Title :
Backpropagation neural networks with short time frequency data
Author_Institution :
Dept. of Electr. Eng., California Univ., Irvine, CA, USA
Abstract :
A major task in signal processing is the determination of the significant frequencies of received waveforms. Radar, sonar, and speech processing all employ techniques that rely on a short time frequency representation of a received waveform. This paper uses a backpropagation neural network to extract information about the presence of a target and, if present, the determination of the dominant frequency in the presence of clutter.
Keywords :
Fourier transforms; backpropagation; neural nets; signal representation; waveform analysis; backpropagation neural networks; clutter; dominant frequency determination; radar processing; received waveforms; short time Fourier transform; short time frequency data; short time frequency representation; signal processing; sonar processing; speech processing; target; Backpropagation; Discrete Fourier transforms; Fourier transforms; Frequency domain analysis; Logistics; Neural networks; Supervised learning; Time frequency analysis; Vectors;
Conference_Titel :
Signals, Systems & Computers, 1998. Conference Record of the Thirty-Second Asilomar Conference on
Conference_Location :
Pacific Grove, CA, USA
Print_ISBN :
0-7803-5148-7
DOI :
10.1109/ACSSC.1998.751545
