Download:
by Eric Granger, Marka. Rubin, Stephen Grossberg, Pierre Lavoie, Pdws Pdws Pdws
http://www.livia.etsmtl.ca/publications/2001/nnsp011.pdf
Add To MetaCart
Abstract:
Abstract. A neural network recognition and tracking system is proposed for classification of radar pulses in autonomous Electronic Support Measure systems. Radar type information is combined with position-specific information from active emitters in a scene. Such a What-and-Where fusion strategy is motivated by a similar subdivision of labor in the brain. OVERVIEW A critical function of radar Electronic Support Measures (ESM) [1, 2, 3] is the real-time identification of the radar type associated with each pulse train that is intercepted. In this paper, a newapproach to this task is examined. Type-specific parameters of the input pulse stream are used to classify pulses according to radar type, while environment-specific parameters are used to separate pulses corresponding to active emitters. An ESM system incorporating a neural network recognition system is depicted in Figure 1. First a time of arrival (TOA) deinterleaver uncovers periodicities in the TOA of input pulse description words (PDWs). Whenever grouping of pulses is straightforward, it forms tracks and assigns a track number and a pulse repetition interval (PRI) to each grouped pulse. The neural network recognition system receives all the PDWs, some of which have track numbers and PRI parameters. The neural network outputs a prediction of the radar type for every PDW, and assigns a track number to the PDWs that did not get one from the TOA deinterleaver.
Citations
|
494
|
Statistical Analysis with Missing Data
– Little, Rubin
- 1987
|
|
189
|
Fuzzy ARTMAP: A neural network architecture for incremental supervised learning of analog multidimensional maps
– Carpenter, Grossberg, et al.
- 1992
|
|
188
|
Comparing partitions
– Hubert, Arabie
- 1985
|
|
108
|
Estimation and Tracking
– Bar-Shalom, Li
- 1993
|
|
74
|
Multiple-Target Tracking with Radar Applications
– Blackman
- 1986
|
|
42
|
Learning from incomplete data
– Ghahramani, Jordan
- 1994
|
|
40
|
Semi-supervised clustering using genetic algorithms
– Demiriz, Bennett, et al.
- 1999
|
|
37
|
Fast learning VIEWNET architectures for recognizing 3-D objects from multiple 2-D views
– Bradski, Grossberg
- 1995
|
|
25
|
Fuzzy Clustering with Partial Supervision
– Pedrycz, Waletzky
- 1997
|
|
24
|
ARTMAP-IC and medical diagnosis: instance counting and inconsistent cases
– Carpenter, Markuzon
- 1998
|
|
22
|
STORE working memory networks for storage and recall of arbitrary temporal sequences
– Bradski, Carpenter, et al.
- 1994
|
|
20
|
Partially supervised clustering for image segmentation
– Bensaid, Hall, et al.
- 1996
|
|
8
|
Familiarity discrimination of radar pulses
– Granger, Grossberg, et al.
- 1999
|
|
6
|
Electronic Intelligence: The Analysis of Radar Signals
– Wiley
- 1993
|
|
6
|
The complementary brain: A unifying view of brain specialization and modularity. Trends in Cognitive Sciences
– Grossberg
- 2000
|
|
5
|
Classification of incomplete data using the Fuzzy ARTMAP neural network
– Granger, Rubin, et al.
- 2000
|
|
5
|
ARTMAP-FD: familiarity discrimination applied to radar target recognition
– Carpenter, Rubin, et al.
- 1997
|
|
4
|
Automatic Processing for ESM
– Davies, Hollands
- 1982
|
|
3
|
A what-and-where fusion neural network for recognition and tracking of multiple radar emitters
– Granger, Rubin, et al.
- 2001
|
