NONLINEAR FILTERING OF RANDOM SEQUENCES WITH EXTENDED LEAST-SQUARE METHOD 1
For nonlinear random sequences filtering the extended least-square method is proposed. The received suboptimal filter equations include linearization for nonlinear measurement function only. The filter gain coefficient can be calculated by formulas without solving additional equations as in extended...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | Russian |
| Published: |
National Academy of Sciences of Belarus, the United Institute of Informatics Problems
2018-03-01
|
| Series: | Informatika |
| Subjects: | |
| Online Access: | https://inf.grid.by/jour/article/view/316 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | For nonlinear random sequences filtering the extended least-square method is proposed. The received suboptimal filter equations include linearization for nonlinear measurement function only. The filter gain coefficient can be calculated by formulas without solving additional equations as in extended Kalman filter. In comparison with the extended Kalman filter, the implementation of the proposed filter has less computational complexity. Examples of a comparative accuracy evaluation of the proposed filter with the extended Kalman filter are given. |
|---|---|
| ISSN: | 1816-0301 |