Automatic digital modulation recognition based on ART2A-DWNN

Authors:
Zhilu Wu;Xuexia Wang;Cuiyan Liu;Guanghui Ren
Affiliations:
School of Electronics and Information Technology, Harbin Institute of Technology, Harbin, Heilongjiang, China;School of Electronics and Information Technology, Harbin Institute of Technology, Harbin, Heilongjiang, China;School of Electronics and Information Technology, Harbin Institute of Technology, Harbin, Heilongjiang, China;School of Electronics and Information Technology, Harbin Institute of Technology, Harbin, Heilongjiang, China
Venue:
ISNN'05 Proceedings of the Second international conference on Advances in neural networks - Volume Part II
Year:
2005

Citing 1
Cited 4

Comparative analysis of fuzzy ART and ART-2A network clustering performance

IEEE Transactions on Neural Networks

Performance comparison of wavelet families for analog modulation classification using expert discrete wavelet neural network system

Expert Systems with Applications: An International Journal
An expert Discrete Wavelet Adaptive Network Based Fuzzy Inference System for digital modulation recognition

Expert Systems with Applications: An International Journal
Modified ART2A-DWNN for Automatic Digital Modulation Recognition

ISNN '07 Proceedings of the 4th international symposium on Neural Networks: Part II--Advances in Neural Networks
Automatic modulation recognition using wavelet transform and neural networks in wireless systems

EURASIP Journal on Advances in Signal Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

A novel automatic digital modulation recognition classifier combining adaptive resonance theory 2A (ART2A) with discrete wavelet neural network (DWNN), called ART2A-DWNN, is proposed in this paper. The modified ART2A network with a low vigilance parameter is used to categorize input modulation schemes into some classes and then DWNN is employed in each class to recognize modulation schemes. Moreover, error back propagation (BP) learning algorithm with momentum is adopted in DWNN to speed up the training phase and improve the convergence capability. Simulation results obtained from modulated signals corrupted with Gaussian noise at 8dB Signal to Noise Ratio (SNR) are given to evaluate the performance of the proposed method and it is found that the benefits of the developed method include improvement of recognition capability, training convergence enhancement and easiness to accommodate new patterns without forgetting old ones.