A Study on the Adaptive Neural Network Filter for Signal Detection

신호 검출을 위한 적응형 신경망 필터에 관한 연구

  • Published : 2004.04.01

Abstract

In this paper, the adaptive noise canceler using neural network with backpropagation is designed. The adaptive noise canceler using the least mean square algorithm has the large correlativity of the reference signal. The performance of the adaptive noise canceler shows the limitation when the information signal is relatively small to the noise. The system proposed in this paper plays an important role in denoising these signals. In addition, the experiments are carried out to analyze the effects of the number of hidden layers and nodes about the system. The performance of the proposed adaptive noise canceler is compared with that of the system which is used the least mean square algorithm.

본 논문에서는 다층 신경회로망의 구조를 가지며, 백프로퍼게이션 학습 알고리즘을 이용한 적응신호처리 시스템을 구현하였다. 최소자승 알고리즘을 이용한 적응 잡음 제거기는 기준 신호와 잡음과의 상관도에 영향을 많이 받고, 정보 신호가 잡음에 비하여 상대적으로 작은 경우에 한계를 보이고 있다. 이와 같은 잡음에 대하여 본 논문에서 제안된 시스템은 좋은 성능을 보인다. 또한, 은닉층의 수와 노드 수를 다르게 구성했을 경우에 시스템의 출력에 미치는 결과에 대하여 분석하였다. 제안된 적응 신호처리 시스템의 장점을 알아보기 위하여 성능 평가의 기준이 되는 최소자승 알고리즘을 이용한 시스템과 비교하였다.

Keywords

References

  1. Itelligent Control and Automation 2002. Proceedings of the 4th World Congress on v.2 Adaptive noise canceler and its addlications for systems with time-variant correlative noise Liu Tienan
  2. Adaptive Systems for Signal Processing, Communications, and Control Symposium 2000. AS-SPCC. The IEEE 2000 Non-linear eggects in LMS adaptive filters Reuter,M.;Quirk,K.;Zeidler,J.;Milstein,L.
  3. Circuits and Systems Ⅱ: Analog and Digital Signal Processing, IEEE Transactions on v.46 no.Issue: 6 A novel adaptive mismatch cancellation system for quadrature IF radio receivers Li Yu;Snelgrove,W.M.
  4. Adaptive Filter Theory Simon Haykin
  5. Proc. IEEE v.63 no.12 Adaptive noise cacelling : Principles and applications Widrow,B.;Glover,J.R.;McCool,J.M;Kaunitz,J;Williams,C.S.;Heam,R.H.
  6. Neural Network Design Martin T. Hagan;Howard B. Demuth;Mark Beale
  7. ICASSP on Multidimensional signal processing, Neutal Networks v.4 On the influence of the number of layers on the performance and convergence behvior of the Backpropagation Algorothm Mohamde IBNKAHLA
  8. Proceedings of the IEEE v.78 Backpropagation theory time : what it is and how to do it P.J.Werbos