in a real-world setting, the interpretation of brain commands still remains an error-prone procedure leading to inaccurate interactions. Even for multimodal interaction schemes, the attained performance is far from optimal. As a means to overcome these debilities, and apart from developing more sophisticated machine-learning techniques or adding further modalities, scientists have also exploited the users' ability to perceive errors. During the rapid growth of the BCI/Human-Machine Interaction (HMI) technology over the last years, ErrPs have been used widely in order to enhance several existing BCI applications serving as a passive correction mechanism towards a more user-friendly environment. The principal idea is that a BCI system may incorporate, as feedback, the user's judgement about its function and use this feedback to correct its current output. In this chapter, we discuss the potentials and applications of ErrPs into developing hybrid BCI systems that emphasize in reliability and user experience by introducing the so-called error awareness.

Chapter Contents:

  • 11.1 Introduction to error-related potentials
  • 11.2 Spatial filtering
  • 11.2.1 Subspace learning
  • Unsupervised collaborative representation projection
  • Supervised collaborative representation
  • 11.2.2 Increasing signal-to-noise ratio
  • Preliminaries
  • Discriminant spatial filters
  • 11.3 Measuring the efficiency–ICRT
  • 11.4 An error-aware SSVEP-based BCI
  • 11.4.1 Experimental protocol
  • 11.4.2 Dataset
  • 11.4.3 Implementation details–preprocessing
  • 11.4.4 Results
  • Visual representation
  • Spatial filtering evaluation
  • 11.5 An error-aware gaze-based keyboard
  • 11.5.1 Methodology
  • 11.5.2 Typing task and physiological recordings
  • 11.5.3 Pragmatic typing protocol
  • 11.5.4 Data analysis
  • 11.5.5 System adjustment and evaluation
  • 11.5.6 Results
  • Physiological findings
  • SVM classification for predicting typesetting errors from physiological activity
  • Incorporating the SVM classifier(s) in the gaze-based keyboard
  • Simulated implementation of the EDS
  • 11.6 Summary
  • References

Inspec keywords: medical signal processing; brain-computer interfaces; neurophysiology; electroencephalography; learning (artificial intelligence)

Other keywords: brain commands; human-machine interaction technology; neuroscientific studies; human brain; multimodal interaction schemes; passive correction mechanism; error-aware BCI; real-world setting; machine-learning techniques; human nature; inaccurate interactions; user experience; error-related potentials; hybrid BCI systems; error awareness; neuronal responses; erroneous action perception; error-prone procedure; ErrPs; BCI applications; user-friendly environment; sophisticated machine-learning techniques; brain-computer interfaces; reliability

Subjects: Knowledge engineering techniques; Signal processing and detection; Biology and medical computing; User interfaces; Digital signal processing; Bioelectric signals; Electrodiagnostics and other electrical measurement techniques; Electrical activity in neurophysiological processes

Preview this chapter:
Zoom in

Error-aware BCIs, Page 1 of 2

| /docserver/preview/fulltext/books/ce/pbce129e/PBCE129E_ch11-1.gif /docserver/preview/fulltext/books/ce/pbce129e/PBCE129E_ch11-2.gif

Related content

This is a required field
Please enter a valid email address