Advanced search
2 files | 2.39 MB Add to list

System modeling for active noise control with reservoir computing

Jens Nyman (UGent) , Ken Caluwaerts (UGent) , Tim Waegeman and Benjamin Schrauwen (UGent)
Author
Organization
Abstract
This paper investigates the use of reservoir computing for active noise control (ANC). It is shown that the ANC problem can be solved by a concatenation of physically present subsystems. These subsystems can be modelled by reservoirs that are trained, using one shot learning. This approach is compared to genetic algorithms tuning a Volterra filter. Experimental results show that our approach works well as system model, meaning that a reservoir trained on white noise performs good on other input signals as well. This is a major advantage over genetic algorithms that generalize rather badly. Furthermore, our approach needs less data and this data can be gathered in one experiment only.
Keywords
Active Noise Control (ANC), Reservoir Computing, System Modeling

Downloads

  • (...).pdf
    • full text
    • |
    • UGent only
    • |
    • PDF
    • |
    • 1.18 MB
  • System Modeling for Active Noise Control with.pdf
    • full text
    • |
    • open access
    • |
    • PDF
    • |
    • 1.20 MB

Citation

Please use this url to cite or link to this publication:

MLA
Nyman, Jens, et al. “System Modeling for Active Noise Control with Reservoir Computing.” 9th IASTED International Conference on Signal Processing, Pattern Recognition, and Applications, Proceedings, edited by Maria Petrou, ACTA Press, 2012, pp. 162–67.
APA
Nyman, J., Caluwaerts, K., Waegeman, T., & Schrauwen, B. (2012). System modeling for active noise control with reservoir computing. In M. Petrou (Ed.), 9th IASTED International Conference on Signal Processing, Pattern Recognition, and Applications, Proceedings (pp. 162–167). USA: ACTA Press.
Chicago author-date
Nyman, Jens, Ken Caluwaerts, Tim Waegeman, and Benjamin Schrauwen. 2012. “System Modeling for Active Noise Control with Reservoir Computing.” In 9th IASTED International Conference on Signal Processing, Pattern Recognition, and Applications, Proceedings, edited by Maria Petrou, 162–67. USA: ACTA Press.
Chicago author-date (all authors)
Nyman, Jens, Ken Caluwaerts, Tim Waegeman, and Benjamin Schrauwen. 2012. “System Modeling for Active Noise Control with Reservoir Computing.” In 9th IASTED International Conference on Signal Processing, Pattern Recognition, and Applications, Proceedings, ed by. Maria Petrou, 162–167. USA: ACTA Press.
Vancouver
1.
Nyman J, Caluwaerts K, Waegeman T, Schrauwen B. System modeling for active noise control with reservoir computing. In: Petrou M, editor. 9th IASTED International Conference on Signal Processing, Pattern Recognition, and Applications, Proceedings. USA: ACTA Press; 2012. p. 162–7.
IEEE
[1]
J. Nyman, K. Caluwaerts, T. Waegeman, and B. Schrauwen, “System modeling for active noise control with reservoir computing,” in 9th IASTED International Conference on Signal Processing, Pattern Recognition, and Applications, Proceedings, Crete, Greece, 2012, pp. 162–167.
@inproceedings{2915739,
  abstract     = {{This paper investigates the use of reservoir computing for active noise control (ANC). It is shown that the ANC problem can be solved by a concatenation of physically present subsystems. These subsystems can be modelled by reservoirs that are trained, using one shot learning. This approach is compared to genetic algorithms tuning a Volterra filter. Experimental results show that our approach works well as system model, meaning that a reservoir trained on white noise performs good on other input signals as well. This is a major advantage over genetic algorithms that generalize rather badly. Furthermore, our approach needs less data and this data can be gathered in one experiment only.}},
  articleno    = {{12}},
  author       = {{Nyman, Jens and Caluwaerts, Ken and Waegeman, Tim and Schrauwen, Benjamin}},
  booktitle    = {{9th IASTED International Conference on Signal Processing, Pattern Recognition, and Applications, Proceedings}},
  editor       = {{Petrou, Maria}},
  isbn         = {{9780889869219}},
  keywords     = {{Active Noise Control (ANC),Reservoir Computing,System Modeling}},
  language     = {{eng}},
  location     = {{Crete, Greece}},
  pages        = {{12:162--12:167}},
  publisher    = {{ACTA Press}},
  title        = {{System modeling for active noise control with reservoir computing}},
  year         = {{2012}},
}