Title :
Signal detection with chaotic neural network
Author :
Zhangliang, Xiong ; Yaoliang, Song ; Ming, Liu ; Shi Xiangquan
Author_Institution :
Sch. of Electron. Eng. & Photoelectronic Technol., Nanjing Univ. Sci. & Technol., China
Abstract :
This paper proposes a system model of signal detection in the background of chaotic clutter. In this model, the classical matched filter and single value decomposition (SVD) arithmetic are used to reduce the disturbance of noise. The chaotic neural network based on improvement BP arithmetic and iterative chaotic map with infinite collapses (ICMIC) is used in the approach of the chaotic background clutter and the classical constant false alarm ratio (CFAR) detector is used to ensure CFAR. The results of the analysis and simulation both show this kind of signal detection system based on chaotic neural network has good detecting ability and fine noise immunity.
Keywords :
backpropagation; chaos; clutter; filtering theory; matched filters; neural nets; signal detection; singular value decomposition; chaotic background clutter; chaotic neural network; constant false alarm ratio detector; improvement backpropagation arithmetic; iterative chaotic map with infinite collapses; matched filter; noise immunity; signal detection; single value decomposition arithmetic; Analytical models; Arithmetic; Chaos; Detectors; Iterative methods; Matched filters; Neural networks; Noise reduction; Signal analysis; Signal detection;
Conference_Titel :
Neural Networks and Signal Processing, 2003. Proceedings of the 2003 International Conference on
Conference_Location :
Nanjing
Print_ISBN :
0-7803-7702-8
DOI :
10.1109/ICNNSP.2003.1279237