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|
|Number of pages||5|
|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
|Name||Conference Record - Asilomar Conference on Signals, Systems and Computers|
|Conference||55th Asilomar Conference on Signals, Systems and Computers, ACSSC 2021|
|City||Virtual, Pacific Grove|
|Period||10/31/21 → 11/3/21|
Bibliographical noteFunding Information:
This paper has been supported in part by the NSF under grant number CCF-1814759.
© 2021 IEEE.