Skip to main content

Developing an Optimized Single-Trial P300-Based Brain Computer Interface System

  • Conference paper
  • First Online:
International Conference for Innovation in Biomedical Engineering and Life Sciences (ICIBEL 2015)

Part of the book series: IFMBE Proceedings ((IFMBE,volume 56))

  • 1656 Accesses

Abstract

Brain event related potentials (ERP) have been used in developing brain computer interface (BCI) systems. P300 as a robust ERP has been utilized in BCI and clinical researches. A common P300-based BCI system consist of brain signal recording, pre-processing, P300 features extraction, and classification units. Achieving a high accuracy in detection of single-trial P300, using fast computational algorithms is the main challenge of designing these systems. However, there is trade-off between accuracy and computational time. In this study, various well-developed algorithms controlled by a rule-based platform to optimize the detection algorithm. P300 feature extraction algorithms has been developed by using wavelet transform techniques, while SVM with linear/Gaussian kernels and logistic regression applied as alternative supervised learning classifiers. Principle component analysis also was used for feature selection in order to speed up the classification procedure. This optimization system make decision on selecting the proper P300 detection method via selecting the group of channels, feature extraction algorithm, number of selected principle components, and type of classifier. Controller used cross validation data set to calculate the accuracy and ratio of computational time for each possible combination, and the optimized method was assessed using test data set. The results suggest that designing a P300-BCI system with the ability to select the proper method of detection can be utilized in different applications to benefit the user with a better performance.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 129.00
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 169.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to F. E. Motlagh .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 2016 International Federation for Medical and Biological Engineering

About this paper

Cite this paper

Motlagh, F.E., Ibrahim, F. (2016). Developing an Optimized Single-Trial P300-Based Brain Computer Interface System. In: Ibrahim, F., Usman, J., Mohktar, M., Ahmad, M. (eds) International Conference for Innovation in Biomedical Engineering and Life Sciences . ICIBEL 2015. IFMBE Proceedings, vol 56. Springer, Singapore. https://doi.org/10.1007/978-981-10-0266-3_2

Download citation

  • DOI: https://doi.org/10.1007/978-981-10-0266-3_2

  • Published:

  • Publisher Name: Springer, Singapore

  • Print ISBN: 978-981-10-0265-6

  • Online ISBN: 978-981-10-0266-3

  • eBook Packages: EngineeringEngineering (R0)

Publish with us

Policies and ethics