论文信息 - A new neural network based sequence estimator in non-Gaussian noise environment

A new neural network based sequence estimator in non-Gaussian noise environment

The application of neural network for sequence estimation in the presence of both impulsive noise and intersymbol interference is presented. In this estimator, a nonlinearity is embedded in the conventional steepest descent method for suppressing the impulse noise during the iteration and thus a dual nonlinear steepest descent algorithm is developed for estimating the symbol sequence. This algorithm can be implemented by a recurrent correlation neural network with highly parallel processing. To further improve the performance, a decision feedback technique is developed. It is shown in computer simulations that the new estimator outperforms the linear Viterbi algorithm particularly when there is impulse noise.

G. G. Bi | S. H. Leung | J. F. Weng

[1] Bing J. Sheu,et al. Maximum likelihood sequence estimation of communication signals by a Hopfield neural network , 1994, Proceedings of 1994 IEEE International Conference on Neural Networks (ICNN'94).

[2] Elias Masry,et al. Constrained adaptive filtering algorithms: Asymptotic convergence properties for dependent data , 1989, IEEE Trans. Inf. Theory.

[3] I. Szentesi,et al. Robust Detectors for Signals in Non-Gaussian Noise , 1977 .

[4] John G. Proakis,et al. Digital Communications , 1983 .

[5] J. Miller,et al. The Detection of Signals in Impulsive Noise Modeled as a Mixture Process , 1976, IEEE Trans. Commun..

[6] G. Pfeiffer. Maximum likelihood sequence estimation of minimum shift keying modulated signals using a Hopfield neural network , 1993, IEEE International Conference on Neural Networks.