Journal of the Institute of Electronics Engineers of Korea SP (대한전자공학회논문지SP)

The Institute of Electronics and Information Engineers (대한전자공학회)
권호 표지

Nonlinear Adaptive Prediction using Locally and Globally Recurrent Neural Networks

지역 및 광역 리커런트 신경망을 이용한 비선형 적응예측

  • 최한고 (금오공과대학교 전자공학부)
  • Published : 2003.01.01
Download PDF
⟨ Previous Next ⟩

Abstract

Dynamic neural networks have been applied to diverse fields requiring temporal signal processing such as signal prediction. This paper proposes the hybrid network, composed of locally(LRNN) and globally recurrent neural networks(GRNN), to improve dynamics of multilayered recurrent networks(RNN) and then describes nonlinear adaptive prediction using the proposed network as an adaptive filter. The hybrid network consists of IIR-MLP and Elman RNN as LRNN and GRNN, respectively. The proposed network is evaluated in nonlinear signal prediction and compared with Elman RNN and IIR-MLP networks for the relative comparison of prediction performance. Experimental results show that the hybrid network performs better with respect to convergence speed and accuracy, indicating that the proposed network can be a more effective prediction model than conventional multilayered recurrent networks in nonlinear prediction for nonstationary signals.

동적 신경망은 신호예측과 같이 temporal 신호처리가 요구되는 여러 분야에 적용되어 왔다. 본 논문에서는 다층 리커런트 신경망(RNN)의 동특성을 향상시키기 위해 지역 궤환 신경망(LRNN)과 광역 궤환 신경망(CRNN)으로 구성된 합성 신경망을 제안하고, 적응필터로 제안된 신경망을 사용하여 비선형 적응예측을 다루고 있다. 합성 신경망은 LRNN으로 IIR-MLP와 CRNN으로 Elman RNN 신경망으로 구성되어 있다. 제안된 신경망은 비선형 신호예측을 통해 평가되었으며, 예측 성능의 상대적인 비교를 위해 Elman RNN과 IIR-MLP 신경망과 상호 비교하였다. 실험결과에 의하면 합성 신경망은 수렴속도과 정확도에서 더 우수한 성능을 보여줌으로써, 제안된 신경망이 기존의 다층 리커런트 신경망보다 비정적 신호에 대한 비선형 예측에 더 효과적인 예측모델임을 확인하였다.

Keywords

References

  1. P. M. Ferreira, E. A. Faria, and A. E. Ruano, Yazdizadeh and K. Khorasani, 'Neural network models in greenhouse air temperature prediction', Neurocomputing, Vol. 43, No. 1/4, pp. 51-75, 2002 https://doi.org/10.1016/S0925-2312(01)00620-8
  2. J. Park and D. W. Edington, Yazdizadeh and K. Khorasani, 'A sequential neural network model for diabetes prediction', Artificial intelligence in medicine, Vol. 23, No. 3, pp. 277-293, 2001 https://doi.org/10.1016/S0933-3657(01)00086-0
  3. A. Yazdizadeh and K. Khorasani, 'Adaptive time delay neural network structures fornonlinear system identification', Neurocomputing, Vol. 47, No. 1/4, pp. 207-240, 2002 https://doi.org/10.1016/S0925-2312(01)00589-6
  4. L. Wang and K. Chen, 'Capture interspeaker information with a neural network for speaker identification', IEEE transactions on neural networks, Vol. 13, No. 2, pp. 436-445, 2002 https://doi.org/10.1109/72.991429
  5. S. A. Vorobyov and A. Cichocki, 'Hyper radial basis function neural networks for interference cancellation with nonlinear processing of reference signal', Digital signal processing, Vol. 11, pp. 204-221, 2001 https://doi.org/10.1006/dspr.2001.0398
  6. H. G Choi and E. B. Shim, 'Enhancement of QRS complex using a neural network based ALE', 22nd Int. Conf. of the IEEE EMB, World Congress on Medical Physics and Biomed. Eng., Vol. 27, No. 6, Chicago, U.S.A., Jul. 2000 https://doi.org/10.1109/IEMBS.2000.897880
  7. D. Bhattacharya and A. Antoniou, 'Design of equripple FIR filters using a feedback neural network', IEEE Transactions on circuits and systems II: analog and digital signal processing, Vol. 45, issue 4, April 1998, pp. 527-531, April 1998, pp. 527-531 https://doi.org/10.1109/82.663813
  8. S. Haykin, Neural Networks: A Comprehensive Foundation, IEEE Press, New York, 1994
  9. A. D. Back and A. C. Tsoi, 'FIR and IIR synapses, a new neural network architecture for time series modeling', Neural Comput., Vol. 3, pp. 375-385, 1991 https://doi.org/10.1162/neco.1991.3.3.375
  10. E. A. Wan, 'Temporal backpropagation for FIR neural networks', in Proc. Int. Joint Conf. Neural Networks, Vol. 1, pp. 575-580, 1990 https://doi.org/10.1109/IJCNN.1990.137629
  11. R. J. Williams and D. Zipser, 'A learning algorithm for continually running fully recurrent neural networks', Neural Comput., Vol. 1, pp. 270-280, 1989 https://doi.org/10.1162/neco.1989.1.2.270
  12. J. L. Elman, 'Finding structure in time', Cognitive Science, Vol. 14, pp. 179-11, 1990 https://doi.org/10.1016/0364-0213(90)90002-E
  13. M. Jordan, 'Serial order: A parallel distributed processing approach', Univ. California San Diego, Inst. Cognitive Science, ICS Rep. 8604, 1986
  14. P. Campolucci, A. Uncini, F. Piazza, and B. D. Rao, 'On-line learning algorithm for locally recurrent neural networks', IEEE Trans. Neural Networks, Vol. 10, pp. 253-271, 1999 https://doi.org/10.1109/72.750549
  15. A. C. Tsoi and A. D. Back, 'Locally recurrent globally feedforward neural networks: A critical review of architectures', IEEE Trans. Neural Networks, Vol. 5, pp. 229-239, 1994 https://doi.org/10.1109/72.279187
  16. H. G. Choi, H. S. Lee, and S. H. Kim, 'Adaptive prediction of nonstationary signals using chaotic neural networks', IEEE IJCNN'98, Alaska, U.S.A., pp. 1943-1947, May 1998 https://doi.org/10.1109/IJCNN.1998.687156
  17. H. G. Choi, H. S. Lee, and S. H. Kim, 'Nonlinear prediction of nonstationary signalsusing neural networks', J. of IEEK, IEEK, Vol. 35, No. 10, pp. 166-174, Nov. 199