24
views
0
recommends
+1 Recommend
0 collections
    0
    shares
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

      EEG Signal Processing and Classification for the Novel Tactile-Force Brain-Computer Interface Paradigm

      Preprint
      , , ,

      Read this article at

      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          Abstract

          The presented study explores the extent to which tactile-force stimulus delivered to a hand holding a joystick can serve as a platform for a brain computer interface (BCI). The four pressure directions are used to evoke tactile brain potential responses, thus defining a tactile-force brain computer interface (tfBCI). We present brain signal processing and classification procedures leading to successful interfacing results. Experimental results with seven subjects performing online BCI experiments provide a validation of the hand location tfBCI paradigm, while the feasibility of the concept is illuminated through remarkable information-transfer rates.

          Related collections

          Most cited references4

          • Record: found
          • Abstract: found
          • Article: not found

          10/20, 10/10, and 10/5 systems revisited: their validity as relative head-surface-based positioning systems.

          With the advent of multi-channel EEG hardware systems and the concurrent development of topographic and tomographic signal source localization methods, the international 10/20 system, a standard system for electrode positioning with 21 electrodes, was extended to higher density electrode settings such as 10/10 and 10/5 systems, allowing more than 300 electrode positions. However, their effectiveness as relative head-surface-based positioning systems has not been examined. We previously developed a virtual 10/20 measurement algorithm that can analyze any structural MR head and brain image. Extending this method to the virtual 10/10 and 10/5 measurement algorithms, we analyzed the MR images of 17 healthy subjects. The acquired scalp positions of the 10/10 and 10/5 systems were normalized to the Montreal Neurological Institute (MNI) stereotactic coordinates and their spatial variability was assessed. We described and examined the effects of spatial variability due to the selection of positioning systems and landmark placement strategies. As long as a detailed rule for a particular system was provided, it yielded precise landmark positions on the scalp. Moreover, we evaluated the effective spatial resolution of 329 scalp landmark positions of the 10/5 system for multi-subject studies. As long as a detailed rule for landmark setting was provided, 241 scalp positions could be set effectively when there was no overlapping of two neighboring positions. Importantly, 10/10 positions could be well separated on a scalp without overlapping. This study presents a referential framework for establishing the effective spatial resolutions of 10/20, 10/10, and 10/5 systems as relative head-surface-based positioning systems.
            Bookmark
            • Record: found
            • Abstract: found
            • Article: not found

            A comparison of classification techniques for the P300 Speller.

            This study assesses the relative performance characteristics of five established classification techniques on data collected using the P300 Speller paradigm, originally described by Farwell and Donchin (1988 Electroenceph. Clin. Neurophysiol. 70 510). Four linear methods: Pearson's correlation method (PCM), Fisher's linear discriminant (FLD), stepwise linear discriminant analysis (SWLDA) and a linear support vector machine (LSVM); and one nonlinear method: Gaussian kernel support vector machine (GSVM), are compared for classifying offline data from eight users. The relative performance of the classifiers is evaluated, along with the practical concerns regarding the implementation of the respective methods. The results indicate that while all methods attained acceptable performance levels, SWLDA and FLD provide the best overall performance and implementation characteristics for practical classification of P300 Speller data.
              Bookmark
              • Record: found
              • Abstract: found
              • Article: not found

              Introducing the tactile speller: an ERP-based brain-computer interface for communication.

              In this study, a tactile speller was developed and compared with existing visual speller paradigms in terms of classification performance and elicited event-related potentials (ERPs). The fingertips of healthy participants were stimulated with short mechanical taps while electroencephalographic activity was measured. The letters of the alphabet were allocated to different fingers and subjects could select one of the fingers by silently counting the number of taps on that finger. The offline and online performance of the tactile speller was compared to the overt and covert attention visual matrix speller and the covert attention Hex-o-Spell speller. For the tactile speller, binary target versus non-target classification accuracy was 67% on average. Classification and decoding accuracies of the tactile speller were lower than the overt matrix speller, but higher than the covert matrix speller, and similar to Hex-o-Spell. The average maximum information transfer rate of the tactile speller was 7.8 bits min(-1) (1.51 char min(-1)), with the best subject reaching a bit-rate of 27 bits min(-1) (5.22 char min(-1)). An increased amplitude of the P300 ERP component was found in response to attended stimuli versus unattended stimuli in all speller types. In addition, the tactile and overt matrix spellers also used the N2 component for discriminating between targets and non-targets. Overall, this study shows that it is possible to use a tactile speller for communication. The tactile speller provides a useful alternative to the visual speller, especially for people whose eye gaze is impaired.
                Bookmark

                Author and article information

                Journal
                06 October 2013
                2013-10-17
                Article
                10.1109/SITIS.2013.132
                1310.1593
                cc2d70e0-1173-4bb3-85ee-f31c68ac4872

                http://arxiv.org/licenses/nonexclusive-distrib/1.0/

                History
                Custom metadata
                92C55, 92C50, 92C30
                Proceedings of the 9th International Conference on Signal Image Technology and Internet Based Systems, (Kyoto, Japan), pp. 812-817, IEEE Computer Society, December 3-5, 2013
                6 pages (in conference proceedings original version); 6 figures, submitted to The 9th International Conference on Signal Image Technology & Internet Based Systems, December 2-5, 2013, Kyoto, Japan; to be available at IEEE Xplore; IEEE Copyright 2013
                q-bio.NC cs.HC

                Comments

                Comment on this article