Biological Gender Classification from fMRI via Hyperdimensional Computing

Ryan Billmeyer; Keshab K. Parhi

doi:10.1109/IEEECONF53345.2021.9723179

Biological Gender Classification from fMRI via Hyperdimensional Computing

Ryan Billmeyer, Keshab K. Parhi

Electrical and Computer Engineering

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

9 Scopus citations

Abstract

Hyperdimensional (HD) computing is a brain-inspired form of computing based on the manipulation of high-dimensional vectors. Offering robust data representation and relatively fast learning, HD computing is a promising candidate for energy-efficient classification of biological signals. This paper describes the application of HD computing-based machine learning to the classification of biological gender from resting-state and task functional magnetic resonance imaging (fMRI) from the publicly available Human Connectome Project (HCP). The developed HD algorithm derives predictive features through mean dynamic functional connectivity (dFC) analysis. Record encoding is employed to map features onto hyperdimensional space. Utilizing adaptive retraining techniques, the HD computing-based classifier achieves an average biological gender classification accuracy of 87%, as compared to 84% achieved by edge entropy measure.

Original language	English (US)
Title of host publication	55th Asilomar Conference on Signals, Systems and Computers, ACSSC 2021
Editors	Michael B. Matthews
Publisher	IEEE Computer Society
Pages	578-582
Number of pages	5
ISBN (Electronic)	9781665458283
DOIs	https://doi.org/10.1109/IEEECONF53345.2021.9723179
State	Published - 2021
Event	55th Asilomar Conference on Signals, Systems and Computers, ACSSC 2021 - Virtual, Pacific Grove, United States Duration: Oct 31 2021 → Nov 3 2021

Publication series

Name	Conference Record - Asilomar Conference on Signals, Systems and Computers
Volume	2021-October
ISSN (Print)	1058-6393

Conference

Conference	55th Asilomar Conference on Signals, Systems and Computers, ACSSC 2021
Country/Territory	United States
City	Virtual, Pacific Grove
Period	10/31/21 → 11/3/21

Bibliographical note

Funding Information:
This paper has been supported in part by the NSF under grant number CCF-1814759.

Publisher Copyright:
© 2021 IEEE.

Publisher link

10.1109/IEEECONF53345.2021.9723179

Find It

Find It at U of M Libraries

Cite this

Billmeyer, R., & Parhi, K. K. (2021). Biological Gender Classification from fMRI via Hyperdimensional Computing. In M. B. Matthews (Ed.), 55th Asilomar Conference on Signals, Systems and Computers, ACSSC 2021 (pp. 578-582). (Conference Record - Asilomar Conference on Signals, Systems and Computers; Vol. 2021-October). IEEE Computer Society. https://doi.org/10.1109/IEEECONF53345.2021.9723179

Biological Gender Classification from fMRI via Hyperdimensional Computing. / Billmeyer, Ryan; Parhi, Keshab K.
55th Asilomar Conference on Signals, Systems and Computers, ACSSC 2021. ed. / Michael B. Matthews. IEEE Computer Society, 2021. p. 578-582 (Conference Record - Asilomar Conference on Signals, Systems and Computers; Vol. 2021-October).

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

Billmeyer, R & Parhi, KK 2021, Biological Gender Classification from fMRI via Hyperdimensional Computing. in MB Matthews (ed.), 55th Asilomar Conference on Signals, Systems and Computers, ACSSC 2021. Conference Record - Asilomar Conference on Signals, Systems and Computers, vol. 2021-October, IEEE Computer Society, pp. 578-582, 55th Asilomar Conference on Signals, Systems and Computers, ACSSC 2021, Virtual, Pacific Grove, United States, 10/31/21. https://doi.org/10.1109/IEEECONF53345.2021.9723179

@inproceedings{ce8fd445a6554f28a9e576f103162e21,

title = "Biological Gender Classification from fMRI via Hyperdimensional Computing",

abstract = "Hyperdimensional (HD) computing is a brain-inspired form of computing based on the manipulation of high-dimensional vectors. Offering robust data representation and relatively fast learning, HD computing is a promising candidate for energy-efficient classification of biological signals. This paper describes the application of HD computing-based machine learning to the classification of biological gender from resting-state and task functional magnetic resonance imaging (fMRI) from the publicly available Human Connectome Project (HCP). The developed HD algorithm derives predictive features through mean dynamic functional connectivity (dFC) analysis. Record encoding is employed to map features onto hyperdimensional space. Utilizing adaptive retraining techniques, the HD computing-based classifier achieves an average biological gender classification accuracy of 87%, as compared to 84% achieved by edge entropy measure. ",

author = "Ryan Billmeyer and Parhi, {Keshab K.}",

note = "Funding Information: This paper has been supported in part by the NSF under grant number CCF-1814759. Publisher Copyright: {\textcopyright} 2021 IEEE.; 55th Asilomar Conference on Signals, Systems and Computers, ACSSC 2021 ; Conference date: 31-10-2021 Through 03-11-2021",

year = "2021",

doi = "10.1109/IEEECONF53345.2021.9723179",

language = "English (US)",

series = "Conference Record - Asilomar Conference on Signals, Systems and Computers",

publisher = "IEEE Computer Society",

pages = "578--582",

editor = "Matthews, {Michael B.}",

booktitle = "55th Asilomar Conference on Signals, Systems and Computers, ACSSC 2021",

}

TY - GEN

T1 - Biological Gender Classification from fMRI via Hyperdimensional Computing

AU - Billmeyer, Ryan

AU - Parhi, Keshab K.

PY - 2021

Y1 - 2021

N2 - Hyperdimensional (HD) computing is a brain-inspired form of computing based on the manipulation of high-dimensional vectors. Offering robust data representation and relatively fast learning, HD computing is a promising candidate for energy-efficient classification of biological signals. This paper describes the application of HD computing-based machine learning to the classification of biological gender from resting-state and task functional magnetic resonance imaging (fMRI) from the publicly available Human Connectome Project (HCP). The developed HD algorithm derives predictive features through mean dynamic functional connectivity (dFC) analysis. Record encoding is employed to map features onto hyperdimensional space. Utilizing adaptive retraining techniques, the HD computing-based classifier achieves an average biological gender classification accuracy of 87%, as compared to 84% achieved by edge entropy measure.

AB - Hyperdimensional (HD) computing is a brain-inspired form of computing based on the manipulation of high-dimensional vectors. Offering robust data representation and relatively fast learning, HD computing is a promising candidate for energy-efficient classification of biological signals. This paper describes the application of HD computing-based machine learning to the classification of biological gender from resting-state and task functional magnetic resonance imaging (fMRI) from the publicly available Human Connectome Project (HCP). The developed HD algorithm derives predictive features through mean dynamic functional connectivity (dFC) analysis. Record encoding is employed to map features onto hyperdimensional space. Utilizing adaptive retraining techniques, the HD computing-based classifier achieves an average biological gender classification accuracy of 87%, as compared to 84% achieved by edge entropy measure.

UR - http://www.scopus.com/inward/record.url?scp=85127050482&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85127050482&partnerID=8YFLogxK

U2 - 10.1109/IEEECONF53345.2021.9723179

DO - 10.1109/IEEECONF53345.2021.9723179

M3 - Conference contribution

AN - SCOPUS:85127050482

T3 - Conference Record - Asilomar Conference on Signals, Systems and Computers

SP - 578

EP - 582

BT - 55th Asilomar Conference on Signals, Systems and Computers, ACSSC 2021

A2 - Matthews, Michael B.

PB - IEEE Computer Society

T2 - 55th Asilomar Conference on Signals, Systems and Computers, ACSSC 2021

Y2 - 31 October 2021 through 3 November 2021

ER -

Biological Gender Classification from fMRI via Hyperdimensional Computing

Abstract

Publication series

Conference

Bibliographical note

Publisher link

Find It

Other files and links

Fingerprint

Cite this