International Journal of Fuzzy Logic and Intelligent Systems

Korean Institute of Intelligent Systems (한국지능시스템학회)
권호 표지
DOI QR코드

DOI QR Code

Fuzzy-ART Basis Equalizer for Satellite Nonlinear Channel

  • Lee, Jung-Sik (School of Electronic & Information Eng., Kunsan National University) ;
  • Hwang, Jae-Jeong (School of Electronic & Information Eng., Kunsan National University)
  • Published : 2002.03.01
Download PDF
⟨ Previous Next ⟩

Abstract

This paper discusses the application of fuzzy-ARTMAP neural network to compensate the nonlinearity of satellite communication channel. The fuzzy-ARTMAP is the class of ART(adaptive resonance theory) architectures designed fur supervised loaming. It has capabilities not fecund in other neural network approaches, that includes a small number of parameters, no requirements fur the choice of initial weights, automatic increase of hidden units, and capability of adding new data without retraining previously trained data. By a match tracking process with vigilance parameter, fuzzy-ARTMAP neural network achieves a minimax teaming rule that minimizes predictive error and maximizes generalization. Thus, the system automatically leans a minimal number of recognition categories, or hidden units, to meet accuracy criteria. As a input-converting process for implementing fuzzy-ARTMAP equalizer, the sigmoid function is chosen to convert actual channel output to the proper input values of fuzzy-ARTMAP. Simulation studies are performed over satellite nonlinear channels. QPSK signals with Gaussian noise are generated at random from Volterra model. The performance of proposed fuzzy-ARTMAP equalizer is compared with MLP equalizer.

Keywords

References

  1. S. Benedetto and E. Biglieri, 'Nonlinear Equalization of Digital Satellite Channels,' IEEE Jour. Sel. Areas inCommun., vol. 1, pp. 57-62, Jan., 1983 https://doi.org/10.1109/JSAC.1983.1145885
  2. E. Biglieri, S. Barberis and M. Catena, 'Analysis andCompensations of Nonlinearities in Digital TransmissionSystems,' IEEE Jour. Sel. Areas in Commun., vol. 6,pp. 42-51, Jan., 1988 https://doi.org/10.1109/49.192728
  3. S. Benedetto, E. Biglieri, and R. Daffara, 'Modeling and evaluation of nonlinear satellite links- A Volterra series approach,' IEEE Trans. Aerosp. Electron. Syst., vol. AES-15, pp. 494-506, July 1979 https://doi.org/10.1109/TAES.1979.308734
  4. A. A. M. Saleh, 'Frequency-Independent and Frequency-Dependent Nonlinear Models of TWT Amplifier,' IEEE Trans. Commun., vol. 9, pp. 1715-1720, Nov., 1981
  5. Gibson, G. J., S. Siu, and C. F. N. Cowan, 'Applicationof Multilayer Perceptrons as Adaptive Channel Equalizers,'Proc. IEEE Int. Conf. Acoust, Speech, Signal Processing,Glasgow, Scotland, pp. 1183-1186, 1989
  6. Chen, S., B. Mulgrew, P. M. Grant, 'A Clustering Tech-nique for Digital Communications Channel EqualizationUsing Radial Basis Function Networks,' IEEE Trans. Neural Networks, vol. 4, pp. 570-579, Sep. 1993 https://doi.org/10.1109/72.238312
  7. J. Lee, C. D. Beach, and L. V. Fausett, 'Channel Equali-zation via Fuzzy ARTMAP,' Proc. IEEE, Int. Conf. onSignal Processing Applications & Technology, Boston,Massachusetts, vol. 2, pp. 1397-1401, Oct. 1997
  8. Grossberg, S., 'Adaptive Pattern Classification and Univer-sal Recording: I. Parallel development and Coding of Neural Feature Detectors', Biological Cybernetics, pp.121-134, 1976
  9. G. A. Carpenter and S. Grossberg, 'A Massively Parallel Architecture for a Self-organizing Neural Pattern Recognition Machines,' Computer Vision, Graphics, andImage Processing, vol. 37, pp. 54-115, 1987 https://doi.org/10.1016/S0734-189X(87)80014-2
  10. G. A. Carpenter and S. Grossberg, 'ART2: Stable Self-organization of Pattern Recognition Codes for AnalogInput Patterns,' Applied Optics, vol. 26, pp. 4919-4930, 1987 https://doi.org/10.1364/AO.26.004919
  11. G. A. Carpenter, S. Grossberg and J. H. Reynolds, 'ART-MAP: Supervised Real-time Learning and Classificationof Nonstationary Data by a Self-organizing NeuralNetwork,' Neural Networks, vol. 4, pp. 565-588, 1991 https://doi.org/10.1016/0893-6080(91)90012-T
  12. G. A. Carpenter, S. Grossberg, N. Markuzon, J. H. Rey-nolds, and D. B. Rosen, 'Fuzzy ARTMAP: A NeuralNetwork Architecture for Incremental Supervised learningof Analog Multidimensional Maps,' IEEE Trans. Neural Networks, vol. pp. 698-713, Sep. 1992