Collaborative Filtering for Brain-Computer Interaction Using Transfer Learning and Active Class Selection

PDF Version Also Available for Download.

Description

Article discussing collaborative filtering for brain-computer interaction using transfer learning and active class selection.

Physical Description

18 p. : col. ill.

Creation Information

Wu, Dongrui; Lance, Brent J. & Parsons, Thomas D. February 21, 2013.

Context

This article is part of the collection entitled: UNT Scholarly Works and was provided by UNT College of Arts and Sciences to Digital Library, a digital repository hosted by the UNT Libraries. It has been viewed 237 times , with 10 in the last month . More information about this article can be viewed below.

Who

People and organizations associated with either the creation of this article or its content.

Authors

Publisher

Provided By

UNT College of Arts and Sciences

The UNT College of Arts and Sciences educates students in traditional liberal arts, performing arts, sciences, professional, and technical academic programs. In addition to its departments, the college includes academic centers, institutes, programs, and offices providing diverse courses of study.

Contact Us

What

Descriptive information to help identify this article. Follow the links below to find similar items on the Digital Library.

Degree Information

Description

Article discussing collaborative filtering for brain-computer interaction using transfer learning and active class selection.

Physical Description

18 p. : col. ill.

Notes

Abstract: Brain-computer interaction (BCI) and physiological computing are terms that refer to using processed neural or physiological signals to influence human interaction with computers, environment, and each other. A major challenge in developing these systems arises from the large individual differences typically seen in the neural/physiological responses. As a result, many researchers use individually-trained recognition algorithms to process this data. In order to minimize time, cost, and barriers to use, there is a need to minimize the amount of individual training data required, or equivalently, to increase the recognition accuracy without increasing the number of user-specific training samples. One promising method for achieving this is collaborative filtering, which combines training data from the individual subject with additional training data from other, similar subjects. This paper describes a successful application of a collaborative filtering approach intended for a BCI system. This approach is based on transfer learning (TL), active class selection (ACS), and a mean squared difference user-similarity heuristic. The resulting BCI system uses neural and physiological signals for automatic task difficulty recognition. TL improves the learning performance by combining a small number of user-specific training samples with a large number of auxiliary training samples from other similar subjects. ACS optimally selects the classes to generate user-specific training samples. Experimental results on 18 subjects, using both nearest neighbors and support vector machine classifiers, demonstrate that the proposed approach can significantly reduce the number of user-specific training data samples. This collaborative filtering approach will also be generalizable to handling individual differences in many other applications that involve human neural or physiological data, such as affective computing.

Source

  • PLoS One, 2013, San Francisco: Public Library of Science

Language

Item Type

Identifier

Unique identifying numbers for this article in the Digital Library or other systems.

Publication Information

  • Publication Title: PLoS One
  • Volume: 8
  • Issue: 2
  • Pages: 18
  • Peer Reviewed: Yes

Collections

This article is part of the following collection of related materials.

UNT Scholarly Works

Materials from the UNT community's research, creative, and scholarly activities and UNT's Open Access Repository. Access to some items in this collection may be restricted.

What responsibilities do I have when using this article?

When

Dates and time periods associated with this article.

Creation Date

  • February 21, 2013

Added to The UNT Digital Library

  • July 15, 2014, 5:33 a.m.

Description Last Updated

  • Aug. 29, 2014, 10:02 a.m.

Usage Statistics

When was this article last used?

Yesterday: 0
Past 30 days: 10
Total Uses: 237

Interact With This Article

Here are some suggestions for what to do next.

Start Reading

PDF Version Also Available for Download.

Citations, Rights, Re-Use

Wu, Dongrui; Lance, Brent J. & Parsons, Thomas D. Collaborative Filtering for Brain-Computer Interaction Using Transfer Learning and Active Class Selection, article, February 21, 2013; [San Francisco, California]. (digital.library.unt.edu/ark:/67531/metadc306986/: accessed June 26, 2017), University of North Texas Libraries, Digital Library, digital.library.unt.edu; crediting UNT College of Arts and Sciences.