A Generic Machine-Learning Tool for Online Whole Brain Classification from fMRI

Ori Cohen; Michal Ramot; Rafael Malach; Moshe Koppel; Doron Friedman

doi:10.3217/978-3-85125-378-8-34

A Generic Machine-Learning Tool for Online Whole Brain Classification from fMRI

Ori Cohen, Michal Ramot, Rafael Malach, Moshe Koppel, Doron Friedman

Department of Brain Sciences

Weizmann Institute of Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Objective : We have developed an efficient generic machine learning (ML) tool for realtime fMRI whole brain classification, which can be used to explore novel brain-computer interface (BCI) or advanced neurofeedback (NF) strategies.
Approach : We use information gain for isolating the most relevant voxels in the brain and a support vector machine classifier.
Main results : We have used our tool in three types of experiments: motor movement, motor imagery and visual categories.
Significance : We show high accuracy results in real-time, using an optimal number of voxels, with a shorter delay compared to the previous method based on regions of interest (ROI). Finally, our tool is integrated with a virtual environment and can be used to control a virtual avatar or a robot.

Original language	English
Title of host publication	Proceedings of the 6th International Brain-Computer Interface Conference 2014
Subtitle of host publication	The Future of Brain-Computer Interaction: Basics, Shortcomings, Users
Editors	Gernot Müller-Putz, Günther Bauernfeind, Clemens Brunner, David Steyrl, Selina Wriessnegger, Reinhold Scherer
Pages	133-136
Number of pages	4
DOIs	https://doi.org/10.3217/978-3-85125-378-8-34
State	Published - 2014
Event	6th International Brain-Computer Interface Conference - Graz, Austria Duration: 16 Sep 2014 → 19 Sep 2014 Conference number: 6 https://www.tugraz.at/institute/ine/graz-bci-conferences/6th-graz-bci-conference-2014/

Conference

Conference	6th International Brain-Computer Interface Conference
Abbreviated title	BCI
Country/Territory	Austria
City	Graz
Period	16/09/14 → 19/09/14
Internet address	https://www.tugraz.at/institute/ine/graz-bci-conferences/6th-graz-bci-conference-2014/

Access to Document

10.3217/978-3-85125-378-8-34License: Unspecified

https://www.tugraz.at/institute/ine/graz-bci-conferences/6th-graz-bci-conference-2014/License: Unspecified

Cite this

Cohen, O., Ramot, M., Malach, R., Koppel, M., & Friedman, D. (2014). A Generic Machine-Learning Tool for Online Whole Brain Classification from fMRI. In G. Müller-Putz, G. Bauernfeind, C. Brunner, D. Steyrl, S. Wriessnegger, & R. Scherer (Eds.), Proceedings of the 6th International Brain-Computer Interface Conference 2014: The Future of Brain-Computer Interaction: Basics, Shortcomings, Users (pp. 133-136) https://doi.org/10.3217/978-3-85125-378-8-34

Cohen, Ori ; Ramot, Michal ; Malach, Rafael et al. / A Generic Machine-Learning Tool for Online Whole Brain Classification from fMRI. Proceedings of the 6th International Brain-Computer Interface Conference 2014: The Future of Brain-Computer Interaction: Basics, Shortcomings, Users. editor / Gernot Müller-Putz ; Günther Bauernfeind ; Clemens Brunner ; David Steyrl ; Selina Wriessnegger ; Reinhold Scherer. 2014. pp. 133-136

@inproceedings{0c16d3620eda4a708e3c7ce3776f4c5f,

title = "A Generic Machine-Learning Tool for Online Whole Brain Classification from fMRI",

abstract = "Objective : We have developed an efficient generic machine learning (ML) tool for realtime fMRI whole brain classification, which can be used to explore novel brain-computer interface (BCI) or advanced neurofeedback (NF) strategies.Approach : We use information gain for isolating the most relevant voxels in the brain and a support vector machine classifier.Main results : We have used our tool in three types of experiments: motor movement, motor imagery and visual categories.Significance : We show high accuracy results in real-time, using an optimal number of voxels, with a shorter delay compared to the previous method based on regions of interest (ROI). Finally, our tool is integrated with a virtual environment and can be used to control a virtual avatar or a robot.",

author = "Ori Cohen and Michal Ramot and Rafael Malach and Moshe Koppel and Doron Friedman",

note = "This research was supported by the EU project VERE (number 257695), www.vereproject.eu; 6th International Brain-Computer Interface Conference ; Conference date: 16-09-2014 Through 19-09-2014",

year = "2014",

doi = "10.3217/978-3-85125-378-8-34",

language = "الإنجليزيّة",

isbn = "9783851253788",

pages = "133--136",

editor = "Gernot M{\"u}ller-Putz and G{\"u}nther Bauernfeind and Clemens Brunner and David Steyrl and Selina Wriessnegger and Reinhold Scherer",

booktitle = "Proceedings of the 6th International Brain-Computer Interface Conference 2014",

url = "https://www.tugraz.at/institute/ine/graz-bci-conferences/6th-graz-bci-conference-2014/",

}

Cohen, O, Ramot, M, Malach, R, Koppel, M & Friedman, D 2014, A Generic Machine-Learning Tool for Online Whole Brain Classification from fMRI. in G Müller-Putz, G Bauernfeind, C Brunner, D Steyrl, S Wriessnegger & R Scherer (eds), Proceedings of the 6th International Brain-Computer Interface Conference 2014: The Future of Brain-Computer Interaction: Basics, Shortcomings, Users. pp. 133-136, 6th International Brain-Computer Interface Conference, Graz, Austria, 16/09/14. https://doi.org/10.3217/978-3-85125-378-8-34

A Generic Machine-Learning Tool for Online Whole Brain Classification from fMRI. / Cohen, Ori; Ramot, Michal; Malach, Rafael et al.
Proceedings of the 6th International Brain-Computer Interface Conference 2014: The Future of Brain-Computer Interaction: Basics, Shortcomings, Users. ed. / Gernot Müller-Putz; Günther Bauernfeind; Clemens Brunner; David Steyrl; Selina Wriessnegger; Reinhold Scherer. 2014. p. 133-136.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - A Generic Machine-Learning Tool for Online Whole Brain Classification from fMRI

AU - Cohen, Ori

AU - Ramot, Michal

AU - Malach, Rafael

AU - Koppel, Moshe

AU - Friedman, Doron

N1 - Conference code: 6

PY - 2014

Y1 - 2014

N2 - Objective : We have developed an efficient generic machine learning (ML) tool for realtime fMRI whole brain classification, which can be used to explore novel brain-computer interface (BCI) or advanced neurofeedback (NF) strategies.Approach : We use information gain for isolating the most relevant voxels in the brain and a support vector machine classifier.Main results : We have used our tool in three types of experiments: motor movement, motor imagery and visual categories.Significance : We show high accuracy results in real-time, using an optimal number of voxels, with a shorter delay compared to the previous method based on regions of interest (ROI). Finally, our tool is integrated with a virtual environment and can be used to control a virtual avatar or a robot.

AB - Objective : We have developed an efficient generic machine learning (ML) tool for realtime fMRI whole brain classification, which can be used to explore novel brain-computer interface (BCI) or advanced neurofeedback (NF) strategies.Approach : We use information gain for isolating the most relevant voxels in the brain and a support vector machine classifier.Main results : We have used our tool in three types of experiments: motor movement, motor imagery and visual categories.Significance : We show high accuracy results in real-time, using an optimal number of voxels, with a shorter delay compared to the previous method based on regions of interest (ROI). Finally, our tool is integrated with a virtual environment and can be used to control a virtual avatar or a robot.

U2 - 10.3217/978-3-85125-378-8-34

DO - 10.3217/978-3-85125-378-8-34

M3 - منشور من مؤتمر

SN - 9783851253788

SP - 133

EP - 136

BT - Proceedings of the 6th International Brain-Computer Interface Conference 2014

A2 - Müller-Putz, Gernot

A2 - Bauernfeind, Günther

A2 - Brunner, Clemens

A2 - Steyrl, David

A2 - Wriessnegger, Selina

A2 - Scherer, Reinhold

T2 - 6th International Brain-Computer Interface Conference

Y2 - 16 September 2014 through 19 September 2014

ER -

Cohen O, Ramot M, Malach R, Koppel M, Friedman D. A Generic Machine-Learning Tool for Online Whole Brain Classification from fMRI. In Müller-Putz G, Bauernfeind G, Brunner C, Steyrl D, Wriessnegger S, Scherer R, editors, Proceedings of the 6th International Brain-Computer Interface Conference 2014: The Future of Brain-Computer Interaction: Basics, Shortcomings, Users. 2014. p. 133-136 doi: 10.3217/978-3-85125-378-8-34