Design of a neural network based adaptive noise canceler for broadband noise rejection

광대역 잡음제거를 위한 신경망 적응잡음제거기 설계

  • Published : 2002.04.01

Abstract

This paper describes a nonlinear adaptive noise canceler(ANC) using neural networks(NN) based on filter to make up for the drawback of the conventional ANC with the linear adaptive filter. The proposed ANC was tested its noise rejection performance using broadband time-varying noise signal and compared with the ANC of TDL linear filter. Experimental results show that in cases of nonlinear correlations between the noise of primary input and reference input, the neural network based ANC outperforms the linear ANC with respect to mean square error It is also verified that the recurrent NN adaptive filter is superior to the feedforward NN filter. Thus, we identify that the NN adaptive filter is more effective than the linear adaptive filter for rejection of broadband time-varying noise in the ANC.

본 논문에서는 선형적응필터를 사용하고 있는 기존의 적응잡음제거 기 의 단점을 보완하기 위해 신경망 적응필터를 이용한 비선형 적응잡음제거기를 다루고 있다. 제안된 적응잡음제거기는 광대역 시변 잡음신호를 사용하여 잡음제거 성능을 조사하였으며 상대평가를 위해 TDL (tapped-delay -line) 선형필터의 적응잡음제거기와 비교하였다. 실험결과에 의하면 적응잡음 제거기의 주입력에 포함된 잡음과 기준입력 사이에 비선형적인 상관관계가 존재하는 경우 신경망 적응잡음제거기는 평균자승오차값을 기준으로 선형잡음제거기보다 더 우수한 성능을 보여주었으며, 또한 리커런트 신경망 적응필터가 순방향 신경망 필터보다 성능이 우수하였다. 따라서 적응잡음제거기에서 광대역 시변잡음을 제거하는데 신경망 적응필터가 선형 적응필터보다 효과적임을 확인하였다.

Keywords

References

  1. Neural Networks v.8 no.2 Recurrent Radial Basis Function Networks for Adaptive Noise Cancellation S.A.Billings;C.F.Fung
  2. Nonlinear Digital Filters,Principles and Applications I.Patas;A.N.Venetsanopou
  3. IEEE Proc-Pt.Circ.,Dev.and Syst. v.138 no.4 Analysis and VLSI architecture of a nonlinear edge-preserving noise-smoothing image filter Y.Papananos;D.Anastassiou
  4. Adaptive Signal Processing B.Widrow;S.D.Stearns
  5. Pro.of IEEE Int.Conf.on Neural Networks v.7 System Identification and Noise Cancellation via neural-Net computing G.H.Park;Y.H.Pao
  6. Proc.Int.Symp.Circuits and Systems v.3 A new adaptive algorithm of adaptive digital filters using neural networks A.Miyazaki;M.Nakata
  7. IEEE Trans.on circuits and systems-II:Analog and digital signal processing v.41 no.5 New Nonlinear Adaptive FIR Digital Filter for Broadhand Noise Cancellation H.K.Kwan;Q.P.Li
  8. Neural Networks for Signal processing B.Kosko
  9. Adaptive Filter Theory(2nd edition) S.Haykin
  10. Congnitive Science v.14 Finding structure in time J.L.Elman
  11. Neural Networks:A Comprehensive Foundation S.Haykin