Supervised Hyperalignment for Multisubject fMRI Data Alignment

Hyperalignment (HA) has been widely employed in multivariate pattern (MVP) analysis to discover the cognitive states in the human brains based on multisubject functional magnetic resonance imaging (fMRI) data sets. Most of the existing HA methods utilized unsupervised approaches, where they only maximized the correlation between the voxels with the same position in the time series. However, these unsupervised solutions may not be optimum for handling the functional alignment in the supervised MVP problems. This article proposes a supervised HA (SHA) method to ensure better functional alignment for MVP analysis, where the proposed method provides a supervised shared space that can maximize the correlation among the stimuli belonging to the same category and minimize the correlation between distinct categories of stimuli. Furthermore, SHA employs a generalized optimization solution, which generates the shared space and calculates the mapped features in a single iteration, hence with optimum time and space complexities for large data sets. Experiments on multisubject data sets demonstrate that the SHA method achieves up to 19% better performance for multiclass problems over the state-of-the-art HA algorithms.