Performance Considerations for General-Purpose Typing BCIs, Including the Handwriting BCI. Technical Report #01.

Placeholder Show Content

Abstract/Contents

Abstract
This is an informal technical report regarding performance considerations for general-purpose typing brain-computer interfaces (BCIs). A general-purpose typing BCI is a BCI that enables the user to type any string of characters (as opposed to a BCI that can only type certain strings, such as sequences of words drawn from a small set of allowed words). This living document is intended to grow, evolve and serve as a resource for the community. We use our new Handwriting BCI [1] as an example system. In addition to this technical report (Technical Report #01), we are also openly sharing all electrophysiology data (Dryad, [2]) and all code (Python, GitHub, [3]) from the paper [1]. Defining and measuring performance metrics are key to our community’s ability to compare, coordinate and cooperate in order to advance general-purpose typing BCIs and bring them into widespread clinical use. This report begins with investigations in people with paralysis (Sections 1-5), where our studies are part of the BrainGate2 pilot clinical trial (NCT00912041)1 with Prof. Leigh Hochberg (sponsor-investigator), Prof. Jaimie Henderson (NPTL co-director, BrainGate2 Stanford site PI), Prof. Krishna Shenoy (NPTL co-director), Dr. Frank Willett (Research Scientist) and Prof. Paul Nuyujukian (NPTL alumnus). This report also includes pre-clinical studies with nonhuman primates (NHPs, rhesus macaques; Section 6), where our studies are part of NPSL with Prof. Krishna Shenoy (Director) and Prof. Paul Nuyujukian (NPSL alumnus). This living document is intended to be inclusive, accurate and accessible to students and investigators. We welcome suggested corrections, edits and additions; please contact Krishna Shenoy (shenoy@stanford.edu).

Description

Type of resource text
Date created May 19, 2021
Date modified September 8, 2022; February 22, 2023
Publication date September 2, 2022

Creators/Contributors

Advisor Shenoy, Krishna V.
Advisor Henderson, Jaimie M.
Author Willet, Frank R.
Author Nuyujukian, Paul

Subjects

Subject General purpose typing
Subject Brain-computer interfaces
Subject brain machine interfaces
Subject BCI
Subject BMI
Subject Handwriting BCI
Subject neural prpostheses
Subject communication prostheses
Subject motor prostheses
Genre Text
Genre Technical report

Bibliographic information

Related item
DOI https://doi.org/10.25740/jx921pv3255
Location https://purl.stanford.edu/jx921pv3255

Access conditions

Use and reproduction
User agrees that, where applicable, content will not be used to identify or to otherwise infringe the privacy or confidentiality rights of individuals. Content distributed via the Stanford Digital Repository may be subject to additional license and use restrictions applied by the depositor.
License
This work is licensed under a Creative Commons Attribution 4.0 International license (CC BY).

Preferred citation

Preferred citation
Shenoy KV, Willett FR, Nuyujukian P, Henderson JM (2021) Performance considerations for general-purpose typing BCIs, including the handwriting BCI. Technical Report #01, Stanford Digital Repository, Stanford University. URL: https://purl.stanford.edu/jx921pv3255. https://doi.org/10.25740/jx921pv3255

Collection

Faculty, Student, and Staff Publications

View other items in this collection in SearchWorks

Contact information

Also listed in

Loading usage metrics...