Quadratic programming feature selection for multicorrelated signal decoding with partial least squares

This paper investigates dimensionality reduction problem for signal decoding. Its main application is brain-computer interface modeling. The challenge is high redundancy in the data description. Data combines time series of two origins: design space: brain cortex signals and target space: limb motion signals. High correlations among measurements of complex signals lead to multiple correlations. This case studies correlations in both input and target spaces that carry heterogeneous data. This paper proposes feature selection algorithms to construct simple and stable forecasting model. It extends ideas of the quadratic programming feature selection approach and selects non-correlated features that are relevant to the target. The proposed methods take into account dependencies in both design and target space and select features, which fit both spaces jointly. The computational experiment was carried out using an electrocorticogram (ECoG) dataset. The obtained models predict hand motions using signals of the brain cortex. The partial least squares (PLS) regression model is used as the base model for dimensionality reduction. The best result is obtained by PLS algorithm, that reduces space dimensionality using the QPFS.

Automated summary

This paper investigates dimensionality reduction problem in signal decoding, specifically in the field of brain-computer interface modeling. It proposes a feature selection algorithm to construct a simple and stable forecasting model. The algorithm considers the correlations in both design and target spaces and selects features that fit both. Experimental results demonstrate that the algorithm achieves the best result in reducing space dimensionality.