Related Experiment Video
Updated: May 24, 2026
Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data
Published on: June 26, 2013
On the decoding of intracranial data using sparse orthonormalized partial least squares.
Marcel A J van Gerven1, Zenas C Chao, Tom Heskes
1Radboud University Nijmegen, Donders Institute for Brain, Cognition and Behaviour, Donders Centre for Cognition, Montessorilaan 3, 6500 HE Nijmegen, The Netherlands. m.vangerven@donders.ru.nl
A new decoding method, sparse orthonormalized partial least squares (SOPLS), achieves high performance in motor decoding from electrocorticogram signals. SOPLS offers a more interpretable and compact model for neuroprosthetics research.
Area of Science:
- * Neuroscience
- * Biomedical Engineering
Background:
- * Electrocorticogram (ECoG) signals are used for decoding motor output.
- * Multivariate partial least-squares (PLS) regression is effective but complex.
- * Robust decoding over prolonged periods is a key challenge.
Purpose of the Study:
- * To develop a novel decoding method, sparse orthonormalized partial least squares (SOPLS).
- * To compare SOPLS performance against existing PLS methods.
- * To enhance the interpretability of decoding components.
Main Methods:
- * Developed SOPLS, a novel decoding algorithm.
- * Applied SOPLS to a subset of ECoG data from previous studies.
- * Analyzed the sparse components generated by SOPLS.
Main Results:
- * SOPLS achieved comparable decoding performance to PLS with fewer components.
- * Identified two sparse components, interpretable as motor parameter combinations.
- * Demonstrated the involvement of beta and gamma band responses in motor cortex prediction.
Conclusions:
- * SOPLS provides a sparse, compact, and interpretable decoding model.
- * Facilitates understanding of spectral, spatial, and temporal components in decoding.
- * SOPLS is a valuable tool for neuroprosthetics research.
More Related Videos
06:50Analyzing Neural Activity and Connectivity Using Intracranial EEG Data with SPM Software
Published on: October 30, 2018
11:14A Novel Experimental and Analytical Approach to the Multimodal Neural Decoding of Intent During Social Interaction in Freely-behaving Human Infants
Published on: October 4, 2015