Title :
Schroedinger Eigenmaps for the Analysis of Biomedical Data
Author :
Czaja, Wojciech ; Ehler, M.
Author_Institution :
Dept. of Math., Univ. of Maryland, College Park, MD, USA
Abstract :
We introduce Schroedinger Eigenmaps (SE), a new semi-supervised manifold learning and recovery technique. This method is based on an implementation of graph Schroedinger operators with appropriately constructed barrier potentials as carriers of labeled information. We use our approach for the analysis of standard biomedical datasets and new multispectral retinal images.
Keywords :
eigenvalues and eigenfunctions; graph theory; learning (artificial intelligence); medical image processing; retinal recognition; SE; biomedical data analysis; graph Schroedinger operators; multispectral retinal images; schroedinger Eigenmaps; semisupervised manifold learning; Biomedical imaging; Eigenvalues and eigenfunctions; Kernel; Labeling; Laplace equations; Manifolds; Vectors; Laplacian Eigenmaps; Schroedinger Eigenmaps; Schroedinger operator on a graph; barrier potential; dimension reduction; manifold learning; Algorithms; Artificial Intelligence; Biomedical Research; Breast Neoplasms; Data Interpretation, Statistical; Data Mining; Databases, Factual; Female; Heart Diseases; Humans; Pattern Recognition, Automated; Retinal Diseases;
Journal_Title :
Pattern Analysis and Machine Intelligence, IEEE Transactions on
DOI :
10.1109/TPAMI.2012.270
