Incomplete multi-view feature selection with adaptive consensus graph constraint for Parkinson's disease diagnosis
Abstract: Highlights•We introduce multiple index matrices to mitigate the interference caused by missing samples during the calculation process.•The proposed method integrates low-dimensional consensus representation and similarity learning.•The corrected similarity matrix is used to compute the missing data in the corresponding view.•Experimental results show that our method has the best performance.
External IDs:dblp:journals/asc/HuangLWCYSZG25
Loading