Characterizing the transient electrocardiographic signature of ischemic stress using Laplacian Eigenmaps for dimensionality reduction.
Wilson W. GoodBurak EremBrian ZengerJaume Coll-FontJake A. BergquistDana H. BrooksRob S. MacLeodPublished in: Comput. Biol. Medicine (2020)
Keyphrases
- laplacian eigenmaps
- dimensionality reduction
- manifold learning
- nonlinear dimensionality reduction
- kernel pca
- locally linear embedding
- low dimensional
- dimensionality reduction methods
- high dimensional data
- high dimensional
- principal component analysis
- feature extraction
- pattern recognition
- subspace learning
- linear discriminant analysis
- preprocessing step
- data points
- feature space
- high dimensionality
- input space
- euclidean distance
- lower dimensional
- random projections
- principal components
- metric learning
- feature selection
- euclidean space
- principal components analysis
- nearest neighbor
- singular value decomposition
- feature set
- data sets
- semi supervised
- feature vectors
- multidimensional scaling
- multi dimensional
- empirical mode decomposition
- computer vision