Dimensionality reduction using elastic measures
- Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)
- Boeing, Albuquerque, NM (United States)
- Moffitt Cancer Center, Tampa, FL (United States)
With the recent surge in big data analytics for hyperdimensional data, there is a renewed interest in dimensionality reduction techniques. In order for these methods to improve performance gains and understanding of the underlying data, a proper metric needs to be identified. This step is often overlooked, and metrics are typically chosen without consideration of the underlying geometry of the data. Here, in this paper, we present a method for incorporating elastic metrics into the t-distributed stochastic neighbour embedding (t-SNE) and Uniform Manifold Approximation and Projection (UMAP). We apply our method to functional data, which is uniquely characterized by rotations, parameterization and scale. If these properties are ignored, they can lead to incorrect analysis and poor classification performance. Through our method, we demonstrate improved performance on shape identification tasks for three benchmark data sets (MPEG-7, Car data set and Plane data set of Thankoor), where we achieve 0.77, 0.95 and 1.00 F1 score, respectively.
- Research Organization:
- Sandia National Laboratories (SNL-NM), Albuquerque, NM (United States)
- Sponsoring Organization:
- USDOE Laboratory Directed Research and Development (LDRD) Program; USDOE National Nuclear Security Administration (NNSA)
- Grant/Contract Number:
- NA0003525
- OSTI ID:
- 2311587
- Alternate ID(s):
- OSTI ID: 1970420
- Report Number(s):
- SAND--2023-04438J
- Journal Information:
- Stat, Journal Name: Stat Journal Issue: 1 Vol. 12; ISSN 2049-1573
- Publisher:
- WileyCopyright Statement
- Country of Publication:
- United States
- Language:
- English