MVPAlab: A machine learning decoding toolbox for multidimensional electroencephalography data

David López-García; José M G Peñalver; Juan M Górriz; María Ruz

doi:10.1016/j.cmpb.2021.106549

MVPAlab: A machine learning decoding toolbox for multidimensional electroencephalography data

Comput Methods Programs Biomed. 2022 Feb:214:106549. doi: 10.1016/j.cmpb.2021.106549. Epub 2021 Nov 29.

Authors

David López-García¹, José M G Peñalver², Juan M Górriz³, María Ruz⁴

Affiliations

¹ Mind, Brain and Behavior Research Center, University of Granada, Spain. Electronic address: dlopez@ugr.es.
² Mind, Brain and Behavior Research Center, University of Granada, Spain.
³ Data Science & Computational Intelligence Institute, University of Granada, Spain.
⁴ Mind, Brain and Behavior Research Center, Department of Experimental Psychology, University of Granada, Spain.

PMID: 34910975
DOI: 10.1016/j.cmpb.2021.106549

Abstract

Background and objective: The study of brain function has recently expanded from classical univariate to multivariate analyses. These multivariate, machine learning-based algorithms afford neuroscientists extracting more detailed and richer information from the data. However, the implementation of these procedures is usually challenging, especially for researchers with no coding experience. To address this problem, we have developed MVPAlab, a MATLAB-based, flexible decoding toolbox for multidimensional electroencephalography and magnetoencephalography data.

Methods: The MVPAlab Toolbox implements several machine learning algorithms to compute multivariate pattern analyses, cross-classification, temporal generalization matrices and feature and frequency contribution analyses. It also provides access to an extensive set of preprocessing routines for, among others, data normalization, data smoothing, dimensionality reduction and supertrial generation. To draw statistical inferences at the group level, MVPAlab includes a non-parametric cluster-based permutation approach.

Results: A sample electroencephalography dataset was compiled to test all the MVPAlab main functionalities. Significant clusters (p<0.01) were found for the proposed decoding analyses and different configurations, proving the software capability for discriminating between different experimental conditions.

Conclusions: This toolbox has been designed to include an easy-to-use and intuitive graphic user interface and data representation software, which makes MVPAlab a very convenient tool for users with few or no previous coding experience. In addition, MVPAlab is not for beginners only, as it implements several high and low-level routines allowing more experienced users to design their own projects in a highly flexible manner.

Keywords: Classification; Cross-classification; Cross-validation; Decoding; EEG; MEG; MVPA; MVPAlab toolbox; Machine learning; Multivariate pattern analysis.

MeSH terms

Algorithms
Brain
Electroencephalography*
Machine Learning
Magnetoencephalography*
Software