Stable Sparse Classifiers Identify qEEG Signatures that Predict Learning Disabilities (NOS) Severity

Stable Sparse Classifiers Identify qEEG Signatures that Predict Learning Disabilities (NOS) Severity

In this paper, we present a novel methodology to solve the classification problem, based on sparse (data-driven) regressions, combined with techniques for ensuring stability, especially useful for high-dimensional datasets and small samples number. The sensitivity and specificity of the classifiers...

Full description

Bibliographic Details
Main Authors: Jorge Bosch-Bayard, Lídice Galán-García, Thalia Fernandez, Rolando B. Lirio, Maria L. Bringas-Vega, Milene Roca-Stappung, Josefina Ricardo-Garcell, Thalía Harmony, Pedro A. Valdes-Sosa
Format: Article
Language:English
Published: Frontiers Media S.A. 2018-01-01
Series:Frontiers in Neuroscience
Subjects:
LD-NOS classification
EEG classification
stability based biomarkers
non-parametric ROC
sparse classifiers
elastic-net
Online Access:http://journal.frontiersin.org/article/10.3389/fnins.2017.00749/full

Internet

http://journal.frontiersin.org/article/10.3389/fnins.2017.00749/full

Similar Items