Weighted pair-wise scatter to improve linear discriminant analysis
US6567771B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Feb 16, 2001 |
| Grant date | May 20, 2003 |
| Priority date | — |
| Expiry date | Aug 11, 2021 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06F18/24317
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
In general, the present invention determines and applies weights for class pairs. The weights are selected to better separate, in reduced-dimensional class space, the classes that are confusable in normal-dimensional class space. During the dimension-reducing process, higher weights are preferably assigned to more confusable class pairs while lower weights are assigned to less confusable class pairs. As compared to unweighted Linear Discriminant Analysis (LDA), the present invention will result in decreased confusability of class pairs in reduced-dimensional class space. The weights can be assigned through a monotonically decreasing function of distance, which assigns lower weights to class pairs that are separated by larger distances. Additionally, weights may also be assigned through a monotonically increasing function of confusability, in which higher weights would be assigned to class pairs that are more confusable.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.