Title :
A neural net application to signal identification
Author :
Sverdlove, Ronald
Author_Institution :
David Sarnoff Res. Center, Princeton, NJ, USA
Abstract :
Results from an ongoing research project concerning detection and identification of signals in a relatively quiescent background are discussed. The signals to be identified are of varying duration, and the number of different signal classes is large (> 1,000) and is frequently expanded or reduced. The author´s approach to solving this real-world problem is presented, and initial results are shown
Keywords :
identification; neural nets; signal processing; neural net; quiescent background; real-world problem; signal identification; signal recognition; Data mining; Displays; Laboratories; Neural networks; Signal design; Signal processing; Supervised learning;
Conference_Titel :
Neural Networks for Processing [1993] III. Proceedings of the 1993 IEEE-SP Workshop
Conference_Location :
Linthicum Heights, MD
Print_ISBN :
0-7803-0928-6
DOI :
10.1109/NNSP.1993.471833
