“…In the experiment, nine methods are selected for comparison to validate the effectiveness of the proposed framework. The baseline methods include MKSVM [ 33 ], MKSVM with Lasso feature selection performed independently on single modality (Lasso-MKSVM) [ 35 ], manifold regularized-based multimodal feature selection (M2TFS) [ 15 ], hypergraph-based multimodal feature selection (HMTFS) [ 16 ], ASMFS [ 17 ], self-expression topological manifolds-based multimodal feature selection (SETMFS) [ 18 ], multimodal classification framework based on ordinary features’ latent relation (OLR), unimodal fMRI and unimodal ASL. The first six methods and unimodal fMRI, along with the proposed framework, depend on SHMR-based brain functional networks to obtain hypergraph feature matrices.…”