Higger, Matt and Quivira, Fernando and Akçakaya, Murat and Moghadamfalahi, Mohammad and Nezamfar, Hooman and Çetin, Müjdat and Erdoğmuş, Deniz (2016) Recursive Bayesian coding for BCIs. IEEE Transactions on Neural Systems and Rehabilitation Engineering . ISSN 1534-4320 (Print) 1558-0210 (Online) Published Online First http://dx.doi.org/10.1109/TNSRE.2016.2590959
![Warning](/style/images/warning.png)
There is a more recent version of this item available.
![[thumbnail of J_Higger_RecursiveBayesCodingBCI_TNSRE_submitted.pdf]](https://research.sabanciuniv.edu/style/images/fileicons/application_pdf.png)
J_Higger_RecursiveBayesCodingBCI_TNSRE_submitted.pdf
Restricted to Repository staff only
Download (688kB) | Request a copy
![[thumbnail of higger_TNSRE16_early_access.pdf]](https://research.sabanciuniv.edu/style/images/fileicons/application_pdf.png)
higger_TNSRE16_early_access.pdf
Restricted to Registered users only
Download (2MB) | Request a copy
Official URL: http://dx.doi.org/10.1109/TNSRE.2016.2590959
Abstract
Brain Computer Interfaces (BCI) seek to infer some task symbol, a task relevant instruction, from brain symbols, classifiable physiological states. For example, in a motor imagery robot control task a user would indicate their choice from a dictionary of task symbols (rotate arm left, grasp, etc.) by selecting from a smaller dictionary of brain symbols (imagined left or right hand movements). We examine how a BCI infers a task symbol using selections of brain symbols. We offer a recursive Bayesian decision framework which incorporates context prior distributions (e.g. language model priors in spelling applications), accounts for varying brain symbol accuracy and is robust to single brain symbol query errors. This framework is paired with Maximum Mutual Information (MMI) coding which maximizes a generalization of ITR. Both are applicable to any discrete task and brain phenomena (e.g. P300, SSVEP, MI). To demonstrate the efficacy of our approach we perform SSVEP “Shuffle” Speller experiments and compare our recursive coding scheme with traditional decision tree methods including Huffman coding. MMI coding leverages the asymmetry of the classifier’s mistakes across a particular user’s SSVEP responses; in doing so it offers a 33% increase in letter accuracy though it is 13% slower in our experiment.
Item Type: | Article |
---|---|
Uncontrolled Keywords: | Discrete Memoryless Channel, BCI, SSVEP Shuffle Speller, Decision Tree, Huffman Coding, Mutual Information |
Subjects: | T Technology > TK Electrical engineering. Electronics Nuclear engineering Q Science > QP Physiology > QP1-(981) Physiology > QP351-495 Neurophysiology and neuropsychology |
Divisions: | Faculty of Engineering and Natural Sciences > Academic programs > Electronics Faculty of Engineering and Natural Sciences |
Depositing User: | Müjdat Çetin |
Date Deposited: | 12 Nov 2016 14:17 |
Last Modified: | 22 May 2019 13:43 |
URI: | https://research.sabanciuniv.edu/id/eprint/30324 |
Available Versions of this Item
-
Recursive Bayesian coding for BCIs. (deposited 24 Dec 2015 16:36)
- Recursive Bayesian coding for BCIs. (deposited 12 Nov 2016 14:17) [Currently Displayed]