Abstract
This paper proposes new variable regularized (VR) partial update (PU) affine projection algorithms (APAs) for distributed estimation over adaptive networks. They extend the conventional diffuse PU-APAs (Diff-PU-APAs) by imposing a regularization parameter to mitigate possible impairments, such as modeling uncertainties and lacking of excitation, and to deal with sparse channel estimation problems. In addition, the mean and mean square convergence performance of the proposed algorithms is studied, which provides convergence conditions of the proposed algorithms. The performance of the Diff-VR-PU-APAs is demonstrated by several computer simulations in distributed networks.
Original language | English |
---|---|
Title of host publication | Proceedings - 14th International Symposium on Pervasive Systems, Algorithms and Networks, I-SPAN 2017, 11th International Conference on Frontier of Computer Science and Technology, FCST 2017 and 3rd International Symposium of Creative Computing, ISCC 2017 |
Publisher | IEEE |
Pages | 325-330 |
Number of pages | 6 |
Volume | 2017-November |
ISBN (Electronic) | 9781538608401 |
DOIs | |
Publication status | Published - 27 Nov 2017 |
Event | 14th International Symposium on Pervasive Systems, Algorithms and Networks, I-SPAN 2017, 11th International Conference on Frontier of Computer Science and Technology, FCST 2017 and 3rd International Symposium of Creative Computing, ISCC 2017 - Exeter, Devon, United Kingdom Duration: 21 Jun 2017 → 23 Jun 2017 |
Conference
Conference | 14th International Symposium on Pervasive Systems, Algorithms and Networks, I-SPAN 2017, 11th International Conference on Frontier of Computer Science and Technology, FCST 2017 and 3rd International Symposium of Creative Computing, ISCC 2017 |
---|---|
Country/Territory | United Kingdom |
City | Exeter, Devon |
Period | 21/06/17 → 23/06/17 |
Keywords
- Adaptive networks
- Affine projection
- Distributed estimation
- Partial update
- Variable regularization
ASJC Scopus subject areas
- Industrial and Manufacturing Engineering
- Control and Systems Engineering
- Computer Science(all)
- Electrical and Electronic Engineering